library(here)
library(tidyverse)
library(psych)
library(readr)
library(stats)
library(dplyr)
library(stargazer)
library(apaTables)
library(car)s3 <- read_csv(here("data", "s3.csv"))
s6 <- read_csv(here("data", "s6.csv"))
s8 <- read_csv(here("data", "s8.csv"))
s9 <- read_csv(here("data", "s9.csv"))
s13 <- read_csv(here("data", "s13.csv"))cor.test(s3$zsm_mean, s3$zs_beliefs_US_politics_mean)##
## Pearson's product-moment correlation
##
## data: s3$zsm_mean and s3$zs_beliefs_US_politics_mean
## t = 12.093, df = 507, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.4027905 0.5379295
## sample estimates:
## cor
## 0.4731385cor.test(s8$zsm_mean, s8$zs_beliefs_India_Pakistan_mean) # India##
## Pearson's product-moment correlation
##
## data: s8$zsm_mean and s8$zs_beliefs_India_Pakistan_mean
## t = 11.344, df = 253, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.4929768 0.6566593
## sample estimates:
## cor
## 0.5806557cor.test(s9$zsm_mean, s9$zs_beliefs_India_Pakistan_mean) # Pakistan##
## Pearson's product-moment correlation
##
## data: s9$zsm_mean and s9$zs_beliefs_India_Pakistan_mean
## t = 9.534, df = 647, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.2816215 0.4166818
## sample estimates:
## cor
## 0.3509758A zero-sum mindset will predict specific zero-sum beliefs about a disparate variety of social and economic resources (H4a).
Resources examined: jobs, empathy, respect, status
# Creating dataframe with zero-sum beliefs
zs_df <- select(s6, starts_with("zs_"), -contains("mean"))
colnames(zs_df)## [1] "zs_empathy_group_2" "zs_empathy_group_1" "zs_empathy_ind_1"
## [4] "zs_empathy_ind_2" "zs_jobs_group" "zs_jobs_ind"
## [7] "zs_status_group_1" "zs_respect_group_1" "zs_respect_ind_2"
## [10] "zs_status_ind_2"psych::omega(zs_df, nfactors = 1)## Omega
## Call: omegah(m = m, nfactors = nfactors, fm = fm, key = key, flip = flip,
## digits = digits, title = title, sl = sl, labels = labels,
## plot = plot, n.obs = n.obs, rotate = rotate, Phi = Phi, option = option,
## covar = covar)
## Alpha: 0.93
## G.6: 0.95
## Omega Hierarchical: 0.93
## Omega H asymptotic: 1
## Omega Total 0.93
##
## Schmid Leiman Factor loadings greater than 0.2
## g F1* h2 u2 p2
## zs_empathy_group_2 0.79 0.62 0.38 1
## zs_empathy_group_1 0.80 0.64 0.36 1
## zs_empathy_ind_1 0.72 0.51 0.49 1
## zs_empathy_ind_2 0.85 0.72 0.28 1
## zs_jobs_group 0.66 0.44 0.56 1
## zs_jobs_ind 0.60 0.36 0.64 1
## zs_status_group_1 0.78 0.60 0.40 1
## zs_respect_group_1 0.84 0.71 0.29 1
## zs_respect_ind_2 0.82 0.68 0.32 1
## zs_status_ind_2 0.80 0.63 0.37 1
##
## With Sums of squares of:
## g F1*
## 5.9 0.0
##
## general/max 1.06465e+17 max/min = 1
## mean percent general = 1 with sd = 0 and cv of 0
## Explained Common Variance of the general factor = 1
##
## The degrees of freedom are 35 and the fit is 1.34
## The number of observations was 499 with Chi Square = 660.93 with prob < 1.4e-116
## The root mean square of the residuals is 0.07
## The df corrected root mean square of the residuals is 0.08
## RMSEA index = 0.189 and the 10 % confidence intervals are 0.177 0.202
## BIC = 443.49
##
## Compare this with the adequacy