The aim of this study was to assess how manipulating descriptions of
occupations as exposed to risk (vs bored) and/or helpful (vs unhelpful)
would influence correlates of occupational heroism.
H3 & H4: Outcomes ~ Risk x Help
Risk and helpfulness manipulations will both be dummy coded (-0.5,
0.5)
Attitude and heroism will be based on the single item ratings of
participants.
All variable will be standardised for our analyses (centred on zero,
and transformed to have a SD = 1). Statistical Technique
A model comparison approach will be used to assess our main
hypotheses and qualify the part of variance explained by general
attitude (i.e., Halo effect).
For each step of our model‐comparison procedure, we will evaluate two
models: 1) one based on general-level items, 2) one based on
specific-level items,
If an hypothesis is supported at both the general and specific
levels, we will interpret this as full support for the hypothesis. If
only one type of measure supports the hypothesis, we will interpret this
as partial support for the hypothesis.
We will perform independent OLS regression models predicting each of
our target outcomes (i.e., gratitude, criticism acceptability, support
for workers demands, suffering assessment, acceptability of regulations
violation, belief that workers would choose suffering if their mission
required it, belief that workers would agree to be exploited, and
support for exploiting workers when needed) using Risk manipulation,
Helpfulness manipulation, and occupations as predictors.
We will establish four models assessing the effect of our
manipulations while accounting for possible interactions with occupation
types and possible halo effects (see subsection Variable roles for
details on each model). Variable Roles
Model 1 (Heroism effect across occupations): Target construct
(gratitude, criticism acceptability, support for demands, suffering
assessment, acceptability of regulations violation, belief that workers
would choose suffering if their mission required it, belief that workers
would agree to be exploited, or support for exploiting workers when
needed): predicted variable Occupation: covariate Dummy-coded Risk
manipulation: Main predictor Dummy-coded Helpfulness manipulation: Main
predictor Model: Target outcome ~ Occupation + Risk * Helpfulness
Model 2 (Heroism within occupations): Target construct (gratitude,
criticism acceptability, support for demands, suffering assessment,
acceptability of regulations violation, belief that workers would choose
suffering if their mission required it, belief that workers would agree
to be exploited, or support for exploiting workers when needed):
predicted variable Occupation: main predictor and moderator Dummy-coded
Risk manipulation: Main predictor Dummy-coded Helpfulness manipulation:
Main predictor Model: Target outcome ~ Risk * Helpfulness +
Occupation:Risk + Occupation:Helpfulness + Occupation
Model 3 (Heroism effect across occupations and Halo effect): Target
construct (gratitude, criticism acceptability, support for demands,
suffering assessment, acceptability of regulations violation, belief
that workers would choose suffering if their mission required it, belief
that workers would agree to be exploited, or support for exploiting
workers when needed): predicted variable Occupation: covariate Attitude:
Covariate Dummy-coded Risk manipulation: Main predictor Dummy-coded
Helpfulness manipulation: Main predictor Model: Target outcome ~
Occupation + Risk*Helpfulness + Attitude
Model 4 (Heroism within occupations and Halo effect): Target
construct (gratitude, criticism acceptability, support for demands,
suffering assessment,acceptability of regulations violation, belief that
workers would choose suffering if their mission required it, belief that
workers would agree to be exploited, or support for exploiting workers
when needed): predicted variable Occupation: main predictor and
moderator Heroism: Main predictor and moderator Attitude: Covariate
Model: Target outcome ~ Risk * Helpfulness + Occupation:Risk +
Occupation:Helpfulness + Occupation + Attitude
NOTE: for gratitude, belief in self
exploitation, support for exploitation, and victim perception, following
our registration document, we used a global factor. Details on each
subset can be found in the exploratory section.
NOTE, we also registered some diagnostics, as follow:
We will assess the normality of the residual via a Q-Q plot. We will
also check homoscedasticity by plotting fitted values vs residuals. If
any those conditions are not met, we will still report the predicted
analyses (given their robustness to these violations of assumptions),
but will additionally assess if using huber weighted robust regression
(lmrob from the package robustbase) more
robust to assumptions deviations (see Wilcox, 1997) results in
differences in conclusion.
You can toggle details about these assumpation/robustness checks
below.
Toggle details of diagnostics and robustness checks
Below, we assess normality via Q-Q plots, heteroscedasticity via
residuals v fitted values plots, and we compare outputs of robust
regressions (using robustbase) and classic OLS models. As
you can see, homoscedasticity is sometimes not great - residuals’
normality can also sometimes smell fishy. But in almost all cases - our
inferences are robust to using robust models - indicating that models
which are less sensitive to these assumpations provide similar
outputs.
run_model_diagnostics_and_robust <- function(
data,
outcomes = c(
"GlobalGratitude",
"criticism_items_G_mean", "criticism_items_S_mean",
"DemandSupp_G_mean", "DemandSupp_S_mean",
"GlobalVictim",
"Villain_G_mean", "Villain_S_mean",
"Endure_G_mean", "Endure_S_mean",
"SelfExploit_G_mean", "SelfExploit_S_mean",
"GlobalSupportExpl"
),
models_to_run = c(1, 2, 3, 4),
occupation_var = "Cond",
risk_var = "Risk_cond",
help_var = "Help_cond",
attitude_var = "Attitude",
print_summaries = TRUE
) {
if (!requireNamespace("robustbase", quietly = TRUE)) {
stop("Package 'robustbase' is required.")
}
# Formula builders ------------------------------------------------------
f_model_1 <- function(y) {
as.formula(paste0(
y, " ~ ", occupation_var, " + ", risk_var, " * ", help_var
))
}
f_model_2 <- function(y) {
as.formula(paste0(
y, " ~ ", risk_var, " * ", help_var,
" + ", occupation_var, ":", risk_var,
" + ", occupation_var, ":", help_var,
" + ", occupation_var
))
}
f_model_3 <- function(y) {
as.formula(paste0(
y, " ~ ", occupation_var,
" + ", risk_var, " * ", help_var,
" + ", attitude_var
))
}
f_model_4 <- function(y) {
as.formula(paste0(
y, " ~ ", risk_var, " * ", help_var,
" + ", occupation_var, ":", risk_var,
" + ", occupation_var, ":", help_var,
" + ", occupation_var,
" + ", attitude_var
))
}
formula_builders <- list(
"1" = f_model_1,
"2" = f_model_2,
"3" = f_model_3,
"4" = f_model_4
)
results <- list()
for (outcome_name in outcomes) {
results[[outcome_name]] <- list()
for (model_number in models_to_run) {
model_key <- as.character(model_number)
formula_i <- formula_builders[[model_key]](outcome_name)
model_name <- paste0("model_", model_number)
cat("\n====================================================\n")
cat("Outcome:", outcome_name, "\n")
cat("Model:", model_name, "\n")
cat("Formula:", deparse(formula_i), "\n")
cat("====================================================\n")
# Standard OLS model ------------------------------------------------
lm_fit <- lm(formula_i, data = data)
if (print_summaries) {
cat("\n--- lm summary ---\n")
print(summary(lm_fit))
}
# Diagnostic plots for OLS ------------------------------------------
old_par <- par(no.readonly = TRUE)
par(mfrow = c(1, 2))
qqnorm(
resid(lm_fit),
main = paste("QQ plot\n", outcome_name, "-", model_name)
)
qqline(resid(lm_fit))
plot(
fitted(lm_fit),
resid(lm_fit),
xlab = "Fitted values",
ylab = "Residuals",
main = paste("Residuals vs fitted\n", outcome_name, "-", model_name)
)
abline(h = 0, lty = 2)
par(old_par)
# Robust model ------------------------------------------------------
lmrob_fit <- robustbase::lmrob(formula_i, data = data)
if (print_summaries) {
cat("\n--- lmrob summary ---\n")
print(summary(lmrob_fit))
}
results[[outcome_name]][[model_name]] <- list(
formula = formula_i,
lm_fit = lm_fit,
lmrob_fit = lmrob_fit
)
}
}
return(results)
}
diagnostic_results <- run_model_diagnostics_and_robust(
data = scale_scores,
models_to_run = c(1, 2, 3, 4),
print_summaries = TRUE
)
##
## ====================================================
## Outcome: GlobalGratitude
## Model: model_1
## Formula: GlobalGratitude ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.30112 -0.59313 0.03678 0.62718 2.10343
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0002094 0.0241467 0.009 0.99308
## Cond1 -0.0023042 0.0242079 -0.095 0.92419
## Risk_cond 0.1302404 0.0483046 2.696 0.00711 **
## Help_cond 0.2255853 0.0483161 4.669 3.37e-06 ***
## Risk_cond:Help_cond -0.0774810 0.0967730 -0.801 0.42350
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8336 on 1187 degrees of freedom
## Multiple R-squared: 0.02417, Adjusted R-squared: 0.02088
## F-statistic: 7.35 on 4 and 1187 DF, p-value: 7.582e-06
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.32171 -0.59767 0.02469 0.61094 2.11069
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.01264 0.02542 0.497 0.61901
## Cond1 -0.00484 0.02552 -0.190 0.84962
## Risk_cond 0.13476 0.05063 2.662 0.00788 **
## Help_cond 0.24385 0.05069 4.810 1.7e-06 ***
## Risk_cond:Help_cond -0.10055 0.10222 -0.984 0.32549
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.8851
## Multiple R-squared: 0.0264, Adjusted R-squared: 0.02312
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 90 weights are ~= 1. The remaining 1102 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.4713 0.8809 0.9497 0.9175 0.9834 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalGratitude
## Model: model_2
## Formula: GlobalGratitude ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.36223 -0.59019 0.01833 0.62010 2.03441
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.001740 0.024148 0.072 0.9426
## Risk_cond 0.127882 0.048366 2.644 0.0083 **
## Help_cond 0.220581 0.048378 4.560 5.66e-06 ***
## Cond1 -0.002033 0.024193 -0.084 0.9331
## Risk_cond:Help_cond -0.070552 0.096779 -0.729 0.4661
## Risk_cond:Cond1 -0.082185 0.048389 -1.698 0.0897 .
## Help_cond:Cond1 -0.041420 0.048388 -0.856 0.3922
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.833 on 1185 degrees of freedom
## Multiple R-squared: 0.02711, Adjusted R-squared: 0.02218
## F-statistic: 5.503 on 6 and 1185 DF, p-value: 1.239e-05
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.39089 -0.59835 0.01275 0.60512 2.02928
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.014392 0.025370 0.567 0.5706
## Risk_cond 0.130893 0.050897 2.572 0.0102 *
## Help_cond 0.236786 0.050926 4.650 3.7e-06 ***
## Cond1 -0.004195 0.025453 -0.165 0.8691
## Risk_cond:Help_cond -0.093128 0.101976 -0.913 0.3613
## Risk_cond:Cond1 -0.091955 0.050913 -1.806 0.0712 .
## Help_cond:Cond1 -0.051425 0.050887 -1.011 0.3124
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.8831
## Multiple R-squared: 0.02987, Adjusted R-squared: 0.02496
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 98 weights are ~= 1. The remaining 1094 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.4437 0.8846 0.9488 0.9168 0.9825 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalGratitude
## Model: model_3
## Formula: GlobalGratitude ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.19080 -0.44096 0.05308 0.46112 2.35567
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0003964 0.0186570 -0.021 0.983
## Cond1 0.0238073 0.0187270 1.271 0.204
## Risk_cond 0.0357576 0.0374714 0.954 0.340
## Help_cond 0.0332298 0.0379442 0.876 0.381
## Attitude 0.5398395 0.0190588 28.325 <2e-16 ***
## Risk_cond:Help_cond -0.1151371 0.0747837 -1.540 0.124
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6441 on 1186 degrees of freedom
## Multiple R-squared: 0.4179, Adjusted R-squared: 0.4155
## F-statistic: 170.3 on 5 and 1186 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.22083 -0.45472 0.04392 0.44606 2.36523
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.01215 0.01956 0.621 0.535
## Cond1 0.02291 0.01947 1.177 0.240
## Risk_cond 0.04111 0.03854 1.067 0.286
## Help_cond 0.03214 0.03929 0.818 0.414
## Attitude 0.55376 0.01929 28.708 <2e-16 ***
## Risk_cond:Help_cond -0.11550 0.07767 -1.487 0.137
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.6622
## Multiple R-squared: 0.4255, Adjusted R-squared: 0.4231
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 79 weights are ~= 1. The remaining 1113 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1754 0.8826 0.9518 0.9139 0.9848 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalGratitude
## Model: model_4
## Formula: GlobalGratitude ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.19613 -0.44109 0.05417 0.46448 2.35079
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0003946 0.0186861 -0.021 0.983
## Risk_cond 0.0354680 0.0375689 0.944 0.345
## Help_cond 0.0335259 0.0380187 0.882 0.378
## Cond1 0.0237827 0.0187431 1.269 0.205
## Attitude 0.5399996 0.0191515 28.196 <2e-16 ***
## Risk_cond:Help_cond -0.1153202 0.0749054 -1.540 0.124
## Risk_cond:Cond1 0.0054836 0.0375729 0.146 0.884
## Help_cond:Cond1 -0.0039961 0.0374665 -0.107 0.915
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6446 on 1184 degrees of freedom
## Multiple R-squared: 0.4179, Adjusted R-squared: 0.4145
## F-statistic: 121.5 on 7 and 1184 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.22829 -0.45203 0.04429 0.44824 2.35893
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.012051 0.019568 0.616 0.538
## Risk_cond 0.040590 0.038884 1.044 0.297
## Help_cond 0.032840 0.039588 0.830 0.407
## Cond1 0.022804 0.019499 1.169 0.242
## Attitude 0.554171 0.019491 28.432 <2e-16 ***
## Risk_cond:Help_cond -0.116184 0.077701 -1.495 0.135
## Risk_cond:Cond1 0.010546 0.039201 0.269 0.788
## Help_cond:Cond1 -0.001638 0.038986 -0.042 0.966
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.6636
## Multiple R-squared: 0.4253, Adjusted R-squared: 0.4219
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 81 weights are ~= 1. The remaining 1111 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1800 0.8821 0.9508 0.9140 0.9847 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: criticism_items_G_mean
## Model: model_1
## Formula: criticism_items_G_mean ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.9425 -0.7832 -0.0032 0.7463 4.2168
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.66934 0.03186 83.772 < 2e-16 ***
## Cond1 0.07631 0.03195 2.389 0.017058 *
## Risk_cond -0.23439 0.06374 -3.677 0.000247 ***
## Help_cond -0.12105 0.06376 -1.899 0.057857 .
## Risk_cond:Help_cond 0.07643 0.12770 0.599 0.549613
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.1 on 1187 degrees of freedom
## Multiple R-squared: 0.0184, Adjusted R-squared: 0.01509
## F-statistic: 5.563 on 4 and 1187 DF, p-value: 0.0001946
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.88425 -0.74572 0.04642 0.76801 4.26728
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.62812 0.03235 81.252 < 2e-16 ***
## Cond1 0.07577 0.03242 2.337 0.019590 *
## Risk_cond -0.22220 0.06467 -3.436 0.000611 ***
## Help_cond -0.09673 0.06474 -1.494 0.135406
## Risk_cond:Help_cond 0.08361 0.12970 0.645 0.519318
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.162
## Multiple R-squared: 0.01633, Adjusted R-squared: 0.01301
## Convergence in 9 IRWLS iterations
##
## Robustness weights:
## 98 weights are ~= 1. The remaining 1094 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1488 0.8711 0.9502 0.9176 0.9852 0.9988
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: criticism_items_G_mean
## Model: model_2
## Formula: criticism_items_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.9105 -0.7983 0.0121 0.7202 4.2017
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.66851 0.03191 83.634 < 2e-16 ***
## Risk_cond -0.23163 0.06391 -3.625 0.000302 ***
## Help_cond -0.12040 0.06392 -1.884 0.059876 .
## Cond1 0.07635 0.03197 2.388 0.017074 *
## Risk_cond:Help_cond 0.07371 0.12788 0.576 0.564436
## Risk_cond:Cond1 0.01256 0.06394 0.196 0.844261
## Help_cond:Cond1 0.04501 0.06394 0.704 0.481610
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.101 on 1185 degrees of freedom
## Multiple R-squared: 0.01884, Adjusted R-squared: 0.01387
## F-statistic: 3.792 on 6 and 1185 DF, p-value: 0.0009513
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.84894 -0.74501 0.04633 0.73820 4.25499
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.62750 0.03232 81.288 < 2e-16 ***
## Risk_cond -0.22013 0.06483 -3.395 0.000708 ***
## Help_cond -0.09466 0.06490 -1.459 0.144951
## Cond1 0.07534 0.03243 2.323 0.020327 *
## Risk_cond:Help_cond 0.08064 0.12964 0.622 0.534039
## Risk_cond:Cond1 0.03185 0.06480 0.492 0.623154
## Help_cond:Cond1 0.03105 0.06481 0.479 0.631963
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.164
## Multiple R-squared: 0.01668, Adjusted R-squared: 0.0117
## Convergence in 9 IRWLS iterations
##
## Robustness weights:
## 85 weights are ~= 1. The remaining 1107 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1527 0.8753 0.9555 0.9188 0.9853 0.9988
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: criticism_items_G_mean
## Model: model_3
## Formula: criticism_items_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5290 -0.6423 -0.0491 0.5721 5.1462
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.66999 0.02729 97.841 <2e-16 ***
## Cond1 0.04827 0.02739 1.762 0.0783 .
## Risk_cond -0.13293 0.05481 -2.425 0.0154 *
## Help_cond 0.08550 0.05550 1.540 0.1237
## Attitude -0.57968 0.02788 -20.794 <2e-16 ***
## Risk_cond:Help_cond 0.11687 0.10938 1.068 0.2856
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9421 on 1186 degrees of freedom
## Multiple R-squared: 0.2807, Adjusted R-squared: 0.2776
## F-statistic: 92.55 on 5 and 1186 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.559652 -0.585040 -0.007434 0.596595 5.247062
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.64050 0.02769 95.345 <2e-16 ***
## Cond1 0.04878 0.02749 1.774 0.0762 .
## Risk_cond -0.12236 0.05468 -2.238 0.0254 *
## Help_cond 0.13207 0.05552 2.379 0.0175 *
## Attitude -0.61000 0.03163 -19.286 <2e-16 ***
## Risk_cond:Help_cond 0.11945 0.10929 1.093 0.2746
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.8885
## Multiple R-squared: 0.3077, Adjusted R-squared: 0.3048
## Convergence in 11 IRWLS iterations
##
## Robustness weights:
## observation 506 is an outlier with |weight| = 0 ( < 8.4e-05);
## 94 weights are ~= 1. The remaining 1097 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.02075 0.86830 0.94970 0.90080 0.98500 0.99900
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: criticism_items_G_mean
## Model: model_4
## Formula: criticism_items_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4985 -0.6709 -0.0375 0.5734 5.1864
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.67081 0.02731 97.810 <2e-16 ***
## Risk_cond -0.13185 0.05490 -2.402 0.0165 *
## Help_cond 0.08156 0.05556 1.468 0.1423
## Cond1 0.04848 0.02739 1.770 0.0770 .
## Attitude -0.58303 0.02799 -20.833 <2e-16 ***
## Risk_cond:Help_cond 0.12205 0.10946 1.115 0.2651
## Risk_cond:Cond1 -0.08209 0.05491 -1.495 0.1351
## Help_cond:Cond1 0.00460 0.05475 0.084 0.9331
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.942 on 1184 degrees of freedom
## Multiple R-squared: 0.282, Adjusted R-squared: 0.2778
## F-statistic: 66.44 on 7 and 1184 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.55400 -0.61508 -0.02272 0.60286 5.30005
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.64188 0.02771 95.335 <2e-16 ***
## Risk_cond -0.12311 0.05473 -2.249 0.0247 *
## Help_cond 0.12969 0.05557 2.334 0.0198 *
## Cond1 0.04909 0.02748 1.787 0.0742 .
## Attitude -0.61387 0.03177 -19.320 <2e-16 ***
## Risk_cond:Help_cond 0.12308 0.10925 1.127 0.2602
## Risk_cond:Cond1 -0.06715 0.05505 -1.220 0.2228
## Help_cond:Cond1 -0.03494 0.05483 -0.637 0.5241
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.89
## Multiple R-squared: 0.3088, Adjusted R-squared: 0.3047
## Convergence in 11 IRWLS iterations
##
## Robustness weights:
## observation 506 is an outlier with |weight| = 0 ( < 8.4e-05);
## 81 weights are ~= 1. The remaining 1110 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.02363 0.86630 0.95260 0.90240 0.98300 0.99890
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: criticism_items_S_mean
## Model: model_1
## Formula: criticism_items_S_mean ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3565 -0.7485 -0.2263 0.6694 2.7628
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.2918609 0.0257267 89.085 <2e-16 ***