of just a general factor and no group factors
## The degrees of freedom for just the general factor are 35 and the fit is 1.34
## The number of observations was 499 with Chi Square = 660.93 with prob < 1.4e-116
## The root mean square of the residuals is 0.07
## The df corrected root mean square of the residuals is 0.08
##
## RMSEA index = 0.189 and the 10 % confidence intervals are 0.177 0.202
## BIC = 443.49
##
## Measures of factor score adequacy
## g F1*
## Correlation of scores with factors 0.97 0
## Multiple R square of scores with factors 0.94 0
## Minimum correlation of factor score estimates 0.88 -1
##
## Total, General and Subset omega for each subset
## g F1*
## Omega total for total scores and subscales 0.93 0.93
## Omega general for total scores and subscales 0.93 0.93
## Omega group for total scores and subscales 0.00 0.00zs_means <- select(s6, zsm_mean, starts_with("zs_") & contains("mean") )
colnames(zs_means)## [1] "zsm_mean" "zs_empathy_mean" "zs_jobs_mean" "zs_status_mean"
## [5] "zs_respect_mean"psych::omega(zs_means, nfactors = 1)## Omega
## Call: omegah(m = m, nfactors = nfactors, fm = fm, key = key, flip = flip,
## digits = digits, title = title, sl = sl, labels = labels,
## plot = plot, n.obs = n.obs, rotate = rotate, Phi = Phi, option = option,
## covar = covar)
## Alpha: 0.9
## G.6: 0.88
## Omega Hierarchical: 0.9
## Omega H asymptotic: 1
## Omega Total 0.9
##
## Schmid Leiman Factor loadings greater than 0.2
## g F1* h2 u2 p2
## zsm_mean 0.71 0.50 0.50 1
## zs_empathy_mean 0.82 0.68 0.32 1
## zs_jobs_mean 0.68 0.47 0.53 1
## zs_status_mean 0.89 0.79 0.21 1
## zs_respect_mean 0.88 0.77 0.23 1
##
## With Sums of squares of:
## g F1*
## 3.2 0.0
##
## general/max 5.767768e+16 max/min = 1
## mean percent general = 1 with sd = 0 and cv of 0
## Explained Common Variance of the general factor = 1
##
## The degrees of freedom are 5 and the fit is 0.05
## The number of observations was 499 with Chi Square = 23.45 with prob < 0.00028
## The root mean square of the residuals is 0.02
## The df corrected root mean square of the residuals is 0.03
## RMSEA index = 0.086 and the 10 % confidence intervals are 0.053 0.123
## BIC = -7.61
##
## Compare this with the adequacy of just a general factor and no group factors
## The degrees of freedom for just the general factor are 5 and the fit is 0.05
## The number of observations was 499 with Chi Square = 23.45 with prob < 0.00028
## The root mean square of the residuals is 0.02
## The df corrected root mean square of the residuals is 0.03
##
## RMSEA index = 0.086 and the 10 % confidence intervals are 0.053 0.123
## BIC = -7.61
##
## Measures of factor score adequacy
## g F1*
## Correlation of scores with factors 0.96 0
## Multiple R square of scores with factors 0.92 0
## Minimum correlation of factor score estimates 0.83 -1
##
## Total, General and Subset omega for each subset
## g F1*
## Omega total for total scores and subscales 0.9 0.9
## Omega general for total scores and subscales 0.9 0.9
## Omega group for total scores and subscales 0.0 0.0# Zero-Order Correlations between Zero-sum mindset and specific zero-sum beliefs
apaTables::apa.cor.table(zs_means)##
##
## Means, standard deviations, and correlations with confidence intervals
##
##
## Variable M SD 1 2 3 4
## 1. zsm_mean 2.67 1.02
##
## 2. zs_empathy_mean 2.80 1.41 .61**
## [.55, .66]
##
## 3. zs_jobs_mean 3.39 1.50 .48** .58**
## [.41, .54] [.52, .63]
##
## 4. zs_status_mean 2.83 1.37 .63** .69** .62**
## [.57, .68] [.65, .74] [.57, .67]
##
## 5. zs_respect_mean 2.43 1.27 .61** .72** .57** .80**
## [.55, .66] [.68, .76] [.51, .63] [.77, .83]
##
##
## Note. M and SD are used to represent mean and standard deviation, respectively.
## Values in square brackets indicate the 95% confidence interval.
## The confidence interval is a plausible range of population correlations
## that could have caused the sample correlation (Cumming, 2014).
## * indicates p < .05. ** indicates p < .01.
## s6$participant_id <- 1:nrow(s6)
zs_means <- select(s6, starts_with("zs_" ) & contains("mean"), participant_id)
zs_means <- filter(zs_means, complete.cases(zs_means))
# Load the necessary package
library(tidyverse)
# Reshape the data using pivot_longer()
reshaped_data <- zs_means %>%
pivot_longer(cols = starts_with("zs_"),
names_to = "belief_domain",
values_to = "score")
# Print the reshaped data
print(reshaped_data)## # A tibble: 1,996 × 3
## participant_id belief_domain score
## <int> <chr> <dbl>
## 1 1 zs_empathy_mean 2
## 2 1 zs_jobs_mean 5
## 3 1 zs_status_mean 3
## 4 1 zs_respect_mean 3
## 5 2 zs_empathy_mean 1
## 6 2 zs_jobs_mean 1
## 7 2 zs_status_mean 1
## 8 2 zs_respect_mean 1
## 9 3 zs_empathy_mean 2
## 10 3 zs_jobs_mean 3
## # ℹ 1,986 more rows# Load the necessary package
library(ez)
# Perform repeated measures ANOVA using ezANOVA()
anova_result <- ezANOVA(data = reshaped_data, dv = score,
wid = participant_id, within = belief_domain, detailed = TRUE)
# Print the ANOVA table
print(anova_result)## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 498 16397.7159 2858.8778 2856.3874 2.090594e-208 *
## 2 belief_domain 3 1494 235.4203 985.1109 119.0113 4.116714e-69 *
## ges
## 1 0.81009560
## 2 0.05770942
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 2 belief_domain 0.7374703 7.185481e-31 *
##
## $`Sphericity Corrections`
## Effect GGe p[GG] p[GG]<.05 HFe p[HF]
## 2 belief_domain 0.8432409 9.46509e-59 * 0.8479026 4.655001e-59
## p[HF]<.05
## 2 *# Perform repeated measures ANOVA using ezANOVA()
anova_result <- ezANOVA(data = reshaped_data, dv = score,
wid = participant_id, within = belief_domain, detailed = TRUE)
# Print the ANOVA table
print(anova_result)## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 498 16397.7159 2858.8778 2856.3874 2.090594e-208 *
## 2 belief_domain 3 1494 235.4203 985.1109 119.0113 4.116714e-69 *
## ges
## 1 0.81009560
## 2 0.05770942
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 2 belief_domain 0.7374703 7.185481e-31 *
##
## $`Sphericity Corrections`
## Effect GGe p[GG] p[GG]<.05 HFe p[HF]
## 2 belief_domain 0.8432409 9.46509e-59 * 0.8479026 4.655001e-59
## p[HF]<.05
## 2 *# The corrected p-values obtained from these corrections are both less than the chosen significance level (p < 0.05), indicating a significant effect of belief_domain on the scores even after accounting for the violation of sphericity.