## Cond1 0.0494503 0.0257894 1.917 0.0554 .
## Risk_cond 0.0213135 0.0514644 0.414 0.6788
## Help_cond 0.0008514 0.0514764 0.017 0.9868
## Risk_cond:Help_cond -0.0199516 0.1031002 -0.194 0.8466
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8877 on 1186 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.00335, Adjusted R-squared: -1.129e-05
## F-statistic: 0.9966 on 4 and 1186 DF, p-value: 0.4083
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.3408 -0.7107 -0.2063 0.6938 2.8064
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.266000 0.028153 80.488 <2e-16 ***
## Cond1 0.056299 0.027775 2.027 0.0429 *
## Risk_cond 0.019542 0.055062 0.355 0.7227
## Help_cond -0.015068 0.055012 -0.274 0.7842
## Risk_cond:Help_cond -0.004815 0.110414 -0.044 0.9652
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.9522
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.003914, Adjusted R-squared: 0.0005546
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.3651 0.8619 0.9505 0.9247 0.9913 0.9975
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.396e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: criticism_items_S_mean
## Model: model_2
## Formula: criticism_items_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3858 -0.7508 -0.2246 0.6930 2.7291
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.292056 0.025758 88.985 <2e-16 ***
## Risk_cond 0.019178 0.051589 0.372 0.7101
## Help_cond 0.002764 0.051602 0.054 0.9573
## Cond1 0.049254 0.025804 1.909 0.0565 .
## Risk_cond:Help_cond -0.020350 0.103226 -0.197 0.8438
## Risk_cond:Cond1 0.029110 0.051613 0.564 0.5729
## Help_cond:Cond1 -0.033314 0.051611 -0.645 0.5187
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8882 on 1184 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.003977, Adjusted R-squared: -0.001071
## F-statistic: 0.7878 on 6 and 1184 DF, p-value: 0.5795
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.3705 -0.7060 -0.2060 0.7247 2.7700
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.265665 0.028254 80.188 <2e-16 ***
## Risk_cond 0.016806 0.055395 0.303 0.7616
## Help_cond -0.011843 0.055361 -0.214 0.8306
## Cond1 0.055943 0.027776 2.014 0.0442 *
## Risk_cond:Help_cond -0.005252 0.110739 -0.047 0.9622
## Risk_cond:Cond1 0.038184 0.055467 0.688 0.4913
## Help_cond:Cond1 -0.028355 0.055444 -0.511 0.6092
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.9504
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.004561, Adjusted R-squared: -0.0004836
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.3757 0.8618 0.9497 0.9245 0.9924 0.9983
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.396e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: criticism_items_S_mean
## Model: model_3
## Formula: criticism_items_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.20829 -0.65575 -0.08522 0.60028 3.05005
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.292163 0.024950 91.871 <2e-16 ***
## Cond1 0.038660 0.025041 1.544 0.123
## Risk_cond 0.060084 0.050108 1.199 0.231
## Help_cond 0.079892 0.050738 1.575 0.116
## Attitude -0.222115 0.025477 -8.718 <2e-16 ***
## Risk_cond:Help_cond -0.004258 0.100003 -0.043 0.966
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8609 on 1185 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.06342, Adjusted R-squared: 0.05947
## F-statistic: 16.05 on 5 and 1185 DF, p-value: 2.486e-15
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.31233 -0.62888 -0.08996 0.63443 3.12011
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.268089 0.026889 84.349 <2e-16 ***
## Cond1 0.045929 0.026684 1.721 0.0855 .
## Risk_cond 0.056811 0.052825 1.075 0.2824
## Help_cond 0.080493 0.054300 1.482 0.1385
## Attitude -0.249742 0.029316 -8.519 <2e-16 ***
## Risk_cond:Help_cond 0.001862 0.105722 0.018 0.9860
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.8967
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.0744, Adjusted R-squared: 0.07049
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 92 weights are ~= 1. The remaining 1099 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2010 0.8762 0.9491 0.9142 0.9845 0.9988
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.396e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: criticism_items_S_mean
## Model: model_4
## Formula: criticism_items_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.2437 -0.6601 -0.1057 0.5981 3.0291
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.292971 0.024978 91.800 <2e-16 ***
## Risk_cond 0.057323 0.050217 1.142 0.254
## Help_cond 0.080037 0.050817 1.575 0.116
## Cond1 0.038551 0.025053 1.539 0.124
## Attitude -0.223256 0.025590 -8.724 <2e-16 ***
## Risk_cond:Help_cond -0.001720 0.100123 -0.017 0.986
## Risk_cond:Cond1 -0.007075 0.050221 -0.141 0.888
## Help_cond:Cond1 -0.048727 0.050079 -0.973 0.331
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8613 on 1183 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.06419, Adjusted R-squared: 0.05865
## F-statistic: 11.59 on 7 and 1183 DF, p-value: 2.605e-14
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.34385 -0.65383 -0.07139 0.60677 3.09977
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.269152 0.027055 83.872 <2e-16 ***
## Risk_cond 0.053939 0.053181 1.014 0.3107
## Help_cond 0.081643 0.054573 1.496 0.1349
## Cond1 0.045638 0.026677 1.711 0.0874 .
## Attitude -0.250757 0.029621 -8.466 <2e-16 ***
## Risk_cond:Help_cond 0.005787 0.106203 0.054 0.9566
## Risk_cond:Cond1 -0.005168 0.053689 -0.096 0.9233
## Help_cond:Cond1 -0.043963 0.053346 -0.824 0.4100
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.8984
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.07485, Adjusted R-squared: 0.06938
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 94 weights are ~= 1. The remaining 1097 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2095 0.8802 0.9469 0.9144 0.9853 0.9989
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.396e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: DemandSupp_G_mean
## Model: model_1
## Formula: DemandSupp_G_mean ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1920 -0.9312 0.0688 0.9635 3.2243
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.984409 0.040951 97.297 < 2e-16 ***
## Cond1 0.130382 0.041055 3.176 0.00153 **
## Risk_cond 0.005219 0.081921 0.064 0.94922
## Help_cond 0.001122 0.081941 0.014 0.98908
## Risk_cond:Help_cond -0.300512 0.164121 -1.831 0.06734 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.414 on 1187 degrees of freedom
## Multiple R-squared: 0.01186, Adjusted R-squared: 0.00853
## F-statistic: 3.562 on 4 and 1187 DF, p-value: 0.006761
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.22572 -0.93726 0.06274 0.93462 3.22308
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.996779 0.043110 92.712 < 2e-16 ***
## Cond1 0.144229 0.042992 3.355 0.000819 ***
## Risk_cond 0.009077 0.085860 0.106 0.915820
## Help_cond -0.012964 0.085882 -0.151 0.880039
## Risk_cond:Help_cond -0.294746 0.171251 -1.721 0.085487 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.371
## Multiple R-squared: 0.01339, Adjusted R-squared: 0.01006
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 183 weights are ~= 1. The remaining 1009 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.5590 0.8274 0.9453 0.8933 0.9709 0.9980
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: DemandSupp_G_mean
## Model: model_2
## Formula: DemandSupp_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1967 -0.9412 0.0588 0.9731 3.2265
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.9841392 0.0410145 97.140 < 2e-16 ***
## Risk_cond 0.0063438 0.0821470 0.077 0.93846
## Help_cond 0.0010175 0.0821684 0.012 0.99012
## Cond1 0.1304235 0.0410907 3.174 0.00154 **
## Risk_cond:Help_cond -0.3012370 0.1643759 -1.833 0.06711 .
## Risk_cond:Cond1 -0.0008511 0.0821874 -0.010 0.99174
## Help_cond:Cond1 0.0181194 0.0821850 0.220 0.82554
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.415 on 1185 degrees of freedom
## Multiple R-squared: 0.0119, Adjusted R-squared: 0.006898
## F-statistic: 2.379 on 6 and 1185 DF, p-value: 0.02737
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.22131 -0.95734 0.04266 0.94322 3.23524
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.996401 0.043198 92.514 < 2e-16 ***
## Risk_cond 0.010522 0.085894 0.122 0.902526
## Help_cond -0.014028 0.085926 -0.163 0.870339
## Cond1 0.144258 0.042966 3.358 0.000811 ***
## Risk_cond:Help_cond -0.296213 0.171580 -1.726 0.084540 .
## Risk_cond:Cond1 -0.007292 0.085976 -0.085 0.932421
## Help_cond:Cond1 0.030446 0.085936 0.354 0.723188
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.373
## Multiple R-squared: 0.0135, Adjusted R-squared: 0.008501
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 183 weights are ~= 1. The remaining 1009 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.5583 0.8292 0.9448 0.8937 0.9709 0.9979
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: DemandSupp_G_mean
## Model: model_3
## Formula: DemandSupp_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2300 -0.9511 0.0291 0.9693 3.2711
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.98444 0.04096 97.276 < 2e-16 ***
## Cond1 0.12898 0.04111 3.137 0.00175 **
## Risk_cond 0.01029 0.08227 0.125 0.90046
## Help_cond 0.01145 0.08330 0.137 0.89070
## Attitude -0.02899 0.04184 -0.693 0.48861
## Risk_cond:Help_cond -0.29849 0.16418 -1.818 0.06931 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.414 on 1186 degrees of freedom
## Multiple R-squared: 0.01226, Adjusted R-squared: 0.008095
## F-statistic: 2.944 on 5 and 1186 DF, p-value: 0.01198
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.23760 -0.94694 0.04064 0.94256 3.25635
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.996365 0.043151 92.614 < 2e-16 ***
## Cond1 0.143243 0.043003 3.331 0.000892 ***
## Risk_cond 0.011737 0.085480 0.137 0.890810
## Help_cond -0.004755 0.087386 -0.054 0.956612
## Attitude -0.023280 0.048096 -0.484 0.628459
## Risk_cond:Help_cond -0.292053 0.171561 -1.702 0.088955 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.372
## Multiple R-squared: 0.01362, Adjusted R-squared: 0.009465
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 183 weights are ~= 1. The remaining 1009 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.5526 0.8286 0.9449 0.8935 0.9713 0.9986
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: DemandSupp_G_mean
## Model: model_4
## Formula: DemandSupp_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2400 -0.9561 0.0293 0.9695 3.2664
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.984254 0.041024 97.120 < 2e-16 ***
## Risk_cond 0.011296 0.082480 0.137 0.89109
## Help_cond 0.011041 0.083467 0.132 0.89478
## Cond1 0.129040 0.041149 3.136 0.00176 **
## Attitude -0.028937 0.042046 -0.688 0.49144
## Risk_cond:Help_cond -0.298838 0.164449 -1.817 0.06944 .
## Risk_cond:Cond1 -0.005549 0.082489 -0.067 0.94638
## Help_cond:Cond1 0.016114 0.082255 0.196 0.84472
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.415 on 1184 degrees of freedom
## Multiple R-squared: 0.0123, Adjusted R-squared: 0.006456
## F-statistic: 2.106 on 7 and 1184 DF, p-value: 0.04034
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.25652 -0.96698 0.02194 0.94024 3.25908
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.996060 0.043228 92.440 < 2e-16 ***
## Risk_cond 0.013262 0.085562 0.155 0.876845
## Help_cond -0.005911 0.087477 -0.068 0.946142
## Cond1 0.143277 0.042978 3.334 0.000883 ***
## Attitude -0.023385 0.048140 -0.486 0.627213
## Risk_cond:Help_cond -0.293246 0.171931 -1.706 0.088345 .
## Risk_cond:Cond1 -0.010971 0.086227 -0.127 0.898779
## Help_cond:Cond1 0.029205 0.085896 0.340 0.733917
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.375
## Multiple R-squared: 0.01374, Adjusted R-squared: 0.007904
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 183 weights are ~= 1. The remaining 1009 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.5535 0.8281 0.9456 0.8939 0.9713 0.9988
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: DemandSupp_S_mean
## Model: model_1
## Formula: DemandSupp_S_mean ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.2271 -0.7463 0.1360 0.8047 2.3047
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.982093 0.036292 137.278 < 2e-16 ***
## Cond1 -0.197811 0.036384 -5.437 6.58e-08 ***
## Risk_cond 0.126926 0.072601 1.748 0.0807 .
## Help_cond 0.009214 0.072618 0.127 0.8991
## Risk_cond:Help_cond -0.083586 0.145448 -0.575 0.5656
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.253 on 1187 degrees of freedom
## Multiple R-squared: 0.02648, Adjusted R-squared: 0.02319
## F-statistic: 8.07 on 4 and 1187 DF, p-value: 2.027e-06
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -4.31741 -0.80189 0.02824 0.73371 2.23371
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.06885 0.03524 143.837 < 2e-16 ***
## Cond1 -0.17282 0.03506 -4.929 9.42e-07 ***
## Risk_cond 0.13596 0.06993 1.944 0.0521 .
## Help_cond 0.06951 0.07027 0.989 0.3228
## Risk_cond:Help_cond -0.10799 0.14008 -0.771 0.4409
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.166
## Multiple R-squared: 0.02475, Adjusted R-squared: 0.02146
## Convergence in 9 IRWLS iterations
##
## Robustness weights:
## 126 weights are ~= 1. The remaining 1066 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1411 0.8748 0.9479 0.8946 0.9851 0.9978
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: DemandSupp_S_mean
## Model: model_2
## Formula: DemandSupp_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.3130 -0.7200 0.1005 0.7886 2.2886
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.984535 0.036298 137.323 < 2e-16 ***
## Risk_cond 0.119358 0.072700 1.642 0.1009
## Help_cond 0.006526 0.072719 0.090 0.9285
## Cond1 -0.197859 0.036365 -5.441 6.44e-08 ***
## Risk_cond:Help_cond -0.075194 0.145473 -0.517 0.6053
## Risk_cond:Cond1 -0.048826 0.072736 -0.671 0.5022
## Help_cond:Cond1 -0.124121 0.072734 -1.707 0.0882 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.252 on 1185 degrees of freedom
## Multiple R-squared: 0.02921, Adjusted R-squared: 0.02429
## F-statistic: 5.942 on 6 and 1185 DF, p-value: 3.969e-06
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -4.39898 -0.84168 -0.00281 0.71121 2.15832
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.07042 0.03510 144.469 < 2e-16 ***
## Risk_cond 0.12681 0.06995 1.813 0.0701 .
## Help_cond 0.06395 0.07034 0.909 0.3634
## Cond1 -0.17442 0.03502 -4.980 7.29e-07 ***
## Risk_cond:Help_cond -0.10496 0.13969 -0.751 0.4526
## Risk_cond:Cond1 -0.03586 0.06980 -0.514 0.6075
## Help_cond:Cond1 -0.13413 0.06991 -1.919 0.0553 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.165
## Multiple R-squared: 0.02827, Adjusted R-squared: 0.02335
## Convergence in 9 IRWLS iterations
##
## Robustness weights:
## 110 weights are ~= 1. The remaining 1082 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1228 0.8729 0.9510 0.8962 0.9835 0.9987
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: DemandSupp_S_mean
## Model: model_3
## Formula: DemandSupp_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.6665 -0.5927 0.0743 0.8335 2.6518
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.98164 0.03443 144.695 < 2e-16 ***
## Cond1 -0.17819 0.03456 -5.156 2.95e-07 ***
## Risk_cond 0.05595 0.06915 0.809 0.4186
## Help_cond -0.13529 0.07002 -1.932 0.0536 .
## Attitude 0.40555 0.03517 11.531 < 2e-16 ***
## Risk_cond:Help_cond -0.11188 0.13800 -0.811 0.4177
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.189 on 1186 degrees of freedom
## Multiple R-squared: 0.1246, Adjusted R-squared: 0.1209
## F-statistic: 33.77 on 5 and 1186 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -4.726481 -0.691767 -0.005724 0.704129 2.533021
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.06846 0.03404 148.911 < 2e-16 ***
## Cond1 -0.15417 0.03312 -4.656 3.59e-06 ***
## Risk_cond 0.08274 0.06568 1.260 0.208
## Help_cond -0.08836 0.06875 -1.285 0.199
## Attitude 0.39472 0.03757 10.508 < 2e-16 ***
## Risk_cond:Help_cond -0.12188 0.13217 -0.922 0.357
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.059
## Multiple R-squared: 0.1307, Adjusted R-squared: 0.1271
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 106 weights are ~= 1. The remaining 1086 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.008397 0.852300 0.950500 0.888300 0.985300 0.998800
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: DemandSupp_S_mean
## Model: model_4
## Formula: DemandSupp_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.7261 -0.5758 0.0920 0.7907 2.5975
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.98294 0.03445 144.627 < 2e-16 ***
## Risk_cond 0.05012 0.06927 0.724 0.4695
## Help_cond -0.13362 0.07010 -1.906 0.0569 .
## Cond1 -0.17852 0.03456 -5.166 2.81e-07 ***
## Attitude 0.40458 0.03531 11.457 < 2e-16 ***
## Risk_cond:Help_cond -0.10874 0.13811 -0.787 0.4313
## Risk_cond:Cond1 0.01686 0.06928 0.243 0.8078
## Help_cond:Cond1 -0.09608 0.06908 -1.391 0.1645
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.189 on 1184 degrees of freedom
## Multiple R-squared: 0.1261, Adjusted R-squared: 0.1209
## F-statistic: 24.41 on 7 and 1184 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -4.80931 -0.68627 0.02747 0.71206 2.46076
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.06922 0.03392 149.437 < 2e-16 ***
## Risk_cond 0.07556 0.06575 1.149 0.2507
## Help_cond -0.08837 0.06865 -1.287 0.1983
## Cond1 -0.15548 0.03308 -4.700 2.91e-06 ***
## Attitude 0.39499 0.03766 10.487 < 2e-16 ***
## Risk_cond:Help_cond -0.12220 0.13179 -0.927 0.3540
## Risk_cond:Cond1 0.03807 0.06628 0.574 0.5658
## Help_cond:Cond1 -0.11535 0.06585 -1.752 0.0801 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.061
## Multiple R-squared: 0.1337, Adjusted R-squared: 0.1286
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 128 weights are ~= 1. The remaining 1064 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.004066 0.858500 0.948500 0.886700 0.984000 0.999000
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalVictim
## Model: model_1
## Formula: GlobalVictim ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.44446 -0.53092 -0.00233 0.52292 2.56463
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0007449 0.0230606 -0.032 0.974
## Cond1 -0.1447419 0.0231191 -6.261 5.35e-10 ***
## Risk_cond 0.3091352 0.0461321 6.701 3.19e-11 ***
## Help_cond -0.0502585 0.0461431 -1.089 0.276
## Risk_cond:Help_cond -0.0966867 0.0924206 -1.046 0.296
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7961 on 1187 degrees of freedom
## Multiple R-squared: 0.06658, Adjusted R-squared: 0.06343
## F-statistic: 21.17 on 4 and 1187 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.4535200 -0.5195845 -0.0008129 0.5158726 2.5625758
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.001934 0.023524 -0.082 0.934
## Cond1 -0.133828 0.023630 -5.663 1.86e-08 ***
## Risk_cond 0.317473 0.047005 6.754 2.25e-11 ***
## Help_cond -0.054923 0.047073 -1.167 0.244
## Risk_cond:Help_cond -0.092015 0.094275 -0.976 0.329
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.7706
## Multiple R-squared: 0.06558, Adjusted R-squared: 0.06243
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 96 weights are ~= 1. The remaining 1096 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2462 0.8619 0.9520 0.9025 0.9867 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalVictim
## Model: model_2
## Formula: GlobalVictim ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.41368 -0.52475 -0.01441 0.49911 2.59350
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.001706 0.023072 -0.074 0.941
## Risk_cond 0.309636 0.046211 6.701 3.20e-11 ***
## Help_cond -0.045752 0.046223 -0.990 0.322
## Cond1 -0.145036 0.023115 -6.275 4.91e-10 ***
## Risk_cond:Help_cond -0.101724 0.092468 -1.100 0.272
## Risk_cond:Cond1 0.072807 0.046233 1.575 0.116
## Help_cond:Cond1 0.011061 0.046232 0.239 0.811
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7959 on 1185 degrees of freedom
## Multiple R-squared: 0.06856, Adjusted R-squared: 0.06385
## F-statistic: 14.54 on 6 and 1185 DF, p-value: 4.592e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.418318 -0.525988 -0.003531 0.505939 2.598132
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.002609 0.023510 -0.111 0.912
## Risk_cond 0.318066 0.047070 6.757 2.20e-11 ***
## Help_cond -0.050823 0.047153 -1.078 0.281
## Cond1 -0.134477 0.023620 -5.693 1.57e-08 ***
## Risk_cond:Help_cond -0.095482 0.094243 -1.013 0.311
## Risk_cond:Cond1 0.067516 0.047101 1.433 0.152
## Help_cond:Cond1 -0.006187 0.047136 -0.131 0.896
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.7691
## Multiple R-squared: 0.06758, Adjusted R-squared: 0.06286
## Convergence in 11 IRWLS iterations
##
## Robustness weights:
## 110 weights are ~= 1. The remaining 1082 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2305 0.8567 0.9502 0.9010 0.9863 0.9989
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalVictim
## Model: model_3
## Formula: GlobalVictim ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.31638 -0.47580 0.01706 0.48309 2.40265
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.001076 0.021492 -0.050 0.960077
## Cond1 -0.130469 0.021572 -6.048 1.96e-09 ***
## Risk_cond 0.257491 0.043165 5.965 3.22e-09 ***
## Help_cond -0.155400 0.043709 -3.555 0.000392 ***
## Attitude 0.295075 0.021954 13.440 < 2e-16 ***
## Risk_cond:Help_cond -0.117269 0.086146 -1.361 0.173682
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7419 on 1186 degrees of freedom
## Multiple R-squared: 0.19, Adjusted R-squared: 0.1865
## F-statistic: 55.62 on 5 and 1186 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.33989 -0.47868 0.01207 0.48177 2.38465
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0007872 0.0218640 0.036 0.971283
## Cond1 -0.1231878 0.0219768 -5.605 2.58e-08 ***
## Risk_cond 0.2719631 0.0438047 6.209 7.38e-10 ***
## Help_cond -0.1620978 0.0440813 -3.677 0.000246 ***
## Attitude 0.3044101 0.0248098 12.270 < 2e-16 ***
## Risk_cond:Help_cond -0.1149015 0.0878234 -1.308 0.191017
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.7168
## Multiple R-squared: 0.1992, Adjusted R-squared: 0.1958
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 115 weights are ~= 1. The remaining 1077 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2458 0.8651 0.9487 0.9006 0.9856 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalVictim
## Model: model_4
## Formula: GlobalVictim ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.36183 -0.49221 0.00904 0.46609 2.32559
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.002895 0.021449 -0.135 0.892675
## Risk_cond 0.258170 0.043124 5.987 2.84e-09 ***
## Help_cond -0.149925 0.043640 -3.435 0.000612 ***
## Cond1 -0.130660 0.021515 -6.073 1.69e-09 ***
## Attitude 0.300729 0.021983 13.680 < 2e-16 ***
## Risk_cond:Help_cond -0.126656 0.085982 -1.473 0.141002
## Risk_cond:Cond1 0.121630 0.043129 2.820 0.004880 **
## Help_cond:Cond1 0.031903 0.043007 0.742 0.458353
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7399 on 1184 degrees of freedom
## Multiple R-squared: 0.1957, Adjusted R-squared: 0.1909
## F-statistic: 41.15 on 7 and 1184 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.392432 -0.486363 0.006199 0.475777 2.340421
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0008667 0.0217923 -0.040 0.968284
## Risk_cond 0.2720462 0.0438430 6.205 7.55e-10 ***
## Help_cond -0.1543484 0.0440006 -3.508 0.000469 ***
## Cond1 -0.1240608 0.0218965 -5.666 1.84e-08 ***
## Attitude 0.3107277 0.0248139 12.522 < 2e-16 ***
## Risk_cond:Help_cond -0.1239101 0.0876186 -1.414 0.157566
## Risk_cond:Cond1 0.1259772 0.0439588 2.866 0.004233 **
## Help_cond:Cond1 0.0185978 0.0439064 0.424 0.671950
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.7134
## Multiple R-squared: 0.206, Adjusted R-squared: 0.2013
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 107 weights are ~= 1. The remaining 1085 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2378 0.8639 0.9486 0.9011 0.9864 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Villain_G_mean
## Model: model_1
## Formula: Villain_G_mean ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.0202 -0.8080 0.0188 0.9043 3.3129
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.8534028 0.0367392 104.885 < 2e-16 ***
## Cond1 0.1288977 0.0368324 3.500 0.000483 ***
## Risk_cond -0.0004371 0.0734957 -0.006 0.995256
## Help_cond -0.0384674 0.0735132 -0.523 0.600883
## Risk_cond:Help_cond 0.0736009 0.1472405 0.500 0.617261
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.268 on 1187 degrees of freedom
## Multiple R-squared: 0.01042, Adjusted R-squared: 0.00709
## F-statistic: 3.126 on 4 and 1187 DF, p-value: 0.01431
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.05052 -0.82921 0.02629 0.87650 3.31402
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.85997 0.03849 100.292 < 2e-16 ***
## Cond1 0.13018 0.03850 3.381 0.000745 ***
## Risk_cond -0.01656 0.07658 -0.216 0.828866
## Help_cond -0.06025 0.07658 -0.787 0.431610
## Risk_cond:Help_cond 0.08787 0.15283 0.575 0.565426
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.271
## Multiple R-squared: 0.01069, Adjusted R-squared: 0.007359
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 121 weights are ~= 1. The remaining 1071 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.4766 0.8581 0.9473 0.9056 0.9796 0.9975
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Villain_G_mean
## Model: model_2
## Formula: Villain_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.0550 -0.7905 0.0511 0.9067 3.2655
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.854543 0.036765 104.844 < 2e-16 ***
## Risk_cond -0.006678 0.073635 -0.091 0.927757
## Help_cond -0.035955 0.073654 -0.488 0.625531
## Cond1 0.128532 0.036833 3.490 0.000502 ***
## Risk_cond:Help_cond 0.075624 0.147344 0.513 0.607875
## Risk_cond:Cond1 0.035769 0.073672 0.486 0.627396
## Help_cond:Cond1 -0.099248 0.073669 -1.347 0.178172
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.268 on 1185 degrees of freedom
## Multiple R-squared: 0.01215, Adjusted R-squared: 0.007146
## F-statistic: 2.429 on 6 and 1185 DF, p-value: 0.02445
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.10323 -0.79838 0.07321 0.89677 3.25310
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.86232 0.03862 100.007 <2e-16 ***
## Risk_cond -0.02362 0.07687 -0.307 0.7587
## Help_cond -0.05521 0.07689 -0.718 0.4729
## Cond1 0.12936 0.03848 3.362 0.0008 ***
## Risk_cond:Help_cond 0.09333 0.15320 0.609 0.5425
## Risk_cond:Cond1 0.01992 0.07709 0.258 0.7961
## Help_cond:Cond1 -0.11753 0.07714 -1.524 0.1279
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.258
## Multiple R-squared: 0.0128, Adjusted R-squared: 0.007797
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 121 weights are ~= 1. The remaining 1071 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.4835 0.8603 0.9512 0.9040 0.9818 0.9973
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Villain_G_mean
## Model: model_3
## Formula: Villain_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3465 -0.8157 0.0812 0.8552 3.4522
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.85314 0.03616 106.554 < 2e-16 ***
## Cond1 0.14009 0.03630 3.860 0.00012 ***
## Risk_cond -0.04093 0.07263 -0.564 0.57312
## Help_cond -0.12092 0.07354 -1.644 0.10042
## Attitude 0.23139 0.03694 6.264 5.24e-10 ***
## Risk_cond:Help_cond 0.05746 0.14495 0.396 0.69186
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.248 on 1186 degrees of freedom
## Multiple R-squared: 0.04211, Adjusted R-squared: 0.03807
## F-statistic: 10.43 on 5 and 1186 DF, p-value: 8.278e-10
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.38333 -0.82952 0.06375 0.82983 3.44023
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.87315 0.03860 100.335 < 2e-16 ***
## Cond1 0.13487 0.03790 3.558 0.000388 ***
## Risk_cond -0.04740 0.07512 -0.631 0.528177
## Help_cond -0.14324 0.07657 -1.871 0.061641 .
## Attitude 0.24161 0.04249 5.687 1.63e-08 ***
## Risk_cond:Help_cond 0.05897 0.15084 0.391 0.695936
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.25
## Multiple R-squared: 0.04311, Adjusted R-squared: 0.03907
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 98 weights are ~= 1. The remaining 1094 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.4289 0.8725 0.9502 0.9075 0.9853 0.9988
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Villain_G_mean
## Model: model_4
## Formula: Villain_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.4226 -0.8523 0.0803 0.8610 3.3686
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.85362 0.03618 106.506 < 2e-16 ***
## Risk_cond -0.04656 0.07275 -0.640 0.522303
## Help_cond -0.11667 0.07362 -1.585 0.113260
## Cond1 0.13967 0.03629 3.849 0.000125 ***
## Attitude 0.23302 0.03708 6.284 4.64e-10 ***
## Risk_cond:Help_cond 0.05631 0.14504 0.388 0.697936
## Risk_cond:Cond1 0.07360 0.07275 1.012 0.311917
## Help_cond:Cond1 -0.08310 0.07255 -1.145 0.252257
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.248 on 1184 degrees of freedom
## Multiple R-squared: 0.04403, Adjusted R-squared: 0.03838
## F-statistic: 7.79 on 7 and 1184 DF, p-value: 3.056e-09
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.4566 -0.8780 0.0548 0.8253 3.3516
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.87476 0.03874 100.015 < 2e-16 ***
## Risk_cond -0.05503 0.07550 -0.729 0.466244
## Help_cond -0.13651 0.07694 -1.774 0.076278 .
## Cond1 0.13382 0.03792 3.529 0.000433 ***
## Attitude 0.24218 0.04262 5.683 1.67e-08 ***
## Risk_cond:Help_cond 0.05937 0.15141 0.392 0.695030
## Risk_cond:Cond1 0.05941 0.07619 0.780 0.435658
## Help_cond:Cond1 -0.09895 0.07612 -1.300 0.193906
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.245
## Multiple R-squared: 0.04506, Adjusted R-squared: 0.03942
## Convergence in 11 IRWLS iterations
##
## Robustness weights:
## 105 weights are ~= 1. The remaining 1087 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.4207 0.8698 0.9455 0.9064 0.9845 0.9989
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Villain_S_mean
## Model: model_1
## Formula: Villain_S_mean ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.7178 -0.9619 0.2822 1.2240 2.6880
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.040677 0.044492 113.293 < 2e-16 ***
## Cond1 -0.544592 0.044605 -12.209 < 2e-16 ***
## Risk_cond 0.323259 0.089005 3.632 0.000293 ***
## Help_cond -0.006686 0.089027 -0.075 0.940145
## Risk_cond:Help_cond -0.103190 0.178312 -0.579 0.562900
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.536 on 1187 degrees of freedom
## Multiple R-squared: 0.1192, Adjusted R-squared: 0.1162
## F-statistic: 40.17 on 4 and 1187 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -4.8241 -1.0620 0.1759 1.1567 2.5531
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.143780 0.051249 100.368 < 2e-16 ***
## Cond1 -0.547721 0.047145 -11.618 < 2e-16 ***
## Risk_cond 0.284376 0.092363 3.079 0.00213 **
## Help_cond -0.002612 0.092259 -0.028 0.97742
## Risk_cond:Help_cond -0.033239 0.184825 -0.180 0.85731
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.468
## Multiple R-squared: 0.1198, Adjusted R-squared: 0.1169
## Convergence in 11 IRWLS iterations
##
## Robustness weights:
## 52 weights are ~= 1. The remaining 1140 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2578 0.8776 0.9442 0.9033 0.9871 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Villain_S_mean
## Model: model_2
## Formula: Villain_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.6457 -0.9097 0.3028 1.2984 2.7702
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.039115 0.044507 113.221 < 2e-16 ***
## Risk_cond 0.322486 0.089142 3.618 0.00031 ***
## Help_cond 0.002850 0.089165 0.032 0.97451
## Cond1 -0.545272 0.044590 -12.229 < 2e-16 ***
## Risk_cond:Help_cond -0.112491 0.178372 -0.631 0.52839
## Risk_cond:Cond1 0.152714 0.089185 1.712 0.08710 .
## Help_cond:Cond1 -0.006226 0.089183 -0.070 0.94436
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.535 on 1185 degrees of freedom
## Multiple R-squared: 0.1214, Adjusted R-squared: 0.1169
## F-statistic: 27.29 on 6 and 1185 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -4.7490 -1.0099 0.2166 1.1822 2.6607
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.141903 0.051342 100.151 < 2e-16 ***
## Risk_cond 0.297714 0.094694 3.144 0.00171 **
## Help_cond 0.007999 0.094568 0.085 0.93260
## Cond1 -0.551994 0.047356 -11.656 < 2e-16 ***
## Risk_cond:Help_cond -0.045548 0.185009 -0.246 0.80558
## Risk_cond:Cond1 0.187785 0.094828 1.980 0.04791 *
## Help_cond:Cond1 -0.015037 0.094384 -0.159 0.87344
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.462
## Multiple R-squared: 0.1248, Adjusted R-squared: 0.1203
## Convergence in 12 IRWLS iterations
##
## Robustness weights:
## 76 weights are ~= 1. The remaining 1116 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2695 0.8739 0.9413 0.9008 0.9815 0.9986
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Villain_S_mean
## Model: model_3
## Formula: Villain_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.0480 -0.9158 0.2409 1.0786 3.6107
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.04034 0.04366 115.446 < 2e-16 ***
## Cond1 -0.52985 0.04382 -12.091 < 2e-16 ***
## Risk_cond 0.26991 0.08769 3.078 0.00213 **
## Help_cond -0.11530 0.08879 -1.298 0.19438
## Attitude 0.30481 0.04460 6.834 1.31e-11 ***
## Risk_cond:Help_cond -0.12445 0.17500 -0.711 0.47714
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.507 on 1186 degrees of freedom
## Multiple R-squared: 0.1526, Adjusted R-squared: 0.149
## F-statistic: 42.71 on 5 and 1186 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -5.2075 -1.0148 0.1264 0.9847 3.6201
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.14481 0.04923 104.509 < 2e-16 ***
## Cond1 -0.53213 0.04591 -11.591 < 2e-16 ***
## Risk_cond 0.22289 0.09001 2.476 0.0134 *
## Help_cond -0.12866 0.09151 -1.406 0.1600
## Attitude 0.35223 0.05375 6.553 8.39e-11 ***
## Risk_cond:Help_cond -0.06146 0.17988 -0.342 0.7326
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.412
## Multiple R-squared: 0.1661, Adjusted R-squared: 0.1625
## Convergence in 11 IRWLS iterations
##
## Robustness weights:
## 99 weights are ~= 1. The remaining 1093 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1450 0.8702 0.9504 0.8960 0.9818 0.9983
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Villain_S_mean
## Model: model_4
## Formula: Villain_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.9496 -0.9578 0.2554 1.0504 3.7601
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.03788 0.04363 115.471 < 2e-16 ***
## Risk_cond 0.26881 0.08772 3.065 0.00223 **
## Help_cond -0.10579 0.08877 -1.192 0.23361
## Cond1 -0.53028 0.04376 -12.117 < 2e-16 ***
## Attitude 0.31362 0.04472 7.014 3.9e-12 ***
## Risk_cond:Help_cond -0.13849 0.17489 -0.792 0.42860
## Risk_cond:Cond1 0.20363 0.08773 2.321 0.02045 *
## Help_cond:Cond1 0.01551 0.08748 0.177 0.85931
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.505 on 1184 degrees of freedom
## Multiple R-squared: 0.1564, Adjusted R-squared: 0.1515
## F-statistic: 31.37 on 7 and 1184 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -5.1231 -1.0794 0.1176 0.9086 3.8051
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.145427 0.049791 103.340 < 2e-16 ***
## Risk_cond 0.239966 0.092753 2.587 0.00980 **
## Help_cond -0.115879 0.094124 -1.231 0.21852
## Cond1 -0.538608 0.046277 -11.639 < 2e-16 ***
## Attitude 0.364411 0.053834 6.769 2.03e-11 ***
## Risk_cond:Help_cond -0.080885 0.180309 -0.449 0.65381
## Risk_cond:Cond1 0.246672 0.093414 2.641 0.00838 **
## Help_cond:Cond1 -0.009025 0.092362 -0.098 0.92218
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.381
## Multiple R-squared: 0.1759, Adjusted R-squared: 0.1711
## Convergence in 13 IRWLS iterations
##
## Robustness weights:
## 69 weights are ~= 1. The remaining 1123 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1392 0.8579 0.9443 0.8951 0.9853 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Endure_G_mean
## Model: model_1
## Formula: Endure_G_mean ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2523 -0.6994 0.0846 0.8346 3.1190
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.01030 0.03492 114.843 < 2e-16 ***
## Cond1 -0.04345 0.03501 -1.241 0.215
## Risk_cond 0.29481 0.06986 4.220 2.63e-05 ***
## Help_cond 0.07657 0.06987 1.096 0.273
## Risk_cond:Help_cond 0.05160 0.13995 0.369 0.712
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.205 on 1187 degrees of freedom
## Multiple R-squared: 0.01684, Adjusted R-squared: 0.01353
## F-statistic: 5.083 on 4 and 1187 DF, p-value: 0.0004612
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.29353 -0.74276 0.05137 0.80137 3.07890
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.04670 0.03656 110.693 < 2e-16 ***
## Cond1 -0.04745 0.03586 -1.323 0.186
## Risk_cond 0.29136 0.07199 4.047 5.52e-05 ***
## Help_cond 0.08107 0.07196 1.127 0.260
## Risk_cond:Help_cond 0.05267 0.14409 0.366 0.715
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.142
## Multiple R-squared: 0.01714, Adjusted R-squared: 0.01383
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 131 weights are ~= 1. The remaining 1061 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.3853 0.8442 0.9465 0.8946 0.9860 0.9988
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Endure_G_mean
## Model: model_2
## Formula: Endure_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3236 -0.7665 0.1078 0.8578 3.1821
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.01255 0.03490 114.969 < 2e-16 ***
## Risk_cond 0.28514 0.06990 4.079 4.82e-05 ***
## Help_cond 0.07781 0.06992 1.113 0.2660
## Cond1 -0.04384 0.03497 -1.254 0.2102
## Risk_cond:Help_cond 0.05748 0.13987 0.411 0.6812
## Risk_cond:Cond1 0.01282 0.06994 0.183 0.8546
## Help_cond:Cond1 -0.15552 0.06993 -2.224 0.0263 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.204 on 1185 degrees of freedom
## Multiple R-squared: 0.02096, Adjusted R-squared: 0.016
## F-statistic: 4.229 on 6 and 1185 DF, p-value: 0.0003208
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.37159 -0.79664 0.07898 0.82898 3.14686
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.04810 0.03639 111.240 < 2e-16 ***
## Risk_cond 0.28316 0.07183 3.942 8.55e-05 ***
## Help_cond 0.08318 0.07180 1.158 0.2469
## Cond1 -0.04983 0.03588 -1.389 0.1652
## Risk_cond:Help_cond 0.05776 0.14353 0.402 0.6875
## Risk_cond:Cond1 0.01114 0.07160 0.156 0.8764
## Help_cond:Cond1 -0.16325 0.07167 -2.278 0.0229 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.143
## Multiple R-squared: 0.02195, Adjusted R-squared: 0.01699
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 99 weights are ~= 1. The remaining 1093 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.3645 0.8626 0.9477 0.8984 0.9887 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Endure_G_mean
## Model: model_3
## Formula: Endure_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6385 -0.6714 0.0829 0.7586 2.8980
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.00993 0.03364 119.196 < 2e-16 ***