# The results suggest that there are significant differences in scores across the belief domains within participants, regardless of the specific correction method used.# As composite -- describing variance explained
domain_specific_zs_beliefs_df <- select(s6, zs_empathy_mean, zs_jobs_mean, zs_respect_mean, zs_status_mean)
s6$domain_specific_zsbeliefs_mean <- rowMeans(domain_specific_zs_beliefs_df)
# Model Comparison
#Filtering out missing values for model comparison
s6_complete <- s6 %>%
filter(complete.cases(select(., sex, income, education, age, political_lean, race, zsm_mean, A, O, C, N, E, domain_specific_zsbeliefs_mean, p_abundant)))
nrow(s6)## [1] 499nrow(s6_complete)## [1] 471# Simple Model
test_1 <- lm(scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean), data = s6_complete)
summary(test_1)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean),
## data = s6_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.22803 -0.46405 -0.00809 0.43578 2.58678
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -8.723e-17 3.445e-02 0.00 1
## scale(zsm_mean) 6.649e-01 3.449e-02 19.28 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7477 on 469 degrees of freedom
## Multiple R-squared: 0.4421, Adjusted R-squared: 0.4409
## F-statistic: 371.6 on 1 and 469 DF, p-value: < 2.2e-16# Full Model
test_2 <- lm(scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean) + scale(p_abundant) + scale(p_changing) + scale(p_cooperative) + scale(p_harmless) + scale(p_hierarchical) + scale(p_improvable) + scale(A) + scale(O) + scale(C) + scale(E) + scale(N) + scale(income) + scale(age) + scale(education) + as.factor(race) + as.factor(sex) + as.factor(political_lean), data = s6_complete)
summary(test_2)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean) +
## scale(p_abundant) + scale(p_changing) + scale(p_cooperative) +
## scale(p_harmless) + scale(p_hierarchical) + scale(p_improvable) +
## scale(A) + scale(O) + scale(C) + scale(E) + scale(N) + scale(income) +
## scale(age) + scale(education) + as.factor(race) + as.factor(sex) +
## as.factor(political_lean), data = s6_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.06415 -0.42531 0.03621 0.38930 2.11700
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.233338 0.157620 1.480 0.1395
## scale(zsm_mean) 0.526670 0.038270 13.762 < 2e-16 ***
## scale(p_abundant) 0.012348 0.045289 0.273 0.7852
## scale(p_changing) -0.025663 0.035872 -0.715 0.4747
## scale(p_cooperative) -0.082045 0.046587 -1.761 0.0789 .
## scale(p_harmless) -0.050002 0.043399 -1.152 0.2499
## scale(p_hierarchical) 0.175168 0.037057 4.727 3.06e-06 ***
## scale(p_improvable) -0.058253 0.042716 -1.364 0.1733
## scale(A) -0.062017 0.037535 -1.652 0.0992 .
## scale(O) -0.049893 0.035830 -1.393 0.1645
## scale(C) -0.003485 0.039087 -0.089 0.9290
## scale(E) 0.022274 0.039630 0.562 0.5744
## scale(N) -0.029400 0.046750 -0.629 0.5297
## scale(income) 0.031370 0.035574 0.882 0.3783
## scale(age) -0.030540 0.037175 -0.822 0.4118
## scale(education) -0.030223 0.034579 -0.874 0.3826
## as.factor(race)Black/African American -0.172905 0.167557 -1.032 0.3027
## as.factor(race)Latinx -0.177736 0.163142 -1.089 0.2765
## as.factor(race)Mixed -0.331655 0.181608 -1.826 0.0685 .
## as.factor(race)Other -0.052298 0.261859 -0.200 0.8418
## as.factor(race)White -0.141485 0.122434 -1.156 0.2485
## as.factor(sex)Male 0.091707 0.071776 1.278 0.2020
## as.factor(political_lean)Liberal -0.209738 0.110037 -1.906 0.0573 .
## as.factor(political_lean)Moderate -0.061485 0.114457 -0.537 0.5914
## as.factor(political_lean)N/A 0.190374 0.309074 0.616 0.5382
## as.factor(political_lean)Other 0.027676 0.185217 0.149 0.8813
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6951 on 445 degrees of freedom
## Multiple R-squared: 0.5425, Adjusted R-squared: 0.5168
## F-statistic: 21.11 on 25 and 445 DF, p-value: < 2.2e-16# Full Model Sans Zero-Sum Mindset
test_2b <- lm(scale(domain_specific_zsbeliefs_mean) ~ scale(p_abundant) + scale(p_changing) + scale(p_cooperative) + scale(p_harmless) + scale(p_hierarchical) + scale(p_improvable) + scale(A) + scale(O) + scale(C) + scale(E) + scale(N) + scale(income) + scale(age) + scale(education) + as.factor(race) + as.factor(sex) + as.factor(political_lean), data = s6_complete)
summary(test_2b)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(p_abundant) +
## scale(p_changing) + scale(p_cooperative) + scale(p_harmless) +
## scale(p_hierarchical) + scale(p_improvable) + scale(A) +
## scale(O) + scale(C) + scale(E) + scale(N) + scale(income) +
## scale(age) + scale(education) + as.factor(race) + as.factor(sex) +
## as.factor(political_lean), data = s6_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.7705 -0.5725 -0.0526 0.4511 3.1105
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.427416 0.187231 2.283 0.022911 *