## Cond1 -0.02743 0.03377 -0.812 0.416774
## Risk_cond 0.23683 0.06757 3.505 0.000473 ***
## Help_cond -0.04148 0.06842 -0.606 0.544455
## Attitude 0.33129 0.03437 9.640 < 2e-16 ***
## Risk_cond:Help_cond 0.02850 0.13485 0.211 0.832675
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.161 on 1186 degrees of freedom
## Multiple R-squared: 0.08828, Adjusted R-squared: 0.08444
## F-statistic: 22.97 on 5 and 1186 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.74429 -0.73959 0.02583 0.70159 2.83092
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.07082 0.03564 114.208 < 2e-16 ***
## Cond1 -0.02928 0.03406 -0.860 0.390192
## Risk_cond 0.25820 0.06786 3.805 0.000149 ***
## Help_cond -0.04111 0.06887 -0.597 0.550669
## Attitude 0.35665 0.03447 10.348 < 2e-16 ***
## Risk_cond:Help_cond 0.04199 0.13640 0.308 0.758253
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.077
## Multiple R-squared: 0.1052, Adjusted R-squared: 0.1014
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 120 weights are ~= 1. The remaining 1072 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2015 0.8540 0.9466 0.8922 0.9863 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Endure_G_mean
## Model: model_4
## Formula: Endure_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6451 -0.6540 0.1012 0.7816 2.9265
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.01124 0.03362 119.294 < 2e-16 ***
## Risk_cond 0.22836 0.06760 3.378 0.000754 ***
## Help_cond -0.03712 0.06841 -0.543 0.587541
## Cond1 -0.02798 0.03373 -0.830 0.406984
## Attitude 0.33177 0.03446 9.627 < 2e-16 ***
## Risk_cond:Help_cond 0.02998 0.13479 0.222 0.824037
## Risk_cond:Cond1 0.06668 0.06761 0.986 0.324217
## Help_cond:Cond1 -0.13253 0.06742 -1.966 0.049560 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.16 on 1184 degrees of freedom
## Multiple R-squared: 0.09204, Adjusted R-squared: 0.08667
## F-statistic: 17.15 on 7 and 1184 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.75800 -0.72036 0.03197 0.70712 2.85978
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.07148 0.03555 114.520 < 2e-16 ***
## Risk_cond 0.25141 0.06778 3.709 0.000217 ***
## Help_cond -0.03664 0.06883 -0.532 0.594620
## Cond1 -0.03146 0.03412 -0.922 0.356581
## Attitude 0.35546 0.03453 10.295 < 2e-16 ***
## Risk_cond:Help_cond 0.04500 0.13607 0.331 0.740904
## Risk_cond:Cond1 0.06188 0.06794 0.911 0.362557
## Help_cond:Cond1 -0.12800 0.06836 -1.872 0.061394 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.076
## Multiple R-squared: 0.1083, Adjusted R-squared: 0.1031
## Convergence in 11 IRWLS iterations
##
## Robustness weights:
## 105 weights are ~= 1. The remaining 1087 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1973 0.8575 0.9510 0.8939 0.9861 0.9989
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Endure_S_mean
## Model: model_1
## Formula: Endure_S_mean ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8793 -0.9046 -0.2966 0.7341 3.5954
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.61686 0.03804 95.089 < 2e-16 ***
## Cond1 0.21933 0.03813 5.752 1.12e-08 ***
## Risk_cond 0.02717 0.07609 0.357 0.721
## Help_cond 0.05020 0.07611 0.660 0.510
## Risk_cond:Help_cond -0.12643 0.15244 -0.829 0.407
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.313 on 1187 degrees of freedom
## Multiple R-squared: 0.02897, Adjusted R-squared: 0.0257
## F-statistic: 8.854 on 4 and 1187 DF, p-value: 4.806e-07
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.8607 -0.8468 -0.2470 0.7697 3.6808
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.564218 0.041767 85.336 < 2e-16 ***
## Cond1 0.233244 0.040534 5.754 1.11e-08 ***
## Risk_cond 0.003989 0.080562 0.050 0.961
## Help_cond 0.051412 0.080214 0.641 0.522
## Risk_cond:Help_cond -0.158014 0.160477 -0.985 0.325
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.307
## Multiple R-squared: 0.03172, Adjusted R-squared: 0.02845
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 13 weights are ~= 1. The remaining 1179 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.4078 0.8672 0.9621 0.9128 0.9931 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Endure_S_mean
## Model: model_2
## Formula: Endure_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9032 -0.9130 -0.2986 0.7138 3.5777
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.617220 0.038091 94.963 < 2e-16 ***
## Risk_cond 0.027748 0.076291 0.364 0.716
## Help_cond 0.047460 0.076311 0.622 0.534
## Cond1 0.219532 0.038162 5.753 1.12e-08 ***
## Risk_cond:Help_cond -0.124018 0.152658 -0.812 0.417
## Risk_cond:Cond1 -0.043617 0.076329 -0.571 0.568
## Help_cond:Cond1 0.007498 0.076326 0.098 0.922
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.314 on 1185 degrees of freedom
## Multiple R-squared: 0.02925, Adjusted R-squared: 0.02433
## F-statistic: 5.951 on 6 and 1185 DF, p-value: 3.877e-06
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.8949 -0.8547 -0.2470 0.7723 3.6827
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.564382 0.041923 85.021 < 2e-16 ***
## Risk_cond 0.006974 0.080705 0.086 0.931
## Help_cond 0.048744 0.080350 0.607 0.544
## Cond1 0.233055 0.040503 5.754 1.11e-08 ***
## Risk_cond:Help_cond -0.158216 0.161103 -0.982 0.326
## Risk_cond:Cond1 -0.034685 0.080624 -0.430 0.667
## Help_cond:Cond1 0.039377 0.080648 0.488 0.625
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.31
## Multiple R-squared: 0.032, Adjusted R-squared: 0.0271
## Convergence in 11 IRWLS iterations
##
## Robustness weights:
## 44 weights are ~= 1. The remaining 1148 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.4094 0.8666 0.9586 0.9108 0.9917 0.9989
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Endure_S_mean
## Model: model_3
## Formula: Endure_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9911 -0.9150 -0.2285 0.7905 3.5845
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.61677 0.03798 95.218 < 2e-16 ***
## Cond1 0.22322 0.03813 5.855 6.18e-09 ***
## Risk_cond 0.01310 0.07629 0.172 0.8637
## Help_cond 0.02155 0.07725 0.279 0.7803
## Attitude 0.08041 0.03880 2.072 0.0385 *
## Risk_cond:Help_cond -0.13204 0.15225 -0.867 0.3860
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.311 on 1186 degrees of freedom
## Multiple R-squared: 0.03248, Adjusted R-squared: 0.0284
## F-statistic: 7.962 on 5 and 1186 DF, p-value: 2.159e-07
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.9556 -0.8499 -0.1831 0.8252 3.6682
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.567717 0.042362 84.219 < 2e-16 ***
## Cond1 0.235925 0.040546 5.819 7.62e-09 ***
## Risk_cond -0.004092 0.080253 -0.051 0.959
## Help_cond 0.023925 0.084010 0.285 0.776
## Attitude 0.067964 0.044783 1.518 0.129
## Risk_cond:Help_cond -0.166924 0.160907 -1.037 0.300
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.303
## Multiple R-squared: 0.03398, Adjusted R-squared: 0.02991
## Convergence in 12 IRWLS iterations
##
## Robustness weights:
## 47 weights are ~= 1. The remaining 1145 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.4080 0.8659 0.9578 0.9099 0.9889 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: Endure_S_mean
## Model: model_4
## Formula: Endure_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.0100 -0.9240 -0.2217 0.7975 3.5760
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.61691 0.03804 95.080 < 2e-16 ***
## Risk_cond 0.01417 0.07648 0.185 0.8531
## Help_cond 0.01997 0.07740 0.258 0.7964
## Cond1 0.22333 0.03816 5.853 6.25e-09 ***
## Attitude 0.07935 0.03899 2.035 0.0421 *
## Risk_cond:Help_cond -0.13060 0.15249 -0.856 0.3919
## Risk_cond:Cond1 -0.03074 0.07649 -0.402 0.6879
## Help_cond:Cond1 0.01300 0.07627 0.170 0.8647
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.312 on 1184 degrees of freedom
## Multiple R-squared: 0.03263, Adjusted R-squared: 0.02691
## F-statistic: 5.706 on 7 and 1184 DF, p-value: 1.665e-06
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -2.9842 -0.8566 -0.1930 0.8145 3.6783
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.567496 0.042475 83.991 < 2e-16 ***
## Risk_cond -0.001154 0.080450 -0.014 0.989
## Help_cond 0.022171 0.084074 0.264 0.792
## Cond1 0.235742 0.040518 5.818 7.65e-09 ***
## Attitude 0.067333 0.045129 1.492 0.136
## Risk_cond:Help_cond -0.168313 0.161666 -1.041 0.298
## Risk_cond:Cond1 -0.021916 0.081312 -0.270 0.788
## Help_cond:Cond1 0.041874 0.080708 0.519 0.604
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.305
## Multiple R-squared: 0.03419, Adjusted R-squared: 0.02848
## Convergence in 12 IRWLS iterations
##
## Robustness weights:
## 47 weights are ~= 1. The remaining 1145 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.4075 0.8654 0.9586 0.9103 0.9893 0.9990
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: SelfExploit_G_mean
## Model: model_1
## Formula: SelfExploit_G_mean ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.5524 -0.6250 0.1040 0.7661 3.0161
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.25557 0.03478 122.357 < 2e-16 ***
## Cond1 0.03630 0.03487 1.041 0.29810
## Risk_cond 0.38125 0.06958 5.480 5.2e-08 ***
## Help_cond 0.18727 0.06959 2.691 0.00722 **
## Risk_cond:Help_cond 0.19539 0.13939 1.402 0.16124
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.201 on 1187 degrees of freedom
## Multiple R-squared: 0.03274, Adjusted R-squared: 0.02949
## F-statistic: 10.05 on 4 and 1187 DF, p-value: 5.358e-08
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.60057 -0.66249 0.03773 0.69151 2.94151
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.32409 0.03610 119.787 < 2e-16 ***
## Cond1 0.02489 0.03492 0.713 0.4761
## Risk_cond 0.37741 0.06961 5.421 7.16e-08 ***
## Help_cond 0.16467 0.06964 2.365 0.0182 *
## Risk_cond:Help_cond 0.12133 0.13913 0.872 0.3833
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.082
## Multiple R-squared: 0.03214, Adjusted R-squared: 0.02888
## Convergence in 10 IRWLS iterations
##
## Robustness weights:
## 100 weights are ~= 1. The remaining 1092 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2456 0.8526 0.9477 0.8889 0.9876 0.9988
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: SelfExploit_G_mean
## Model: model_2
## Formula: SelfExploit_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6566 -0.6566 0.0881 0.8277 3.1086
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.258775 0.034707 122.705 < 2e-16 ***
## Risk_cond 0.368563 0.069515 5.302 1.37e-07 ***
## Help_cond 0.187593 0.069533 2.698 0.00708 **
## Cond1 0.035883 0.034772 1.032 0.30231
## Risk_cond:Help_cond 0.204461 0.139099 1.470 0.14186
## Risk_cond:Cond1 -0.004218 0.069549 -0.061 0.95165
## Help_cond:Cond1 -0.204909 0.069547 -2.946 0.00328 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.197 on 1185 degrees of freedom
## Multiple R-squared: 0.03978, Adjusted R-squared: 0.03492
## F-statistic: 8.182 on 6 and 1185 DF, p-value: 1.086e-08
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.72947 -0.72947 0.01123 0.75420 3.05642
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.32644 0.03605 120.021 < 2e-16 ***
## Risk_cond 0.36916 0.06963 5.302 1.37e-07 ***
## Help_cond 0.17034 0.06962 2.447 0.0146 *
## Cond1 0.02440 0.03479 0.701 0.4832
## Risk_cond:Help_cond 0.13795 0.13872 0.994 0.3202
## Risk_cond:Cond1 -0.04554 0.06984 -0.652 0.5145
## Help_cond:Cond1 -0.20086 0.06966 -2.884 0.0040 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.08
## Multiple R-squared: 0.04052, Adjusted R-squared: 0.03567
## Convergence in 11 IRWLS iterations
##
## Robustness weights:
## 105 weights are ~= 1. The remaining 1087 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2089 0.8388 0.9553 0.8888 0.9830 0.9985
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: SelfExploit_G_mean
## Model: model_3
## Formula: SelfExploit_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.7990 -0.6218 0.1323 0.7547 3.1024
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.25525 0.03379 125.934 < 2e-16 ***
## Cond1 0.05042 0.03392 1.487 0.137
## Risk_cond 0.33013 0.06786 4.865 1.3e-06 ***
## Help_cond 0.08319 0.06872 1.211 0.226
## Attitude 0.29209 0.03452 8.462 < 2e-16 ***
## Risk_cond:Help_cond 0.17502 0.13544 1.292 0.197
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.166 on 1186 degrees of freedom
## Multiple R-squared: 0.08782, Adjusted R-squared: 0.08397
## F-statistic: 22.84 on 5 and 1186 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -3.99600 -0.69913 0.05688 0.64145 3.01359
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.35166 0.03578 121.614 < 2e-16 ***
## Cond1 0.02518 0.03316 0.759 0.448
## Risk_cond 0.34687 0.06575 5.276 1.57e-07 ***
## Help_cond 0.03640 0.06698 0.543 0.587
## Attitude 0.34227 0.03802 9.001 < 2e-16 ***
## Risk_cond:Help_cond 0.08294 0.13248 0.626 0.531
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.023
## Multiple R-squared: 0.1171, Adjusted R-squared: 0.1134
## Convergence in 11 IRWLS iterations
##
## Robustness weights:
## 99 weights are ~= 1. The remaining 1093 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.09262 0.85120 0.95050 0.88440 0.98780 0.99900
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: SelfExploit_G_mean
## Model: model_4
## Formula: SelfExploit_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.9037 -0.6292 0.1434 0.7287 2.9787
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.25763 0.03373 126.227 < 2e-16 ***
## Risk_cond 0.31882 0.06782 4.701 2.89e-06 ***
## Help_cond 0.08691 0.06863 1.266 0.20563
## Cond1 0.04978 0.03383 1.471 0.14147
## Attitude 0.29066 0.03457 8.408 < 2e-16 ***
## Risk_cond:Help_cond 0.18036 0.13521 1.334 0.18248
## Risk_cond:Cond1 0.04297 0.06782 0.634 0.52648
## Help_cond:Cond1 -0.18476 0.06763 -2.732 0.00639 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.164 on 1184 degrees of freedom
## Multiple R-squared: 0.09388, Adjusted R-squared: 0.08852
## F-statistic: 17.52 on 7 and 1184 DF, p-value: < 2.2e-16
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -4.05701 -0.73769 0.04407 0.65814 2.92248
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.35247 0.03578 121.631 < 2e-16 ***
## Risk_cond 0.33692 0.06622 5.088 4.21e-07 ***
## Help_cond 0.04622 0.06752 0.685 0.4938
## Cond1 0.02507 0.03311 0.757 0.4490
## Attitude 0.33693 0.03774 8.928 < 2e-16 ***
## Risk_cond:Help_cond 0.09814 0.13240 0.741 0.4587
## Risk_cond:Cond1 -0.00610 0.06665 -0.092 0.9271
## Help_cond:Cond1 -0.16918 0.06672 -2.536 0.0114 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.024
## Multiple R-squared: 0.1219, Adjusted R-squared: 0.1167
## Convergence in 12 IRWLS iterations
##
## Robustness weights:
## 118 weights are ~= 1. The remaining 1074 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.08087 0.85080 0.94630 0.88320 0.98570 0.99900
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: SelfExploit_S_mean
## Model: model_1
## Formula: SelfExploit_S_mean ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.6905 -1.0448 -0.3436 0.8416 4.7028
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.460987 0.037328 65.928 < 2e-16 ***
## Cond1 0.006823 0.037423 0.182 0.855368
## Risk_cond 0.052076 0.074674 0.697 0.485705
## Help_cond 0.246700 0.074692 3.303 0.000985 ***
## Risk_cond:Help_cond 0.293379 0.149601 1.961 0.050103 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.289 on 1187 degrees of freedom
## Multiple R-squared: 0.01272, Adjusted R-squared: 0.009392
## F-statistic: 3.823 on 4 and 1187 DF, p-value: 0.00429
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.5609 -0.8942 -0.1893 0.9634 4.8198
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.32197 0.04721 49.186 < 2e-16 ***
## Cond1 0.01913 0.03878 0.493 0.62181
## Risk_cond 0.05887 0.07746 0.760 0.44744
## Help_cond 0.24860 0.07773 3.198 0.00142 **
## Risk_cond:Help_cond 0.26413 0.15539 1.700 0.08942 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.136
## Multiple R-squared: 0.01336, Adjusted R-squared: 0.01003
## Convergence in 12 IRWLS iterations
##
## Robustness weights:
## 55 weights are ~= 1. The remaining 1137 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.03244 0.87190 0.93090 0.88790 0.98340 0.99860
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: SelfExploit_S_mean
## Model: model_2
## Formula: SelfExploit_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7586 -1.0919 -0.3045 0.8212 4.7230
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.463057 0.037346 65.952 < 2e-16 ***
## Risk_cond 0.048563 0.074800 0.649 0.51631
## Help_cond 0.240380 0.074819 3.213 0.00135 **
## Cond1 0.007149 0.037416 0.191 0.84850
## Risk_cond:Help_cond 0.302526 0.149674 2.021 0.04348 *
## Risk_cond:Cond1 -0.104197 0.074836 -1.392 0.16408
## Help_cond:Cond1 -0.060950 0.074834 -0.814 0.41554
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.288 on 1185 degrees of freedom
## Multiple R-squared: 0.01486, Adjusted R-squared: 0.009871
## F-statistic: 2.979 on 6 and 1185 DF, p-value: 0.006835
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.6352 -0.9641 -0.1487 0.9358 4.8513
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.32489 0.04719 49.266 < 2e-16 ***
## Risk_cond 0.05499 0.07739 0.711 0.47752
## Help_cond 0.23986 0.07768 3.088 0.00206 **
## Cond1 0.01805 0.03880 0.465 0.64183
## Risk_cond:Help_cond 0.27933 0.15538 1.798 0.07248 .
## Risk_cond:Cond1 -0.14308 0.07753 -1.846 0.06521 .
## Help_cond:Cond1 -0.07905 0.07762 -1.018 0.30871
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.135
## Multiple R-squared: 0.01758, Adjusted R-squared: 0.0126
## Convergence in 12 IRWLS iterations
##
## Robustness weights:
## 90 weights are ~= 1. The remaining 1102 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.02831 0.86670 0.92460 0.88460 0.98170 0.99840
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: SelfExploit_S_mean
## Model: model_3
## Formula: SelfExploit_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.8385 -1.0530 -0.2675 0.8458 4.5059
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.46085 0.03717 66.199 < 2e-16 ***
## Cond1 0.01289 0.03731 0.345 0.729903
## Risk_cond 0.03014 0.07466 0.404 0.686536
## Help_cond 0.20204 0.07560 2.672 0.007635 **
## Attitude 0.12535 0.03797 3.301 0.000993 ***
## Risk_cond:Help_cond 0.28464 0.14900 1.910 0.056342 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.283 on 1186 degrees of freedom
## Multiple R-squared: 0.02171, Adjusted R-squared: 0.01758
## F-statistic: 5.263 on 5 and 1186 DF, p-value: 8.687e-05
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.6609 -0.9302 -0.1642 0.9604 4.6900
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.32690 0.04800 48.477 < 2e-16 ***
## Cond1 0.02327 0.03892 0.598 0.55001
## Risk_cond 0.04751 0.07761 0.612 0.54055
## Help_cond 0.22171 0.07876 2.815 0.00496 **
## Attitude 0.07876 0.03920 2.009 0.04474 *
## Risk_cond:Help_cond 0.25822 0.15559 1.660 0.09727 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.134
## Multiple R-squared: 0.0172, Adjusted R-squared: 0.01306
## Convergence in 13 IRWLS iterations
##
## Robustness weights:
## 70 weights are ~= 1. The remaining 1122 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.04849 0.86410 0.92840 0.88660 0.98280 0.99900
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: SelfExploit_S_mean
## Model: model_4
## Formula: SelfExploit_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.8757 -1.0945 -0.2831 0.8310 4.5278
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.46258 0.03720 66.190 < 2e-16 ***
## Risk_cond 0.02788 0.07480 0.373 0.70947
## Help_cond 0.19851 0.07570 2.622 0.00884 **
## Cond1 0.01293 0.03732 0.346 0.72908
## Attitude 0.12088 0.03813 3.170 0.00156 **
## Risk_cond:Help_cond 0.29250 0.14914 1.961 0.05008 .
## Risk_cond:Cond1 -0.08457 0.07481 -1.131 0.25849
## Help_cond:Cond1 -0.05257 0.07460 -0.705 0.48111
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.283 on 1184 degrees of freedom
## Multiple R-squared: 0.02315, Adjusted R-squared: 0.01738
## F-statistic: 4.009 on 7 and 1184 DF, p-value: 0.0002399
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.7100 -0.9490 -0.1462 0.9331 4.7284
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.32908 0.04794 48.585 < 2e-16 ***
## Risk_cond 0.04486 0.07754 0.579 0.56297
## Help_cond 0.21619 0.07864 2.749 0.00607 **
## Cond1 0.02200 0.03896 0.565 0.57243
## Attitude 0.07181 0.03974 1.807 0.07101 .
## Risk_cond:Help_cond 0.27264 0.15566 1.752 0.08011 .
## Risk_cond:Cond1 -0.12994 0.07814 -1.663 0.09658 .
## Help_cond:Cond1 -0.07517 0.07774 -0.967 0.33378
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 1.133
## Multiple R-squared: 0.02071, Adjusted R-squared: 0.01492
## Convergence in 13 IRWLS iterations
##
## Robustness weights:
## 84 weights are ~= 1. The remaining 1108 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.04252 0.86330 0.92470 0.88520 0.98280 0.99900
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalSupportExpl
## Model: model_1
## Formula: GlobalSupportExpl ~ Cond + Risk_cond * Help_cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.2493 -0.6761 -0.1213 0.5148 3.9355
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0004483 0.0243377 0.018 0.9853
## Cond1 0.0474236 0.0243995 1.944 0.0522 .
## Risk_cond -0.1104554 0.0486869 -2.269 0.0235 *
## Help_cond 0.0585225 0.0486985 1.202 0.2297
## Risk_cond:Help_cond 0.0453346 0.0975388 0.465 0.6422
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8402 on 1187 degrees of freedom
## Multiple R-squared: 0.008793, Adjusted R-squared: 0.005453
## F-statistic: 2.633 on 4 and 1187 DF, p-value: 0.0329
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.15525 -0.61008 -0.07195 0.57951 4.03796
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.05911 0.02658 -2.224 0.0263 *
## Cond1 0.03803 0.02457 1.548 0.1220
## Risk_cond -0.08774 0.04940 -1.776 0.0760 .
## Help_cond 0.03899 0.04942 0.789 0.4303
## Risk_cond:Help_cond 0.09492 0.09907 0.958 0.3382
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.8295
## Multiple R-squared: 0.006196, Adjusted R-squared: 0.002847
## Convergence in 12 IRWLS iterations
##
## Robustness weights:
## observation 963 is an outlier with |weight| = 0 ( < 8.4e-05);
## 77 weights are ~= 1. The remaining 1114 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0565 0.8775 0.9464 0.9094 0.9835 0.9989
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalSupportExpl
## Model: model_2
## Formula: GlobalSupportExpl ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.2536 -0.6678 -0.1234 0.5094 3.9311
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.001251 0.024367 0.051 0.9591
## Risk_cond -0.112023 0.048805 -2.295 0.0219 *
## Help_cond 0.056360 0.048818 1.155 0.2485
## Cond1 0.047524 0.024413 1.947 0.0518 .
## Risk_cond:Help_cond 0.048735 0.097658 0.499 0.6178
## Risk_cond:Cond1 -0.035916 0.048829 -0.736 0.4621
## Help_cond:Cond1 -0.026764 0.048827 -0.548 0.5837
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8406 on 1185 degrees of freedom
## Multiple R-squared: 0.009488, Adjusted R-squared: 0.004473
## F-statistic: 1.892 on 6 and 1185 DF, p-value: 0.07908
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.20705 -0.60494 -0.06648 0.57922 4.04760
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.05924 0.02668 -2.220 0.0266 *
## Risk_cond -0.09095 0.04940 -1.841 0.0659 .
## Help_cond 0.03629 0.04948 0.733 0.4634
## Cond1 0.03800 0.02464 1.542 0.1234
## Risk_cond:Help_cond 0.09841 0.09891 0.995 0.3200
## Risk_cond:Cond1 -0.03925 0.04937 -0.795 0.4268
## Help_cond:Cond1 -0.05699 0.04936 -1.155 0.2485
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.8232
## Multiple R-squared: 0.007919, Adjusted R-squared: 0.002896
## Convergence in 12 IRWLS iterations
##
## Robustness weights:
## observation 963 is an outlier with |weight| = 0 ( < 8.4e-05);
## 79 weights are ~= 1. The remaining 1112 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.04908 0.87470 0.94480 0.90800 0.98450 0.99900
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 1.819e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalSupportExpl
## Model: model_3
## Formula: GlobalSupportExpl ~ Cond + Risk_cond * Help_cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.6708 -0.6354 -0.1146 0.5112 3.2864
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0006179 0.0239663 0.026 0.9794
## Cond1 0.0401160 0.0240562 1.668 0.0957 .
## Risk_cond -0.0840130 0.0481349 -1.745 0.0812 .
## Help_cond 0.1123559 0.0487422 2.305 0.0213 *
## Attitude -0.1510817 0.0244824 -6.171 9.3e-10 ***
## Risk_cond:Help_cond 0.0558732 0.0960653 0.582 0.5609
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8274 on 1186 degrees of freedom
## Multiple R-squared: 0.03963, Adjusted R-squared: 0.03558
## F-statistic: 9.788 on 5 and 1186 DF, p-value: 3.521e-09
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.60917 -0.57798 -0.05723 0.57313 3.39559
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.06127 0.02593 -2.363 0.0183 *
## Cond1 0.03846 0.02420 1.589 0.1123
## Risk_cond -0.05647 0.04918 -1.148 0.2511
## Help_cond 0.09676 0.04997 1.936 0.0530 .
## Attitude -0.14895 0.02825 -5.273 1.6e-07 ***
## Risk_cond:Help_cond 0.11588 0.09775 1.186 0.2360
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.7961
## Multiple R-squared: 0.03741, Adjusted R-squared: 0.03335
## Convergence in 12 IRWLS iterations
##
## Robustness weights:
## 93 weights are ~= 1. The remaining 1099 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.02933 0.87650 0.94500 0.90250 0.98190 0.99900
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
##
## ====================================================
## Outcome: GlobalSupportExpl
## Model: model_4
## Formula: GlobalSupportExpl ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## ====================================================
##
## --- lm summary ---
##
## Call:
## lm(formula = formula_i, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7354 -0.6361 -0.1270 0.5032 3.2615
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.00186 0.02398 0.078 0.9382
## Risk_cond -0.08562 0.04822 -1.776 0.0760 .
## Help_cond 0.10981 0.04879 2.250 0.0246 *
## Cond1 0.04015 0.02405 1.669 0.0954 .
## Attitude -0.15429 0.02458 -6.277 4.83e-10 ***
## Risk_cond:Help_cond 0.06153 0.09613 0.640 0.5223
## Risk_cond:Cond1 -0.06096 0.04822 -1.264 0.2064
## Help_cond:Cond1 -0.03746 0.04809 -0.779 0.4361
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8273 on 1184 degrees of freedom
## Multiple R-squared: 0.04139, Adjusted R-squared: 0.03572
## F-statistic: 7.303 on 7 and 1184 DF, p-value: 1.346e-08
##
## --- lmrob summary ---
##
## Call:
## robustbase::lmrob(formula = formula_i, data = data)
## \--> method = "MM"
## Residuals:
## Min 1Q Median 3Q Max
## -1.69610 -0.57879 -0.06664 0.56769 3.37402
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.06161 0.02613 -2.358 0.0186 *
## Risk_cond -0.05875 0.04910 -1.196 0.2318
## Help_cond 0.09425 0.04988 1.889 0.0591 .
## Cond1 0.03921 0.02428 1.615 0.1065
## Attitude -0.15370 0.02856 -5.381 8.9e-08 ***
## Risk_cond:Help_cond 0.12166 0.09733 1.250 0.2115
## Risk_cond:Cond1 -0.06935 0.04894 -1.417 0.1568
## Help_cond:Cond1 -0.06446 0.04847 -1.330 0.1838
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Robust residual standard error: 0.7876
## Multiple R-squared: 0.04111, Adjusted R-squared: 0.03545
## Convergence in 13 IRWLS iterations
##
## Robustness weights:
## 76 weights are ~= 1. The remaining 1116 ones are summarized as
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.02685 0.87530 0.94600 0.90230 0.98400 0.99900
## Algorithmic parameters:
## tuning.chi bb tuning.psi refine.tol
## 1.548e+00 5.000e-01 4.685e+00 1.000e-07
## rel.tol scale.tol solve.tol zero.tol
## 1.000e-07 1.000e-10 1.000e-07 1.000e-10
## eps.outlier eps.x warn.limit.reject warn.limit.meanrw
## 8.389e-05 7.768e-12 5.000e-01 5.000e-01
## nResample max.it best.r.s k.fast.s k.max
## 500 50 2 1 200
## maxit.scale trace.lev mts compute.rd fast.s.large.n
## 200 0 1000 0 2000
## psi subsampling cov
## "bisquare" "nonsingular" ".vcov.avar1"
## compute.outlier.stats
## "SM"
## seed : int(0)
Below, we now turn to our main models. This is the crux of the study:
we have previously demonstrated an effect of the manipulations on
occupational heroism – we have previously observed correlates of
occupational heroism. We now test how the manipulations can
causally influence correlates of occupational heroism.
run_prereg_models <- function(
data,
outcomes = c(
"GlobalGratitude",
"criticism_items_G_mean", "criticism_items_S_mean",
"DemandSupp_G_mean", "DemandSupp_S_mean",
"GlobalVictim",
"Villain_G_mean", "Villain_S_mean",
"Endure_G_mean", "Endure_S_mean",
"SelfExploit_G_mean", "SelfExploit_S_mean",
"GlobalSupportExpl"
),
models_to_run = c(1, 2, 3, 4),
occupation_var = "Cond",
risk_var = "Risk_cond",
help_var = "Help_cond",
attitude_var = "Attitude",
print_summaries = TRUE,
alpha = 0.05
) {
# ---- basic checks ----
required_vars <- unique(c(outcomes, occupation_var, risk_var, help_var, attitude_var))
missing_vars <- setdiff(required_vars, names(data))
if (length(missing_vars) > 0) {
stop("Missing columns in `data`: ", paste(missing_vars, collapse = ", "))
}
if (!is.factor(data[[occupation_var]])) {
data[[occupation_var]] <- as.factor(data[[occupation_var]])
}
# ---- hypothesis mapping ----
outcome_family <- function(y) {
# strip _G_mean / _S_mean
gsub("(_G_mean|_S_mean)$", "", y)
}
outcome_level <- function(y) {
if (grepl("_G_mean$", y)) return("general (_G)")
if (grepl("_S_mean$", y)) return("specific (_S)")
return("unknown level")
}
# Which hypothesis letter corresponds to which outcome family?
# (based on your prereg list)
hyp_letter_by_family <- list(
Gratitude = "a",
DemandSupp = "b",
Victim = "c",
criticism_items = "d",
Villain = "e",
Endure = "f",
SelfExploit = "g",
SupportExploit = "h"
)
# Expected direction for EACH hypothesis letter (Risk and Help share same direction)
# +1 means "increase", -1 means "decrease"
expected_sign_by_letter <- c(
a = +1, # gratitude higher
b = +1, # support demands higher
c = +1, # suffering/protection higher
d = -1, # criticism/hate speech acceptability lower
e = +1, # impunity/reg-violation acceptability higher
f = +1, # belief they'd choose suffering higher
g = +1, # belief they'd accept exploitation higher
h = -1 # support exploiting workers lower
)
hypothesis_text <- list(
H3 = c(
a = "H3a: Risk → gratitude ↑",
b = "H3b: Risk → support for workers' demands ↑",
c = "H3c: Risk → perceived suffering/protection need ↑",
d = "H3d: Risk → criticism/hate speech acceptability ↓",
e = "H3e: Risk → support for workers' impunity ↑",
f = "H3f: Risk → belief they'd choose suffering for duty ↑",
g = "H3g: Risk → belief they'd accept exploitation if required ↑",
h = "H3h: Risk → support for exploiting workers if required ↓"
),
H4 = c(
a = "H4a: Helpfulness → gratitude ↑",
b = "H4b: Helpfulness → support for workers' demands ↑",
c = "H4c: Helpfulness → perceived suffering/protection need ↑",
d = "H4d: Helpfulness → criticism/hate speech acceptability ↓",
e = "H4e: Helpfulness → support for workers' impunity ↑",
f = "H4f: Helpfulness → belief they'd choose suffering for duty ↑",
g = "H4g: Helpfulness → belief they'd accept exploitation if required ↑",
h = "H4h: Helpfulness → support for exploiting workers if required ↓"
)
)
get_hyp_letter <- function(y) {
fam <- outcome_family(y)
if (!fam %in% names(hyp_letter_by_family)) return(NA_character_)
hyp_letter_by_family[[fam]]
}
# ---- coefficient extractor + "supported" line ----
get_term_stats <- function(fit, term) {
coefs <- summary(fit)$coefficients
if (!term %in% rownames(coefs)) return(NULL)
list(
beta = unname(coefs[term, 1]),
se = unname(coefs[term, 2]),
t = unname(coefs[term, 3]),
p = unname(coefs[term, 4])
)
}
fmt_num <- function(x, digits = 3) sprintf(paste0("%.", digits, "f"), x)
fmt_p <- function(p) {
if (is.na(p)) return("NA")
if (p < .001) return("<.001")
sub("^0", "", sprintf("%.3f", p))
}
print_support_line_if_sig <- function(stats, hyp_code, expected_sign, alpha) {
if (is.null(stats)) return(invisible(NULL))
if (is.na(stats$p) || stats$p >= alpha) return(invisible(NULL))
direction_ok <- sign(stats$beta) == sign(expected_sign)
if (direction_ok) {
cat("✅ ", hyp_code, " supported: ",
"β=", fmt_num(stats$beta),
", SE=", fmt_num(stats$se),
", t=", fmt_num(stats$t),
", p=", fmt_p(stats$p),
"\n", sep = "")
} else {
cat("⚠️ ", hyp_code, " significant but opposite direction: ",
"β=", fmt_num(stats$beta),
", SE=", fmt_num(stats$se),
", t=", fmt_num(stats$t),
", p=", fmt_p(stats$p),
"\n", sep = "")
}
}
# ---- Define formulas (as prereg) ----
f_model_1 <- function(y) {
as.formula(paste0(y, " ~ ", occupation_var, " + ", risk_var, " * ", help_var))
}
f_model_2 <- function(y) {
as.formula(paste0(
y, " ~ ", risk_var, " * ", help_var,
" + ", occupation_var, ":", risk_var,
" + ", occupation_var, ":", help_var,
" + ", occupation_var
))
}
f_model_3 <- function(y) {
as.formula(paste0(
y, " ~ ", occupation_var,
" + ", risk_var, " * ", help_var,
" + ", attitude_var
))
}
f_model_4 <- function(y) {
as.formula(paste0(
y, " ~ ", risk_var, " * ", help_var,
" + ", occupation_var, ":", risk_var,
" + ", occupation_var, ":", help_var,
" + ", occupation_var,
" + ", attitude_var
))
}
formula_fns <- list(`1` = f_model_1, `2` = f_model_2, `3` = f_model_3, `4` = f_model_4)
model_titles <- list(
`1` = "Heroism + occupation as a covariate",
`2` = "Heroism + occupation as a moderator",
`3` = "Heroism + occupation and attitude as covariates)",
`4` = "Heroism + occupation as a moderator + attitude as a covariate"
)
results <- list()
for (y in outcomes) {
level_label <- outcome_level(y)
letter <- get_hyp_letter(y)
cat("\n\n============================================================\n")
cat("Outcome:", y, " | Level:", level_label, "\n")
cat("============================================================\n")
for (m in models_to_run) {
if (!as.character(m) %in% names(formula_fns)) {
warning("Unknown model number: ", m, " (skipping)")
next
}
form <- formula_fns[[as.character(m)]](y)
fit <- lm(form, data = data)
results[[y]][[paste0("Model_", m)]] <- fit
cat("\n------------------------------------------------------------\n")
cat(model_titles[[as.character(m)]], "\n")
cat("Formula: ", deparse(form), "\n", sep = "")
cat("N used: ", nobs(fit), "\n", sep = "")
# Hypothesis header (Risk=H3*, Help=H4*)
if (!is.na(letter)) {
cat("Hypotheses (this outcome):\n")
cat(" - ", hypothesis_text$H3[[letter]], " [", level_label, "]\n", sep = "")
cat(" - ", hypothesis_text$H4[[letter]], " [", level_label, "]\n", sep = "")
} else {
cat("Hypotheses: (no mapping found for this outcome name)\n")
}
cat("------------------------------------------------------------\n")
# Print "validated" lines ONLY if p < alpha, using main effects Risk and Help
# (These are the prereg H3* / H4* tests in the simplest reading.)
if (!is.na(letter)) {
expected_sign <- expected_sign_by_letter[[letter]]
risk_stats <- get_term_stats(fit, risk_var)
help_stats <- get_term_stats(fit, help_var)
print_support_line_if_sig(
stats = risk_stats,
hyp_code = paste0("H3", letter),
expected_sign = expected_sign,
alpha = alpha
)
print_support_line_if_sig(
stats = help_stats,
hyp_code = paste0("H4", letter),
expected_sign = expected_sign,
alpha = alpha
)
}
if (print_summaries) {
print(summary(fit))
}
}
}
invisible(results)
}
# run it
make_prereg_effect_table <- function(
data,
outcomes,
occupation_var = "Cond",
risk_var = "Risk_cond",
help_var = "Help_cond",
attitude_var = "Attitude"
) {
results_list <- list()
row_index <- 1
for (outcome_name in outcomes) {
formula_without_attitude <- as.formula(
paste0(outcome_name, " ~ ", risk_var, " * ", help_var, " + ", occupation_var)
)
formula_with_attitude <- as.formula(
paste0(outcome_name, " ~ ", risk_var, " * ", help_var, " + ", occupation_var, " + ", attitude_var)
)
model_list <- list(
"Without attitude" = lm(formula_without_attitude, data = data),
"With attitude" = lm(formula_with_attitude, data = data)
)
for (model_label in names(model_list)) {
fit <- model_list[[model_label]]
coef_table <- summary(fit)$coefficients
df_residual <- df.residual(fit)
eta_table <- effectsize::eta_squared(fit, partial = TRUE)
eta_table <- as.data.frame(eta_table)
for (predictor_name in c(risk_var, help_var)) {
if (predictor_name %in% rownames(coef_table)) {
t_value <- coef_table[predictor_name, "t value"]
p_value <- coef_table[predictor_name, "Pr(>|t|)"]
partial_eta_sq_t <- t_value^2 / (t_value^2 + df_residual)
partial_eta_sq_effectsize <- NA_real_
if ("Parameter" %in% names(eta_table)) {
matched_row <- eta_table[eta_table$Parameter == predictor_name, , drop = FALSE]
if (nrow(matched_row) == 1) {
partial_eta_sq_effectsize <- matched_row$Eta2_partial
}
}
results_list[[row_index]] <- data.frame(
Outcome = outcome_name,
Predictor = if (predictor_name == risk_var) "Risk" else "Help",
Model = model_label,
t_value = t_value,
p_value = p_value,
partial_eta_sq_effectsize = partial_eta_sq_effectsize,
stringsAsFactors = FALSE
)
row_index <- row_index + 1
}
}
}
}
results_table <- do.call(rbind, results_list)
results_table$t_value <- round(results_table$t_value, 3)
results_table$p_value <- round(results_table$p_value, 3)
results_table$partial_eta_sq_effectsize <- round(results_table$partial_eta_sq_effectsize, 3)
rownames(results_table) <- NULL
results_table
}
effect_table <- make_prereg_effect_table(
data = scale_scores,
outcomes = c(
"GlobalGratitude",
"criticism_items_G_mean", "criticism_items_S_mean",
"DemandSupp_G_mean", "DemandSupp_S_mean",
"GlobalVictim",
"Villain_G_mean", "Villain_S_mean",
"Endure_G_mean", "Endure_S_mean",
"SelfExploit_G_mean", "SelfExploit_S_mean",
"GlobalSupportExpl"
)
)
effect_table_pretty <- effect_table |>
mutate(
p_value = ifelse(p_value < .001, "< .001", sprintf("%.3f", p_value)),
t_value = sprintf("%.3f", t_value),
partial_eta_sq_effectsize = sprintf("%.3f", partial_eta_sq_effectsize)
)
library(dplyr)
library(tidyr)
library(gt)
library(knitr)
library(kableExtra)
kable(
effect_table_pretty,
format = "html",
caption = "Effects of Risk and Help across outcomes",
align = c("l", "l", "l", "r", "r", "r")
) |>
kable_styling(
bootstrap_options = c("striped", "hover", "condensed", "responsive"),
full_width = FALSE,
position = "left"
) |>
collapse_rows(columns = 1, valign = "top")
effect_table_wide <- effect_table |>
mutate(
p_value = ifelse(p_value < .001, "< .001", sprintf("%.3f", p_value)),
t_value = sprintf("%.3f", t_value),
partial_eta_sq_effectsize = sprintf("%.3f", partial_eta_sq_effectsize)
) |>
pivot_wider(
names_from = Model,
values_from = c(t_value, p_value, partial_eta_sq_effectsize),
names_vary = "slowest"
) |>
rename(
`t1` = `t_value_Without attitude`,
`p1` = `p_value_Without attitude`,
`η²p1` = `partial_eta_sq_effectsize_Without attitude`,
`t2` = `t_value_With attitude`,
`p2` = `p_value_With attitude`,
`η²p2` = `partial_eta_sq_effectsize_With attitude`
)
kable(
effect_table_wide,
format = "html",
caption = "Summary main p-values",
align = c("l", "l", "r", "r", "r", "r", "r", "r"),
escape = TRUE
) |>
add_header_above(c(" " = 2, "Without attitude" = 3, "With attitude" = 3)) |>
kable_styling(
bootstrap_options = c("striped", "hover", "condensed", "responsive"),
full_width = FALSE
) |>
column_spec(5, border_right = TRUE) |>
collapse_rows(columns = 1, valign = "top")
Summary main p-values
|
|
Without attitude
|
With attitude
|
|
Outcome
|
Predictor
|
t1
|
p1
|
η²p1
|
t2
|
p2
|
η²p2
|
|
GlobalGratitude
|
Risk
|
2.696
|
0.007
|
0.006
|
0.954
|
0.340
|
0.010
|
|
Help
|
4.669
|
< .001
|
0.018
|
0.876
|
0.381
|
0.030
|
|
criticism_items_G_mean
|
Risk
|
-3.677
|
< .001
|
0.011
|
-2.425
|
0.015
|
0.015
|
|
Help
|
-1.899
|
0.058
|
0.003
|
1.540
|
0.124
|
0.004
|
|
criticism_items_S_mean
|
Risk
|
0.414
|
0.679
|
0.000
|
1.199
|
0.231
|
0.000
|
|
Help
|
0.017
|
0.987
|
0.000
|
1.575
|
0.116
|
0.000
|
|
DemandSupp_G_mean
|
Risk
|
0.064
|
0.949
|
0.000
|
0.125
|
0.900
|
0.000
|
|
Help
|
0.014
|
0.989
|
0.000
|
0.137
|
0.891
|
0.000
|
|
DemandSupp_S_mean
|
Risk
|
1.748
|
0.081
|
0.002
|
0.809
|
0.419
|
0.002
|
|
Help
|
0.127
|
0.899
|
0.000
|
-1.932
|
0.054
|
0.000
|
|
GlobalVictim
|
Risk
|
6.701
|
< .001
|
0.035
|
5.965
|
< .001
|
0.040
|
|
Help
|
-1.089
|
0.276
|
0.001
|
-3.555
|
< .001
|
0.002
|
|
Villain_G_mean
|
Risk
|
-0.006
|
0.995
|
0.000
|
-0.564
|
0.573
|
0.000
|
|
Help
|
-0.523
|
0.601
|
0.000
|
-1.644
|
0.100
|
0.000
|
|
Villain_S_mean
|
Risk
|
3.632
|
< .001
|
0.009
|
3.078
|
0.002
|
0.010
|
|
Help
|
-0.075
|
0.940
|
0.000
|
-1.298
|
0.194
|
0.000
|
|
Endure_G_mean
|
Risk
|
4.220
|
< .001
|
0.015
|
3.505
|
< .001
|
0.016
|
|
Help
|
1.096
|
0.273
|
0.001
|
-0.606
|
0.544
|
0.001
|
|
Endure_S_mean
|
Risk
|
0.357
|
0.721
|
0.000
|
0.172
|
0.864
|
0.000
|
|
Help
|
0.660
|
0.510
|
0.001
|
0.279
|
0.780
|
0.001
|
|
SelfExploit_G_mean
|
Risk
|
5.480
|
< .001
|
0.025
|
4.865
|
< .001
|
0.026
|
|
Help
|
2.691
|
0.007
|
0.006
|
1.211
|
0.226
|
0.007
|
|
SelfExploit_S_mean
|
Risk
|
0.697
|
0.486
|
0.000
|
0.404
|
0.687
|
0.000
|
|
Help
|
3.303
|
0.001
|
0.009
|
2.672
|
0.008
|
0.009
|
|
GlobalSupportExpl
|
Risk
|
-2.269
|
0.023
|
0.004
|
-1.745
|
0.081
|
0.004
|
|
Help
|
1.202
|
0.230
|
0.001
|
2.305
|
0.021
|
0.001
|
Toggle details of each model (Warning: long output)
fits<-run_prereg_models(scale_scores)
##
##
## ============================================================
## Outcome: GlobalGratitude | Level: unknown level
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: GlobalGratitude ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.30112 -0.59313 0.03678 0.62718 2.10343
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0002094 0.0241467 0.009 0.99308
## Cond1 -0.0023042 0.0242079 -0.095 0.92419
## Risk_cond 0.1302404 0.0483046 2.696 0.00711 **
## Help_cond 0.2255853 0.0483161 4.669 3.37e-06 ***
## Risk_cond:Help_cond -0.0774810 0.0967730 -0.801 0.42350
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8336 on 1187 degrees of freedom
## Multiple R-squared: 0.02417, Adjusted R-squared: 0.02088
## F-statistic: 7.35 on 4 and 1187 DF, p-value: 7.582e-06
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: GlobalGratitude ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.36223 -0.59019 0.01833 0.62010 2.03441
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.001740 0.024148 0.072 0.9426
## Risk_cond 0.127882 0.048366 2.644 0.0083 **
## Help_cond 0.220581 0.048378 4.560 5.66e-06 ***
## Cond1 -0.002033 0.024193 -0.084 0.9331
## Risk_cond:Help_cond -0.070552 0.096779 -0.729 0.4661
## Risk_cond:Cond1 -0.082185 0.048389 -1.698 0.0897 .
## Help_cond:Cond1 -0.041420 0.048388 -0.856 0.3922
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.833 on 1185 degrees of freedom
## Multiple R-squared: 0.02711, Adjusted R-squared: 0.02218
## F-statistic: 5.503 on 6 and 1185 DF, p-value: 1.239e-05
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: GlobalGratitude ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.19080 -0.44096 0.05308 0.46112 2.35567
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0003964 0.0186570 -0.021 0.983
## Cond1 0.0238073 0.0187270 1.271 0.204
## Risk_cond 0.0357576 0.0374714 0.954 0.340
## Help_cond 0.0332298 0.0379442 0.876 0.381
## Attitude 0.5398395 0.0190588 28.325 <2e-16 ***
## Risk_cond:Help_cond -0.1151371 0.0747837 -1.540 0.124
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6441 on 1186 degrees of freedom
## Multiple R-squared: 0.4179, Adjusted R-squared: 0.4155
## F-statistic: 170.3 on 5 and 1186 DF, p-value: < 2.2e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: GlobalGratitude ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.19613 -0.44109 0.05417 0.46448 2.35079
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0003946 0.0186861 -0.021 0.983
## Risk_cond 0.0354680 0.0375689 0.944 0.345
## Help_cond 0.0335259 0.0380187 0.882 0.378
## Cond1 0.0237827 0.0187431 1.269 0.205
## Attitude 0.5399996 0.0191515 28.196 <2e-16 ***
## Risk_cond:Help_cond -0.1153202 0.0749054 -1.540 0.124
## Risk_cond:Cond1 0.0054836 0.0375729 0.146 0.884
## Help_cond:Cond1 -0.0039961 0.0374665 -0.107 0.915
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6446 on 1184 degrees of freedom
## Multiple R-squared: 0.4179, Adjusted R-squared: 0.4145
## F-statistic: 121.5 on 7 and 1184 DF, p-value: < 2.2e-16
##
##
##
## ============================================================
## Outcome: criticism_items_G_mean | Level: general (_G)
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: criticism_items_G_mean ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses (this outcome):
## - H3d: Risk → criticism/hate speech acceptability ↓ [general (_G)]
## - H4d: Helpfulness → criticism/hate speech acceptability ↓ [general (_G)]
## ------------------------------------------------------------
## ✅ H3d supported: β=-0.234, SE=0.064, t=-3.677, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.9425 -0.7832 -0.0032 0.7463 4.2168
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.66934 0.03186 83.772 < 2e-16 ***
## Cond1 0.07631 0.03195 2.389 0.017058 *
## Risk_cond -0.23439 0.06374 -3.677 0.000247 ***
## Help_cond -0.12105 0.06376 -1.899 0.057857 .
## Risk_cond:Help_cond 0.07643 0.12770 0.599 0.549613
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.1 on 1187 degrees of freedom
## Multiple R-squared: 0.0184, Adjusted R-squared: 0.01509
## F-statistic: 5.563 on 4 and 1187 DF, p-value: 0.0001946
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: criticism_items_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses (this outcome):
## - H3d: Risk → criticism/hate speech acceptability ↓ [general (_G)]
## - H4d: Helpfulness → criticism/hate speech acceptability ↓ [general (_G)]
## ------------------------------------------------------------
## ✅ H3d supported: β=-0.232, SE=0.064, t=-3.625, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.9105 -0.7983 0.0121 0.7202 4.2017
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.66851 0.03191 83.634 < 2e-16 ***
## Risk_cond -0.23163 0.06391 -3.625 0.000302 ***
## Help_cond -0.12040 0.06392 -1.884 0.059876 .
## Cond1 0.07635 0.03197 2.388 0.017074 *
## Risk_cond:Help_cond 0.07371 0.12788 0.576 0.564436
## Risk_cond:Cond1 0.01256 0.06394 0.196 0.844261
## Help_cond:Cond1 0.04501 0.06394 0.704 0.481610
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.101 on 1185 degrees of freedom
## Multiple R-squared: 0.01884, Adjusted R-squared: 0.01387
## F-statistic: 3.792 on 6 and 1185 DF, p-value: 0.0009513
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: criticism_items_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3d: Risk → criticism/hate speech acceptability ↓ [general (_G)]
## - H4d: Helpfulness → criticism/hate speech acceptability ↓ [general (_G)]
## ------------------------------------------------------------
## ✅ H3d supported: β=-0.133, SE=0.055, t=-2.425, p=.015
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5290 -0.6423 -0.0491 0.5721 5.1462
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.66999 0.02729 97.841 <2e-16 ***
## Cond1 0.04827 0.02739 1.762 0.0783 .
## Risk_cond -0.13293 0.05481 -2.425 0.0154 *
## Help_cond 0.08550 0.05550 1.540 0.1237
## Attitude -0.57968 0.02788 -20.794 <2e-16 ***
## Risk_cond:Help_cond 0.11687 0.10938 1.068 0.2856
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9421 on 1186 degrees of freedom
## Multiple R-squared: 0.2807, Adjusted R-squared: 0.2776
## F-statistic: 92.55 on 5 and 1186 DF, p-value: < 2.2e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: criticism_items_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3d: Risk → criticism/hate speech acceptability ↓ [general (_G)]
## - H4d: Helpfulness → criticism/hate speech acceptability ↓ [general (_G)]
## ------------------------------------------------------------
## ✅ H3d supported: β=-0.132, SE=0.055, t=-2.402, p=.016
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4985 -0.6709 -0.0375 0.5734 5.1864
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.67081 0.02731 97.810 <2e-16 ***
## Risk_cond -0.13185 0.05490 -2.402 0.0165 *
## Help_cond 0.08156 0.05556 1.468 0.1423
## Cond1 0.04848 0.02739 1.770 0.0770 .
## Attitude -0.58303 0.02799 -20.833 <2e-16 ***
## Risk_cond:Help_cond 0.12205 0.10946 1.115 0.2651
## Risk_cond:Cond1 -0.08209 0.05491 -1.495 0.1351
## Help_cond:Cond1 0.00460 0.05475 0.084 0.9331
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.942 on 1184 degrees of freedom
## Multiple R-squared: 0.282, Adjusted R-squared: 0.2778
## F-statistic: 66.44 on 7 and 1184 DF, p-value: < 2.2e-16
##
##
##
## ============================================================
## Outcome: criticism_items_S_mean | Level: specific (_S)
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: criticism_items_S_mean ~ Cond + Risk_cond * Help_cond
## N used: 1191
## Hypotheses (this outcome):
## - H3d: Risk → criticism/hate speech acceptability ↓ [specific (_S)]
## - H4d: Helpfulness → criticism/hate speech acceptability ↓ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3565 -0.7485 -0.2263 0.6694 2.7628
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.2918609 0.0257267 89.085 <2e-16 ***
## Cond1 0.0494503 0.0257894 1.917 0.0554 .
## Risk_cond 0.0213135 0.0514644 0.414 0.6788
## Help_cond 0.0008514 0.0514764 0.017 0.9868
## Risk_cond:Help_cond -0.0199516 0.1031002 -0.194 0.8466
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8877 on 1186 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.00335, Adjusted R-squared: -1.129e-05
## F-statistic: 0.9966 on 4 and 1186 DF, p-value: 0.4083
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: criticism_items_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1191
## Hypotheses (this outcome):
## - H3d: Risk → criticism/hate speech acceptability ↓ [specific (_S)]
## - H4d: Helpfulness → criticism/hate speech acceptability ↓ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3858 -0.7508 -0.2246 0.6930 2.7291
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.292056 0.025758 88.985 <2e-16 ***
## Risk_cond 0.019178 0.051589 0.372 0.7101
## Help_cond 0.002764 0.051602 0.054 0.9573
## Cond1 0.049254 0.025804 1.909 0.0565 .
## Risk_cond:Help_cond -0.020350 0.103226 -0.197 0.8438
## Risk_cond:Cond1 0.029110 0.051613 0.564 0.5729
## Help_cond:Cond1 -0.033314 0.051611 -0.645 0.5187
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8882 on 1184 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.003977, Adjusted R-squared: -0.001071
## F-statistic: 0.7878 on 6 and 1184 DF, p-value: 0.5795
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: criticism_items_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1191
## Hypotheses (this outcome):
## - H3d: Risk → criticism/hate speech acceptability ↓ [specific (_S)]
## - H4d: Helpfulness → criticism/hate speech acceptability ↓ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.20829 -0.65575 -0.08522 0.60028 3.05005
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.292163 0.024950 91.871 <2e-16 ***
## Cond1 0.038660 0.025041 1.544 0.123
## Risk_cond 0.060084 0.050108 1.199 0.231
## Help_cond 0.079892 0.050738 1.575 0.116
## Attitude -0.222115 0.025477 -8.718 <2e-16 ***
## Risk_cond:Help_cond -0.004258 0.100003 -0.043 0.966
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8609 on 1185 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.06342, Adjusted R-squared: 0.05947
## F-statistic: 16.05 on 5 and 1185 DF, p-value: 2.486e-15
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: criticism_items_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1191
## Hypotheses (this outcome):
## - H3d: Risk → criticism/hate speech acceptability ↓ [specific (_S)]
## - H4d: Helpfulness → criticism/hate speech acceptability ↓ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.2437 -0.6601 -0.1057 0.5981 3.0291
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.292971 0.024978 91.800 <2e-16 ***
## Risk_cond 0.057323 0.050217 1.142 0.254
## Help_cond 0.080037 0.050817 1.575 0.116
## Cond1 0.038551 0.025053 1.539 0.124
## Attitude -0.223256 0.025590 -8.724 <2e-16 ***
## Risk_cond:Help_cond -0.001720 0.100123 -0.017 0.986
## Risk_cond:Cond1 -0.007075 0.050221 -0.141 0.888
## Help_cond:Cond1 -0.048727 0.050079 -0.973 0.331
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8613 on 1183 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.06419, Adjusted R-squared: 0.05865
## F-statistic: 11.59 on 7 and 1183 DF, p-value: 2.605e-14
##
##
##
## ============================================================
## Outcome: DemandSupp_G_mean | Level: general (_G)
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: DemandSupp_G_mean ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses (this outcome):
## - H3b: Risk → support for workers' demands ↑ [general (_G)]
## - H4b: Helpfulness → support for workers' demands ↑ [general (_G)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1920 -0.9312 0.0688 0.9635 3.2243
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.984409 0.040951 97.297 < 2e-16 ***
## Cond1 0.130382 0.041055 3.176 0.00153 **
## Risk_cond 0.005219 0.081921 0.064 0.94922
## Help_cond 0.001122 0.081941 0.014 0.98908
## Risk_cond:Help_cond -0.300512 0.164121 -1.831 0.06734 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.414 on 1187 degrees of freedom
## Multiple R-squared: 0.01186, Adjusted R-squared: 0.00853
## F-statistic: 3.562 on 4 and 1187 DF, p-value: 0.006761
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: DemandSupp_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses (this outcome):
## - H3b: Risk → support for workers' demands ↑ [general (_G)]
## - H4b: Helpfulness → support for workers' demands ↑ [general (_G)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1967 -0.9412 0.0588 0.9731 3.2265
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.9841392 0.0410145 97.140 < 2e-16 ***
## Risk_cond 0.0063438 0.0821470 0.077 0.93846
## Help_cond 0.0010175 0.0821684 0.012 0.99012
## Cond1 0.1304235 0.0410907 3.174 0.00154 **
## Risk_cond:Help_cond -0.3012370 0.1643759 -1.833 0.06711 .
## Risk_cond:Cond1 -0.0008511 0.0821874 -0.010 0.99174
## Help_cond:Cond1 0.0181194 0.0821850 0.220 0.82554
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.415 on 1185 degrees of freedom
## Multiple R-squared: 0.0119, Adjusted R-squared: 0.006898
## F-statistic: 2.379 on 6 and 1185 DF, p-value: 0.02737
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: DemandSupp_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3b: Risk → support for workers' demands ↑ [general (_G)]
## - H4b: Helpfulness → support for workers' demands ↑ [general (_G)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2300 -0.9511 0.0291 0.9693 3.2711
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.98444 0.04096 97.276 < 2e-16 ***
## Cond1 0.12898 0.04111 3.137 0.00175 **
## Risk_cond 0.01029 0.08227 0.125 0.90046
## Help_cond 0.01145 0.08330 0.137 0.89070
## Attitude -0.02899 0.04184 -0.693 0.48861
## Risk_cond:Help_cond -0.29849 0.16418 -1.818 0.06931 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.414 on 1186 degrees of freedom
## Multiple R-squared: 0.01226, Adjusted R-squared: 0.008095
## F-statistic: 2.944 on 5 and 1186 DF, p-value: 0.01198
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: DemandSupp_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3b: Risk → support for workers' demands ↑ [general (_G)]
## - H4b: Helpfulness → support for workers' demands ↑ [general (_G)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2400 -0.9561 0.0293 0.9695 3.2664
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.984254 0.041024 97.120 < 2e-16 ***
## Risk_cond 0.011296 0.082480 0.137 0.89109
## Help_cond 0.011041 0.083467 0.132 0.89478
## Cond1 0.129040 0.041149 3.136 0.00176 **
## Attitude -0.028937 0.042046 -0.688 0.49144
## Risk_cond:Help_cond -0.298838 0.164449 -1.817 0.06944 .
## Risk_cond:Cond1 -0.005549 0.082489 -0.067 0.94638
## Help_cond:Cond1 0.016114 0.082255 0.196 0.84472
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.415 on 1184 degrees of freedom
## Multiple R-squared: 0.0123, Adjusted R-squared: 0.006456
## F-statistic: 2.106 on 7 and 1184 DF, p-value: 0.04034
##
##
##
## ============================================================
## Outcome: DemandSupp_S_mean | Level: specific (_S)
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: DemandSupp_S_mean ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses (this outcome):
## - H3b: Risk → support for workers' demands ↑ [specific (_S)]
## - H4b: Helpfulness → support for workers' demands ↑ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.2271 -0.7463 0.1360 0.8047 2.3047
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.982093 0.036292 137.278 < 2e-16 ***
## Cond1 -0.197811 0.036384 -5.437 6.58e-08 ***
## Risk_cond 0.126926 0.072601 1.748 0.0807 .
## Help_cond 0.009214 0.072618 0.127 0.8991
## Risk_cond:Help_cond -0.083586 0.145448 -0.575 0.5656
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.253 on 1187 degrees of freedom
## Multiple R-squared: 0.02648, Adjusted R-squared: 0.02319
## F-statistic: 8.07 on 4 and 1187 DF, p-value: 2.027e-06
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: DemandSupp_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses (this outcome):
## - H3b: Risk → support for workers' demands ↑ [specific (_S)]
## - H4b: Helpfulness → support for workers' demands ↑ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.3130 -0.7200 0.1005 0.7886 2.2886
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.984535 0.036298 137.323 < 2e-16 ***
## Risk_cond 0.119358 0.072700 1.642 0.1009
## Help_cond 0.006526 0.072719 0.090 0.9285
## Cond1 -0.197859 0.036365 -5.441 6.44e-08 ***
## Risk_cond:Help_cond -0.075194 0.145473 -0.517 0.6053
## Risk_cond:Cond1 -0.048826 0.072736 -0.671 0.5022
## Help_cond:Cond1 -0.124121 0.072734 -1.707 0.0882 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.252 on 1185 degrees of freedom
## Multiple R-squared: 0.02921, Adjusted R-squared: 0.02429
## F-statistic: 5.942 on 6 and 1185 DF, p-value: 3.969e-06
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: DemandSupp_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3b: Risk → support for workers' demands ↑ [specific (_S)]
## - H4b: Helpfulness → support for workers' demands ↑ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.6665 -0.5927 0.0743 0.8335 2.6518
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.98164 0.03443 144.695 < 2e-16 ***
## Cond1 -0.17819 0.03456 -5.156 2.95e-07 ***
## Risk_cond 0.05595 0.06915 0.809 0.4186
## Help_cond -0.13529 0.07002 -1.932 0.0536 .
## Attitude 0.40555 0.03517 11.531 < 2e-16 ***
## Risk_cond:Help_cond -0.11188 0.13800 -0.811 0.4177
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.189 on 1186 degrees of freedom
## Multiple R-squared: 0.1246, Adjusted R-squared: 0.1209
## F-statistic: 33.77 on 5 and 1186 DF, p-value: < 2.2e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: DemandSupp_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3b: Risk → support for workers' demands ↑ [specific (_S)]
## - H4b: Helpfulness → support for workers' demands ↑ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.7261 -0.5758 0.0920 0.7907 2.5975
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.98294 0.03445 144.627 < 2e-16 ***
## Risk_cond 0.05012 0.06927 0.724 0.4695
## Help_cond -0.13362 0.07010 -1.906 0.0569 .
## Cond1 -0.17852 0.03456 -5.166 2.81e-07 ***
## Attitude 0.40458 0.03531 11.457 < 2e-16 ***
## Risk_cond:Help_cond -0.10874 0.13811 -0.787 0.4313
## Risk_cond:Cond1 0.01686 0.06928 0.243 0.8078
## Help_cond:Cond1 -0.09608 0.06908 -1.391 0.1645
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.189 on 1184 degrees of freedom
## Multiple R-squared: 0.1261, Adjusted R-squared: 0.1209
## F-statistic: 24.41 on 7 and 1184 DF, p-value: < 2.2e-16
##
##
##
## ============================================================
## Outcome: GlobalVictim | Level: unknown level
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: GlobalVictim ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.44446 -0.53092 -0.00233 0.52292 2.56463
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0007449 0.0230606 -0.032 0.974
## Cond1 -0.1447419 0.0231191 -6.261 5.35e-10 ***
## Risk_cond 0.3091352 0.0461321 6.701 3.19e-11 ***
## Help_cond -0.0502585 0.0461431 -1.089 0.276
## Risk_cond:Help_cond -0.0966867 0.0924206 -1.046 0.296
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7961 on 1187 degrees of freedom
## Multiple R-squared: 0.06658, Adjusted R-squared: 0.06343
## F-statistic: 21.17 on 4 and 1187 DF, p-value: < 2.2e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: GlobalVictim ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.41368 -0.52475 -0.01441 0.49911 2.59350
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.001706 0.023072 -0.074 0.941
## Risk_cond 0.309636 0.046211 6.701 3.20e-11 ***
## Help_cond -0.045752 0.046223 -0.990 0.322
## Cond1 -0.145036 0.023115 -6.275 4.91e-10 ***
## Risk_cond:Help_cond -0.101724 0.092468 -1.100 0.272
## Risk_cond:Cond1 0.072807 0.046233 1.575 0.116
## Help_cond:Cond1 0.011061 0.046232 0.239 0.811
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7959 on 1185 degrees of freedom
## Multiple R-squared: 0.06856, Adjusted R-squared: 0.06385
## F-statistic: 14.54 on 6 and 1185 DF, p-value: 4.592e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: GlobalVictim ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.31638 -0.47580 0.01706 0.48309 2.40265
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.001076 0.021492 -0.050 0.960077
## Cond1 -0.130469 0.021572 -6.048 1.96e-09 ***
## Risk_cond 0.257491 0.043165 5.965 3.22e-09 ***
## Help_cond -0.155400 0.043709 -3.555 0.000392 ***
## Attitude 0.295075 0.021954 13.440 < 2e-16 ***
## Risk_cond:Help_cond -0.117269 0.086146 -1.361 0.173682
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7419 on 1186 degrees of freedom
## Multiple R-squared: 0.19, Adjusted R-squared: 0.1865
## F-statistic: 55.62 on 5 and 1186 DF, p-value: < 2.2e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: GlobalVictim ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.36183 -0.49221 0.00904 0.46609 2.32559
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.002895 0.021449 -0.135 0.892675
## Risk_cond 0.258170 0.043124 5.987 2.84e-09 ***
## Help_cond -0.149925 0.043640 -3.435 0.000612 ***
## Cond1 -0.130660 0.021515 -6.073 1.69e-09 ***
## Attitude 0.300729 0.021983 13.680 < 2e-16 ***
## Risk_cond:Help_cond -0.126656 0.085982 -1.473 0.141002
## Risk_cond:Cond1 0.121630 0.043129 2.820 0.004880 **
## Help_cond:Cond1 0.031903 0.043007 0.742 0.458353
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7399 on 1184 degrees of freedom
## Multiple R-squared: 0.1957, Adjusted R-squared: 0.1909
## F-statistic: 41.15 on 7 and 1184 DF, p-value: < 2.2e-16
##
##
##
## ============================================================
## Outcome: Villain_G_mean | Level: general (_G)
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: Villain_G_mean ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses (this outcome):
## - H3e: Risk → support for workers' impunity ↑ [general (_G)]
## - H4e: Helpfulness → support for workers' impunity ↑ [general (_G)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.0202 -0.8080 0.0188 0.9043 3.3129
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.8534028 0.0367392 104.885 < 2e-16 ***
## Cond1 0.1288977 0.0368324 3.500 0.000483 ***
## Risk_cond -0.0004371 0.0734957 -0.006 0.995256
## Help_cond -0.0384674 0.0735132 -0.523 0.600883
## Risk_cond:Help_cond 0.0736009 0.1472405 0.500 0.617261
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.268 on 1187 degrees of freedom
## Multiple R-squared: 0.01042, Adjusted R-squared: 0.00709
## F-statistic: 3.126 on 4 and 1187 DF, p-value: 0.01431
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: Villain_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses (this outcome):
## - H3e: Risk → support for workers' impunity ↑ [general (_G)]
## - H4e: Helpfulness → support for workers' impunity ↑ [general (_G)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.0550 -0.7905 0.0511 0.9067 3.2655
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.854543 0.036765 104.844 < 2e-16 ***
## Risk_cond -0.006678 0.073635 -0.091 0.927757
## Help_cond -0.035955 0.073654 -0.488 0.625531
## Cond1 0.128532 0.036833 3.490 0.000502 ***
## Risk_cond:Help_cond 0.075624 0.147344 0.513 0.607875
## Risk_cond:Cond1 0.035769 0.073672 0.486 0.627396
## Help_cond:Cond1 -0.099248 0.073669 -1.347 0.178172
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.268 on 1185 degrees of freedom
## Multiple R-squared: 0.01215, Adjusted R-squared: 0.007146
## F-statistic: 2.429 on 6 and 1185 DF, p-value: 0.02445
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: Villain_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3e: Risk → support for workers' impunity ↑ [general (_G)]
## - H4e: Helpfulness → support for workers' impunity ↑ [general (_G)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3465 -0.8157 0.0812 0.8552 3.4522
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.85314 0.03616 106.554 < 2e-16 ***
## Cond1 0.14009 0.03630 3.860 0.00012 ***
## Risk_cond -0.04093 0.07263 -0.564 0.57312
## Help_cond -0.12092 0.07354 -1.644 0.10042
## Attitude 0.23139 0.03694 6.264 5.24e-10 ***
## Risk_cond:Help_cond 0.05746 0.14495 0.396 0.69186
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.248 on 1186 degrees of freedom
## Multiple R-squared: 0.04211, Adjusted R-squared: 0.03807
## F-statistic: 10.43 on 5 and 1186 DF, p-value: 8.278e-10
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: Villain_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3e: Risk → support for workers' impunity ↑ [general (_G)]
## - H4e: Helpfulness → support for workers' impunity ↑ [general (_G)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.4226 -0.8523 0.0803 0.8610 3.3686
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.85362 0.03618 106.506 < 2e-16 ***
## Risk_cond -0.04656 0.07275 -0.640 0.522303
## Help_cond -0.11667 0.07362 -1.585 0.113260
## Cond1 0.13967 0.03629 3.849 0.000125 ***
## Attitude 0.23302 0.03708 6.284 4.64e-10 ***
## Risk_cond:Help_cond 0.05631 0.14504 0.388 0.697936
## Risk_cond:Cond1 0.07360 0.07275 1.012 0.311917
## Help_cond:Cond1 -0.08310 0.07255 -1.145 0.252257
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.248 on 1184 degrees of freedom
## Multiple R-squared: 0.04403, Adjusted R-squared: 0.03838
## F-statistic: 7.79 on 7 and 1184 DF, p-value: 3.056e-09
##
##
##
## ============================================================
## Outcome: Villain_S_mean | Level: specific (_S)
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: Villain_S_mean ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses (this outcome):
## - H3e: Risk → support for workers' impunity ↑ [specific (_S)]
## - H4e: Helpfulness → support for workers' impunity ↑ [specific (_S)]
## ------------------------------------------------------------
## ✅ H3e supported: β=0.323, SE=0.089, t=3.632, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.7178 -0.9619 0.2822 1.2240 2.6880
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.040677 0.044492 113.293 < 2e-16 ***
## Cond1 -0.544592 0.044605 -12.209 < 2e-16 ***
## Risk_cond 0.323259 0.089005 3.632 0.000293 ***
## Help_cond -0.006686 0.089027 -0.075 0.940145
## Risk_cond:Help_cond -0.103190 0.178312 -0.579 0.562900
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.536 on 1187 degrees of freedom
## Multiple R-squared: 0.1192, Adjusted R-squared: 0.1162
## F-statistic: 40.17 on 4 and 1187 DF, p-value: < 2.2e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: Villain_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses (this outcome):
## - H3e: Risk → support for workers' impunity ↑ [specific (_S)]
## - H4e: Helpfulness → support for workers' impunity ↑ [specific (_S)]
## ------------------------------------------------------------
## ✅ H3e supported: β=0.322, SE=0.089, t=3.618, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.6457 -0.9097 0.3028 1.2984 2.7702
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.039115 0.044507 113.221 < 2e-16 ***
## Risk_cond 0.322486 0.089142 3.618 0.00031 ***
## Help_cond 0.002850 0.089165 0.032 0.97451
## Cond1 -0.545272 0.044590 -12.229 < 2e-16 ***
## Risk_cond:Help_cond -0.112491 0.178372 -0.631 0.52839
## Risk_cond:Cond1 0.152714 0.089185 1.712 0.08710 .
## Help_cond:Cond1 -0.006226 0.089183 -0.070 0.94436
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.535 on 1185 degrees of freedom
## Multiple R-squared: 0.1214, Adjusted R-squared: 0.1169
## F-statistic: 27.29 on 6 and 1185 DF, p-value: < 2.2e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: Villain_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3e: Risk → support for workers' impunity ↑ [specific (_S)]
## - H4e: Helpfulness → support for workers' impunity ↑ [specific (_S)]
## ------------------------------------------------------------
## ✅ H3e supported: β=0.270, SE=0.088, t=3.078, p=.002
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.0480 -0.9158 0.2409 1.0786 3.6107
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.04034 0.04366 115.446 < 2e-16 ***
## Cond1 -0.52985 0.04382 -12.091 < 2e-16 ***
## Risk_cond 0.26991 0.08769 3.078 0.00213 **
## Help_cond -0.11530 0.08879 -1.298 0.19438
## Attitude 0.30481 0.04460 6.834 1.31e-11 ***
## Risk_cond:Help_cond -0.12445 0.17500 -0.711 0.47714
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.507 on 1186 degrees of freedom
## Multiple R-squared: 0.1526, Adjusted R-squared: 0.149
## F-statistic: 42.71 on 5 and 1186 DF, p-value: < 2.2e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: Villain_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3e: Risk → support for workers' impunity ↑ [specific (_S)]
## - H4e: Helpfulness → support for workers' impunity ↑ [specific (_S)]
## ------------------------------------------------------------
## ✅ H3e supported: β=0.269, SE=0.088, t=3.065, p=.002
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.9496 -0.9578 0.2554 1.0504 3.7601
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.03788 0.04363 115.471 < 2e-16 ***
## Risk_cond 0.26881 0.08772 3.065 0.00223 **
## Help_cond -0.10579 0.08877 -1.192 0.23361
## Cond1 -0.53028 0.04376 -12.117 < 2e-16 ***
## Attitude 0.31362 0.04472 7.014 3.9e-12 ***
## Risk_cond:Help_cond -0.13849 0.17489 -0.792 0.42860
## Risk_cond:Cond1 0.20363 0.08773 2.321 0.02045 *
## Help_cond:Cond1 0.01551 0.08748 0.177 0.85931
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.505 on 1184 degrees of freedom
## Multiple R-squared: 0.1564, Adjusted R-squared: 0.1515
## F-statistic: 31.37 on 7 and 1184 DF, p-value: < 2.2e-16
##
##
##
## ============================================================
## Outcome: Endure_G_mean | Level: general (_G)
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: Endure_G_mean ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses (this outcome):
## - H3f: Risk → belief they'd choose suffering for duty ↑ [general (_G)]
## - H4f: Helpfulness → belief they'd choose suffering for duty ↑ [general (_G)]
## ------------------------------------------------------------
## ✅ H3f supported: β=0.295, SE=0.070, t=4.220, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2523 -0.6994 0.0846 0.8346 3.1190
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.01030 0.03492 114.843 < 2e-16 ***
## Cond1 -0.04345 0.03501 -1.241 0.215
## Risk_cond 0.29481 0.06986 4.220 2.63e-05 ***
## Help_cond 0.07657 0.06987 1.096 0.273
## Risk_cond:Help_cond 0.05160 0.13995 0.369 0.712
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.205 on 1187 degrees of freedom
## Multiple R-squared: 0.01684, Adjusted R-squared: 0.01353
## F-statistic: 5.083 on 4 and 1187 DF, p-value: 0.0004612
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: Endure_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses (this outcome):
## - H3f: Risk → belief they'd choose suffering for duty ↑ [general (_G)]
## - H4f: Helpfulness → belief they'd choose suffering for duty ↑ [general (_G)]
## ------------------------------------------------------------
## ✅ H3f supported: β=0.285, SE=0.070, t=4.079, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3236 -0.7665 0.1078 0.8578 3.1821
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.01255 0.03490 114.969 < 2e-16 ***
## Risk_cond 0.28514 0.06990 4.079 4.82e-05 ***
## Help_cond 0.07781 0.06992 1.113 0.2660
## Cond1 -0.04384 0.03497 -1.254 0.2102
## Risk_cond:Help_cond 0.05748 0.13987 0.411 0.6812
## Risk_cond:Cond1 0.01282 0.06994 0.183 0.8546
## Help_cond:Cond1 -0.15552 0.06993 -2.224 0.0263 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.204 on 1185 degrees of freedom
## Multiple R-squared: 0.02096, Adjusted R-squared: 0.016
## F-statistic: 4.229 on 6 and 1185 DF, p-value: 0.0003208
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: Endure_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3f: Risk → belief they'd choose suffering for duty ↑ [general (_G)]
## - H4f: Helpfulness → belief they'd choose suffering for duty ↑ [general (_G)]
## ------------------------------------------------------------
## ✅ H3f supported: β=0.237, SE=0.068, t=3.505, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6385 -0.6714 0.0829 0.7586 2.8980
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.00993 0.03364 119.196 < 2e-16 ***
## Cond1 -0.02743 0.03377 -0.812 0.416774
## Risk_cond 0.23683 0.06757 3.505 0.000473 ***
## Help_cond -0.04148 0.06842 -0.606 0.544455
## Attitude 0.33129 0.03437 9.640 < 2e-16 ***
## Risk_cond:Help_cond 0.02850 0.13485 0.211 0.832675
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.161 on 1186 degrees of freedom
## Multiple R-squared: 0.08828, Adjusted R-squared: 0.08444
## F-statistic: 22.97 on 5 and 1186 DF, p-value: < 2.2e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: Endure_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3f: Risk → belief they'd choose suffering for duty ↑ [general (_G)]
## - H4f: Helpfulness → belief they'd choose suffering for duty ↑ [general (_G)]
## ------------------------------------------------------------
## ✅ H3f supported: β=0.228, SE=0.068, t=3.378, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6451 -0.6540 0.1012 0.7816 2.9265
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.01124 0.03362 119.294 < 2e-16 ***
## Risk_cond 0.22836 0.06760 3.378 0.000754 ***
## Help_cond -0.03712 0.06841 -0.543 0.587541
## Cond1 -0.02798 0.03373 -0.830 0.406984
## Attitude 0.33177 0.03446 9.627 < 2e-16 ***
## Risk_cond:Help_cond 0.02998 0.13479 0.222 0.824037
## Risk_cond:Cond1 0.06668 0.06761 0.986 0.324217
## Help_cond:Cond1 -0.13253 0.06742 -1.966 0.049560 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.16 on 1184 degrees of freedom
## Multiple R-squared: 0.09204, Adjusted R-squared: 0.08667
## F-statistic: 17.15 on 7 and 1184 DF, p-value: < 2.2e-16
##
##
##
## ============================================================
## Outcome: Endure_S_mean | Level: specific (_S)
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: Endure_S_mean ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses (this outcome):
## - H3f: Risk → belief they'd choose suffering for duty ↑ [specific (_S)]
## - H4f: Helpfulness → belief they'd choose suffering for duty ↑ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8793 -0.9046 -0.2966 0.7341 3.5954
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.61686 0.03804 95.089 < 2e-16 ***
## Cond1 0.21933 0.03813 5.752 1.12e-08 ***
## Risk_cond 0.02717 0.07609 0.357 0.721
## Help_cond 0.05020 0.07611 0.660 0.510
## Risk_cond:Help_cond -0.12643 0.15244 -0.829 0.407
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.313 on 1187 degrees of freedom
## Multiple R-squared: 0.02897, Adjusted R-squared: 0.0257
## F-statistic: 8.854 on 4 and 1187 DF, p-value: 4.806e-07
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: Endure_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses (this outcome):
## - H3f: Risk → belief they'd choose suffering for duty ↑ [specific (_S)]
## - H4f: Helpfulness → belief they'd choose suffering for duty ↑ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9032 -0.9130 -0.2986 0.7138 3.5777
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.617220 0.038091 94.963 < 2e-16 ***
## Risk_cond 0.027748 0.076291 0.364 0.716
## Help_cond 0.047460 0.076311 0.622 0.534
## Cond1 0.219532 0.038162 5.753 1.12e-08 ***
## Risk_cond:Help_cond -0.124018 0.152658 -0.812 0.417
## Risk_cond:Cond1 -0.043617 0.076329 -0.571 0.568
## Help_cond:Cond1 0.007498 0.076326 0.098 0.922
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.314 on 1185 degrees of freedom
## Multiple R-squared: 0.02925, Adjusted R-squared: 0.02433
## F-statistic: 5.951 on 6 and 1185 DF, p-value: 3.877e-06
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: Endure_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3f: Risk → belief they'd choose suffering for duty ↑ [specific (_S)]
## - H4f: Helpfulness → belief they'd choose suffering for duty ↑ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9911 -0.9150 -0.2285 0.7905 3.5845
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.61677 0.03798 95.218 < 2e-16 ***
## Cond1 0.22322 0.03813 5.855 6.18e-09 ***
## Risk_cond 0.01310 0.07629 0.172 0.8637
## Help_cond 0.02155 0.07725 0.279 0.7803
## Attitude 0.08041 0.03880 2.072 0.0385 *
## Risk_cond:Help_cond -0.13204 0.15225 -0.867 0.3860
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.311 on 1186 degrees of freedom
## Multiple R-squared: 0.03248, Adjusted R-squared: 0.0284
## F-statistic: 7.962 on 5 and 1186 DF, p-value: 2.159e-07
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: Endure_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3f: Risk → belief they'd choose suffering for duty ↑ [specific (_S)]
## - H4f: Helpfulness → belief they'd choose suffering for duty ↑ [specific (_S)]
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.0100 -0.9240 -0.2217 0.7975 3.5760
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.61691 0.03804 95.080 < 2e-16 ***
## Risk_cond 0.01417 0.07648 0.185 0.8531
## Help_cond 0.01997 0.07740 0.258 0.7964
## Cond1 0.22333 0.03816 5.853 6.25e-09 ***
## Attitude 0.07935 0.03899 2.035 0.0421 *
## Risk_cond:Help_cond -0.13060 0.15249 -0.856 0.3919
## Risk_cond:Cond1 -0.03074 0.07649 -0.402 0.6879
## Help_cond:Cond1 0.01300 0.07627 0.170 0.8647
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.312 on 1184 degrees of freedom
## Multiple R-squared: 0.03263, Adjusted R-squared: 0.02691
## F-statistic: 5.706 on 7 and 1184 DF, p-value: 1.665e-06
##
##
##
## ============================================================
## Outcome: SelfExploit_G_mean | Level: general (_G)
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: SelfExploit_G_mean ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses (this outcome):
## - H3g: Risk → belief they'd accept exploitation if required ↑ [general (_G)]
## - H4g: Helpfulness → belief they'd accept exploitation if required ↑ [general (_G)]
## ------------------------------------------------------------
## ✅ H3g supported: β=0.381, SE=0.070, t=5.480, p=<.001
## ✅ H4g supported: β=0.187, SE=0.070, t=2.691, p=.007
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.5524 -0.6250 0.1040 0.7661 3.0161
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.25557 0.03478 122.357 < 2e-16 ***
## Cond1 0.03630 0.03487 1.041 0.29810
## Risk_cond 0.38125 0.06958 5.480 5.2e-08 ***
## Help_cond 0.18727 0.06959 2.691 0.00722 **
## Risk_cond:Help_cond 0.19539 0.13939 1.402 0.16124
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.201 on 1187 degrees of freedom
## Multiple R-squared: 0.03274, Adjusted R-squared: 0.02949
## F-statistic: 10.05 on 4 and 1187 DF, p-value: 5.358e-08
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: SelfExploit_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses (this outcome):
## - H3g: Risk → belief they'd accept exploitation if required ↑ [general (_G)]
## - H4g: Helpfulness → belief they'd accept exploitation if required ↑ [general (_G)]
## ------------------------------------------------------------
## ✅ H3g supported: β=0.369, SE=0.070, t=5.302, p=<.001
## ✅ H4g supported: β=0.188, SE=0.070, t=2.698, p=.007
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6566 -0.6566 0.0881 0.8277 3.1086
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.258775 0.034707 122.705 < 2e-16 ***
## Risk_cond 0.368563 0.069515 5.302 1.37e-07 ***
## Help_cond 0.187593 0.069533 2.698 0.00708 **
## Cond1 0.035883 0.034772 1.032 0.30231
## Risk_cond:Help_cond 0.204461 0.139099 1.470 0.14186
## Risk_cond:Cond1 -0.004218 0.069549 -0.061 0.95165
## Help_cond:Cond1 -0.204909 0.069547 -2.946 0.00328 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.197 on 1185 degrees of freedom
## Multiple R-squared: 0.03978, Adjusted R-squared: 0.03492
## F-statistic: 8.182 on 6 and 1185 DF, p-value: 1.086e-08
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: SelfExploit_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3g: Risk → belief they'd accept exploitation if required ↑ [general (_G)]
## - H4g: Helpfulness → belief they'd accept exploitation if required ↑ [general (_G)]
## ------------------------------------------------------------
## ✅ H3g supported: β=0.330, SE=0.068, t=4.865, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.7990 -0.6218 0.1323 0.7547 3.1024
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.25525 0.03379 125.934 < 2e-16 ***
## Cond1 0.05042 0.03392 1.487 0.137
## Risk_cond 0.33013 0.06786 4.865 1.3e-06 ***
## Help_cond 0.08319 0.06872 1.211 0.226
## Attitude 0.29209 0.03452 8.462 < 2e-16 ***
## Risk_cond:Help_cond 0.17502 0.13544 1.292 0.197
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.166 on 1186 degrees of freedom
## Multiple R-squared: 0.08782, Adjusted R-squared: 0.08397
## F-statistic: 22.84 on 5 and 1186 DF, p-value: < 2.2e-16
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: SelfExploit_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3g: Risk → belief they'd accept exploitation if required ↑ [general (_G)]
## - H4g: Helpfulness → belief they'd accept exploitation if required ↑ [general (_G)]
## ------------------------------------------------------------
## ✅ H3g supported: β=0.319, SE=0.068, t=4.701, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.9037 -0.6292 0.1434 0.7287 2.9787
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.25763 0.03373 126.227 < 2e-16 ***
## Risk_cond 0.31882 0.06782 4.701 2.89e-06 ***
## Help_cond 0.08691 0.06863 1.266 0.20563
## Cond1 0.04978 0.03383 1.471 0.14147
## Attitude 0.29066 0.03457 8.408 < 2e-16 ***
## Risk_cond:Help_cond 0.18036 0.13521 1.334 0.18248
## Risk_cond:Cond1 0.04297 0.06782 0.634 0.52648
## Help_cond:Cond1 -0.18476 0.06763 -2.732 0.00639 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.164 on 1184 degrees of freedom
## Multiple R-squared: 0.09388, Adjusted R-squared: 0.08852
## F-statistic: 17.52 on 7 and 1184 DF, p-value: < 2.2e-16
##
##
##
## ============================================================
## Outcome: SelfExploit_S_mean | Level: specific (_S)
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: SelfExploit_S_mean ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses (this outcome):
## - H3g: Risk → belief they'd accept exploitation if required ↑ [specific (_S)]
## - H4g: Helpfulness → belief they'd accept exploitation if required ↑ [specific (_S)]
## ------------------------------------------------------------
## ✅ H4g supported: β=0.247, SE=0.075, t=3.303, p=<.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.6905 -1.0448 -0.3436 0.8416 4.7028
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.460987 0.037328 65.928 < 2e-16 ***
## Cond1 0.006823 0.037423 0.182 0.855368
## Risk_cond 0.052076 0.074674 0.697 0.485705
## Help_cond 0.246700 0.074692 3.303 0.000985 ***
## Risk_cond:Help_cond 0.293379 0.149601 1.961 0.050103 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.289 on 1187 degrees of freedom
## Multiple R-squared: 0.01272, Adjusted R-squared: 0.009392
## F-statistic: 3.823 on 4 and 1187 DF, p-value: 0.00429
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: SelfExploit_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses (this outcome):
## - H3g: Risk → belief they'd accept exploitation if required ↑ [specific (_S)]
## - H4g: Helpfulness → belief they'd accept exploitation if required ↑ [specific (_S)]
## ------------------------------------------------------------
## ✅ H4g supported: β=0.240, SE=0.075, t=3.213, p=.001
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7586 -1.0919 -0.3045 0.8212 4.7230
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.463057 0.037346 65.952 < 2e-16 ***
## Risk_cond 0.048563 0.074800 0.649 0.51631
## Help_cond 0.240380 0.074819 3.213 0.00135 **
## Cond1 0.007149 0.037416 0.191 0.84850
## Risk_cond:Help_cond 0.302526 0.149674 2.021 0.04348 *
## Risk_cond:Cond1 -0.104197 0.074836 -1.392 0.16408
## Help_cond:Cond1 -0.060950 0.074834 -0.814 0.41554
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.288 on 1185 degrees of freedom
## Multiple R-squared: 0.01486, Adjusted R-squared: 0.009871
## F-statistic: 2.979 on 6 and 1185 DF, p-value: 0.006835
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: SelfExploit_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3g: Risk → belief they'd accept exploitation if required ↑ [specific (_S)]
## - H4g: Helpfulness → belief they'd accept exploitation if required ↑ [specific (_S)]
## ------------------------------------------------------------
## ✅ H4g supported: β=0.202, SE=0.076, t=2.672, p=.008
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.8385 -1.0530 -0.2675 0.8458 4.5059
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.46085 0.03717 66.199 < 2e-16 ***
## Cond1 0.01289 0.03731 0.345 0.729903
## Risk_cond 0.03014 0.07466 0.404 0.686536
## Help_cond 0.20204 0.07560 2.672 0.007635 **
## Attitude 0.12535 0.03797 3.301 0.000993 ***
## Risk_cond:Help_cond 0.28464 0.14900 1.910 0.056342 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.283 on 1186 degrees of freedom
## Multiple R-squared: 0.02171, Adjusted R-squared: 0.01758
## F-statistic: 5.263 on 5 and 1186 DF, p-value: 8.687e-05
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: SelfExploit_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses (this outcome):
## - H3g: Risk → belief they'd accept exploitation if required ↑ [specific (_S)]
## - H4g: Helpfulness → belief they'd accept exploitation if required ↑ [specific (_S)]
## ------------------------------------------------------------
## ✅ H4g supported: β=0.199, SE=0.076, t=2.622, p=.009
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.8757 -1.0945 -0.2831 0.8310 4.5278
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.46258 0.03720 66.190 < 2e-16 ***
## Risk_cond 0.02788 0.07480 0.373 0.70947
## Help_cond 0.19851 0.07570 2.622 0.00884 **
## Cond1 0.01293 0.03732 0.346 0.72908
## Attitude 0.12088 0.03813 3.170 0.00156 **
## Risk_cond:Help_cond 0.29250 0.14914 1.961 0.05008 .
## Risk_cond:Cond1 -0.08457 0.07481 -1.131 0.25849
## Help_cond:Cond1 -0.05257 0.07460 -0.705 0.48111
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.283 on 1184 degrees of freedom
## Multiple R-squared: 0.02315, Adjusted R-squared: 0.01738
## F-statistic: 4.009 on 7 and 1184 DF, p-value: 0.0002399
##
##
##
## ============================================================
## Outcome: GlobalSupportExpl | Level: unknown level
## ============================================================
##
## ------------------------------------------------------------
## Heroism + occupation as a covariate
## Formula: GlobalSupportExpl ~ Cond + Risk_cond * Help_cond
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.2493 -0.6761 -0.1213 0.5148 3.9355
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0004483 0.0243377 0.018 0.9853
## Cond1 0.0474236 0.0243995 1.944 0.0522 .
## Risk_cond -0.1104554 0.0486869 -2.269 0.0235 *
## Help_cond 0.0585225 0.0486985 1.202 0.2297
## Risk_cond:Help_cond 0.0453346 0.0975388 0.465 0.6422
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8402 on 1187 degrees of freedom
## Multiple R-squared: 0.008793, Adjusted R-squared: 0.005453
## F-statistic: 2.633 on 4 and 1187 DF, p-value: 0.0329
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator
## Formula: GlobalSupportExpl ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.2536 -0.6678 -0.1234 0.5094 3.9311
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.001251 0.024367 0.051 0.9591
## Risk_cond -0.112023 0.048805 -2.295 0.0219 *
## Help_cond 0.056360 0.048818 1.155 0.2485
## Cond1 0.047524 0.024413 1.947 0.0518 .
## Risk_cond:Help_cond 0.048735 0.097658 0.499 0.6178
## Risk_cond:Cond1 -0.035916 0.048829 -0.736 0.4621
## Help_cond:Cond1 -0.026764 0.048827 -0.548 0.5837
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8406 on 1185 degrees of freedom
## Multiple R-squared: 0.009488, Adjusted R-squared: 0.004473
## F-statistic: 1.892 on 6 and 1185 DF, p-value: 0.07908
##
##
## ------------------------------------------------------------
## Heroism + occupation and attitude as covariates)
## Formula: GlobalSupportExpl ~ Cond + Risk_cond * Help_cond + Attitude
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.6708 -0.6354 -0.1146 0.5112 3.2864
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0006179 0.0239663 0.026 0.9794
## Cond1 0.0401160 0.0240562 1.668 0.0957 .
## Risk_cond -0.0840130 0.0481349 -1.745 0.0812 .
## Help_cond 0.1123559 0.0487422 2.305 0.0213 *
## Attitude -0.1510817 0.0244824 -6.171 9.3e-10 ***
## Risk_cond:Help_cond 0.0558732 0.0960653 0.582 0.5609
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8274 on 1186 degrees of freedom
## Multiple R-squared: 0.03963, Adjusted R-squared: 0.03558
## F-statistic: 9.788 on 5 and 1186 DF, p-value: 3.521e-09
##
##
## ------------------------------------------------------------
## Heroism + occupation as a moderator + attitude as a covariate
## Formula: GlobalSupportExpl ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond + Cond + Attitude
## N used: 1192
## Hypotheses: (no mapping found for this outcome name)
## ------------------------------------------------------------
##
## Call:
## lm(formula = form, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7354 -0.6361 -0.1270 0.5032 3.2615
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.00186 0.02398 0.078 0.9382
## Risk_cond -0.08562 0.04822 -1.776 0.0760 .
## Help_cond 0.10981 0.04879 2.250 0.0246 *
## Cond1 0.04015 0.02405 1.669 0.0954 .
## Attitude -0.15429 0.02458 -6.277 4.83e-10 ***
## Risk_cond:Help_cond 0.06153 0.09613 0.640 0.5223
## Risk_cond:Cond1 -0.06096 0.04822 -1.264 0.2064
## Help_cond:Cond1 -0.03746 0.04809 -0.779 0.4361
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8273 on 1184 degrees of freedom
## Multiple R-squared: 0.04139, Adjusted R-squared: 0.03572
## F-statistic: 7.303 on 7 and 1184 DF, p-value: 1.346e-08
We can also compare models including attitudes to models not
including attitudes – following our registration. This will help us
quantify the extent to which attitude contributes to our outcome above
and beyond the manipulations:
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: GRATITUDE GLOBAL")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: GRATITUDE GLOBAL
anova(fits$GlobalGratitude$Model_1, fits$GlobalGratitude$Model_3)
## Analysis of Variance Table
##
## Model 1: GlobalGratitude ~ Cond + Risk_cond * Help_cond
## Model 2: GlobalGratitude ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 824.80
## 2 1186 491.98 1 332.82 802.31 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$GlobalGratitude$Model_2, fits$GlobalGratitude$Model_4)
## Analysis of Variance Table
##
## Model 1: GlobalGratitude ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond
## Model 2: GlobalGratitude ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 822.31
## 2 1184 491.97 1 330.35 795.03 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: criticism_items_G_mean")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: criticism_items_G_mean
anova(fits$criticism_items_G_mean$Model_1, fits$criticism_items_G_mean$Model_3)
## Analysis of Variance Table
##
## Model 1: criticism_items_G_mean ~ Cond + Risk_cond * Help_cond
## Model 2: criticism_items_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 1436.3
## 2 1186 1052.5 1 383.75 432.4 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$criticism_items_G_mean$Model_2, fits$criticism_items_G_mean$Model_4)
## Analysis of Variance Table
##
## Model 1: criticism_items_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond
## Model 2: criticism_items_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 1435.7
## 2 1184 1050.5 1 385.1 434.02 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: criticism_items_S_mean")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: criticism_items_S_mean
anova(fits$criticism_items_S_mean$Model_1, fits$criticism_items_S_mean$Model_3)
## Analysis of Variance Table
##
## Model 1: criticism_items_S_mean ~ Cond + Risk_cond * Help_cond
## Model 2: criticism_items_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1186 934.68
## 2 1185 878.34 1 56.338 76.008 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$criticism_items_S_mean$Model_2, fits$criticism_items_S_mean$Model_4)
## Analysis of Variance Table
##
## Model 1: criticism_items_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond
## Model 2: criticism_items_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1184 934.09
## 2 1183 877.62 1 56.465 76.112 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: DemandSupp_G_mean")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: DemandSupp_G_mean
anova(fits$DemandSupp_G_mean$Model_1, fits$DemandSupp_G_mean$Model_3)
## Analysis of Variance Table
##
## Model 1: DemandSupp_G_mean ~ Cond + Risk_cond * Help_cond
## Model 2: DemandSupp_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 2372.3
## 2 1186 2371.3 1 0.95951 0.4799 0.4886
anova(fits$DemandSupp_G_mean$Model_2, fits$DemandSupp_G_mean$Model_4)
## Analysis of Variance Table
##
## Model 1: DemandSupp_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond
## Model 2: DemandSupp_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 2372.2
## 2 1184 2371.2 1 0.94863 0.4737 0.4914
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: DemandSupp_S_mean")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: DemandSupp_S_mean
anova(fits$DemandSupp_S_mean$Model_1, fits$DemandSupp_S_mean$Model_3)
## Analysis of Variance Table
##
## Model 1: DemandSupp_S_mean ~ Cond + Risk_cond * Help_cond
## Model 2: DemandSupp_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 1863.2
## 2 1186 1675.4 1 187.83 132.97 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$DemandSupp_S_mean$Model_2, fits$DemandSupp_S_mean$Model_4)
## Analysis of Variance Table
##
## Model 1: DemandSupp_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond
## Model 2: DemandSupp_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 1858.0
## 2 1184 1672.5 1 185.44 131.27 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: GlobalVictim")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: GlobalVictim
anova(fits$GlobalVictim$Model_1, fits$GlobalVictim$Model_3)
## Analysis of Variance Table
##
## Model 1: GlobalVictim ~ Cond + Risk_cond * Help_cond
## Model 2: GlobalVictim ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 752.28
## 2 1186 652.84 1 99.435 180.64 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$GlobalVictim$Model_2, fits$GlobalVictim$Model_4)
## Analysis of Variance Table
##
## Model 1: GlobalVictim ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond
## Model 2: GlobalVictim ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 750.67
## 2 1184 648.22 1 102.45 187.14 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: Villain_G_mean")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: Villain_G_mean
anova(fits$Villain_G_mean$Model_1, fits$Villain_G_mean$Model_3)
## Analysis of Variance Table
##
## Model 1: Villain_G_mean ~ Cond + Risk_cond * Help_cond
## Model 2: Villain_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 1909.4
## 2 1186 1848.2 1 61.144 39.235 5.244e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$Villain_G_mean$Model_2, fits$Villain_G_mean$Model_4)
## Analysis of Variance Table
##
## Model 1: Villain_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond
## Model 2: Villain_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 1906.1
## 2 1184 1844.5 1 61.514 39.485 4.636e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: Villain_S_mean")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: Villain_S_mean
anova(fits$Villain_S_mean$Model_1, fits$Villain_S_mean$Model_3)
## Analysis of Variance Table
##
## Model 1: Villain_S_mean ~ Cond + Risk_cond * Help_cond
## Model 2: Villain_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 2800.3
## 2 1186 2694.2 1 106.1 46.708 1.314e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$Villain_S_mean$Model_2, fits$Villain_S_mean$Model_4)
## Analysis of Variance Table
##
## Model 1: Villain_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond
## Model 2: Villain_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 2793.4
## 2 1184 2681.9 1 111.42 49.19 3.897e-12 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: Endure_G_mean")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: Endure_G_mean
anova(fits$Endure_G_mean$Model_1, fits$Endure_G_mean$Model_3)
## Analysis of Variance Table
##
## Model 1: Endure_G_mean ~ Cond + Risk_cond * Help_cond
## Model 2: Endure_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 1725.0
## 2 1186 1599.6 1 125.34 92.932 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$Endure_G_mean$Model_2, fits$Endure_G_mean$Model_4)
## Analysis of Variance Table
##
## Model 1: Endure_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond
## Model 2: Endure_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 1717.7
## 2 1184 1593.0 1 124.7 92.682 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: Endure_S_mean")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: Endure_S_mean
anova(fits$Endure_S_mean$Model_1, fits$Endure_S_mean$Model_3)
## Analysis of Variance Table
##
## Model 1: Endure_S_mean ~ Cond + Risk_cond * Help_cond
## Model 2: Endure_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 2046.6
## 2 1186 2039.2 1 7.3836 4.2942 0.03846 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$Endure_S_mean$Model_2, fits$Endure_S_mean$Model_4)
## Analysis of Variance Table
##
## Model 1: Endure_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond
## Model 2: Endure_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond + Cond:Help_cond +
## Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 2046.0
## 2 1184 2038.9 1 7.1324 4.1418 0.04206 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: SelfExploit_G_mean")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: SelfExploit_G_mean
anova(fits$SelfExploit_G_mean$Model_1, fits$SelfExploit_G_mean$Model_3)
## Analysis of Variance Table
##
## Model 1: SelfExploit_G_mean ~ Cond + Risk_cond * Help_cond
## Model 2: SelfExploit_G_mean ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 1711.2
## 2 1186 1613.7 1 97.433 71.608 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$SelfExploit_G_mean$Model_2, fits$SelfExploit_G_mean$Model_4)
## Analysis of Variance Table
##
## Model 1: SelfExploit_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond
## Model 2: SelfExploit_G_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 1698.7
## 2 1184 1603.0 1 95.712 70.694 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: SelfExploit_S_mean")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: SelfExploit_S_mean
anova(fits$SelfExploit_S_mean$Model_1, fits$SelfExploit_S_mean$Model_3)
## Analysis of Variance Table
##
## Model 1: SelfExploit_S_mean ~ Cond + Risk_cond * Help_cond
## Model 2: SelfExploit_S_mean ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 1971.1
## 2 1186 1953.2 1 17.943 10.895 0.0009927 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$SelfExploit_S_mean$Model_2, fits$SelfExploit_S_mean$Model_4)
## Analysis of Variance Table
##
## Model 1: SelfExploit_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond
## Model 2: SelfExploit_S_mean ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 1966.8
## 2 1184 1950.3 1 16.555 10.05 0.001562 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("## COMPARING MODELS WITH AND WITHOUT ATTITUDE: GlobalSupportExpl")
## ## COMPARING MODELS WITH AND WITHOUT ATTITUDE: GlobalSupportExpl
anova(fits$GlobalSupportExpl$Model_1, fits$GlobalSupportExpl$Model_3)
## Analysis of Variance Table
##
## Model 1: GlobalSupportExpl ~ Cond + Risk_cond * Help_cond
## Model 2: GlobalSupportExpl ~ Cond + Risk_cond * Help_cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1187 837.91
## 2 1186 811.84 1 26.067 38.082 9.296e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(fits$GlobalSupportExpl$Model_2, fits$GlobalSupportExpl$Model_4)
## Analysis of Variance Table
##
## Model 1: GlobalSupportExpl ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond
## Model 2: GlobalSupportExpl ~ Risk_cond * Help_cond + Cond:Risk_cond +
## Cond:Help_cond + Cond + Attitude
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 1185 837.32
## 2 1184 810.35 1 26.969 39.404 4.827e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Aside from the General measures of support for workers (which is a
very bad measure as indicated in our measurement model) and - somewhat -
the specific enduring pain items (which are also bad according to our
measurement model): All models indicate a significantly better
fit when accounting for attitude.
TO SUM UP:
H1. Gratitude Participants expressed
greater gratitude toward occupations framed as exposed to risk or
helpful. The effects were accounted by attitude.
H2. Shielding from criticism Participants
were more likely to shield occupations framed as exposed to risk or
helpful from criticism, although this effect emerged only for the
general-level measure. The effect of helpfulness was accounted by
attitude - but not the effect of risk.
H3. Support for workers’ demands
Participants were more likely to support demands from occupations framed
as exposed to risk, but not those framed as helpful, and this effect
emerged only for the specific-level measure. The effect was accounted by
attitude.
H4. Perceived suffering Participants were
more likely to perceive workers from occupations framed as exposed to
risk as suffering (but not those framed as helpful). This effect was not
fully accounted by attitude. (Interestingly, accounting for attitude
resulted in a negative effect of helpfulness: occupations
framed as helpful were perceived as less victimised after accounting for
attitude)
H5. Protection of rule-breaking workers
Participants were more likely to support protecting rule-breaking
workers from occupations framed as exposed to risk, but not those framed
as helpful, and this effect emerged only for the general-level measure.
This effect was not fully accounted by attitude.
H6. Perceived acceptance of exploitative
policies Participants were more likely to perceive workers
from occupations framed as exposed to risk or helpful as willing to
accept exploitative policies using the general level
measure; the effect of helpfulness was accounted by attitude,
but not the effect of risk.
Participants were more likely to perceive workers from occupations
framed as helpful as willing to accept exploitative policies
using the specific level measure; this effect of
helpfulness was not fully accounted by attitude.
H7. Support for exploitative policies
Participants were less likely to support exploitative policies for
workers from occupations framed as exposed to risk, but not those framed
as helpful. This effect was accounted by attitude (Interestingly,
accounting for attitude resulted in a negative effect of
helpfulness: occupations framed as helpful were more exploited after
accounting for attitude)
H8. Perceived willingness to endure pain
Participants were more likely to perceive workers from occupations
framed as exposed to risk as willing to endure greater pain, but not
those framed as helpful, and this effect emerged only for the
general-level measure. This effect was not fully accounted by
attitude.
Overall, it seems the credibily of our descriptions was average,
slightly credible. The welders condition was more credible than the
psychiatrists condition – which is expected as welders occupations is
less attached to stereotypes than the psych occupation.