## scale(p_abundant) -0.098488 0.053154 -1.853 0.064559 .
## scale(p_changing) -0.058714 0.042687 -1.375 0.169679
## scale(p_cooperative) -0.173586 0.054992 -3.157 0.001705 **
## scale(p_harmless) -0.034345 0.051743 -0.664 0.507180
## scale(p_hierarchical) 0.246560 0.043761 5.634 3.12e-08 ***
## scale(p_improvable) -0.107190 0.050769 -2.111 0.035299 *
## scale(A) -0.159863 0.043955 -3.637 0.000308 ***
## scale(O) -0.044675 0.042730 -1.046 0.296352
## scale(C) -0.016581 0.046603 -0.356 0.722171
## scale(E) 0.069516 0.047087 1.476 0.140557
## scale(N) -0.059938 0.055693 -1.076 0.282411
## scale(income) -0.002679 0.042325 -0.063 0.949558
## scale(age) -0.076897 0.044154 -1.742 0.082277 .
## scale(education) -0.037488 0.041235 -0.909 0.363775
## as.factor(race)Black/African American -0.120665 0.199786 -0.604 0.546169
## as.factor(race)Latinx -0.204700 0.194557 -1.052 0.293309
## as.factor(race)Mixed -0.579982 0.215523 -2.691 0.007390 **
## as.factor(race)Other 0.057123 0.312162 0.183 0.854888
## as.factor(race)White -0.282250 0.145511 -1.940 0.053044 .
## as.factor(sex)Male 0.110467 0.085588 1.291 0.197481
## as.factor(political_lean)Liberal -0.325608 0.130850 -2.488 0.013196 *
## as.factor(political_lean)Moderate -0.138370 0.136345 -1.015 0.310723
## as.factor(political_lean)N/A -0.226454 0.366842 -0.617 0.537348
## as.factor(political_lean)Other -0.108909 0.220582 -0.494 0.621735
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.829 on 446 degrees of freedom
## Multiple R-squared: 0.3479, Adjusted R-squared: 0.3128
## F-statistic: 9.912 on 24 and 446 DF, p-value: < 2.2e-16# Full Model Reversed sans domain-specific beliefs
test_2_r <- lm(scale(zsm_mean) ~ scale(domain_specific_zsbeliefs_mean) + scale(p_abundant) + scale(p_changing) + scale(p_cooperative) + scale(p_harmless) + scale(p_hierarchical) + scale(p_improvable) + scale(A) + scale(O) + scale(C) + scale(E) + scale(N) + scale(income) + scale(age) + scale(education) + as.factor(race) + as.factor(sex) + as.factor(political_lean), data = s6_complete)
summary(test_2_r)##
## Call:
## lm(formula = scale(zsm_mean) ~ scale(domain_specific_zsbeliefs_mean) +
## scale(p_abundant) + scale(p_changing) + scale(p_cooperative) +
## scale(p_harmless) + scale(p_hierarchical) + scale(p_improvable) +
## scale(A) + scale(O) + scale(C) + scale(E) + scale(N) + scale(income) +
## scale(age) + scale(education) + as.factor(race) + as.factor(sex) +
## as.factor(political_lean), data = s6_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.94204 -0.43910 -0.07692 0.43183 2.81972
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.126219 0.163816 0.770 0.441415
## scale(domain_specific_zsbeliefs_mean) 0.566854 0.041189 13.762 < 2e-16 ***
## scale(p_abundant) -0.154618 0.046414 -3.331 0.000937 ***
## scale(p_changing) -0.029473 0.037211 -0.792 0.428748
## scale(p_cooperative) -0.075414 0.048368 -1.559 0.119665
## scale(p_harmless) 0.049197 0.045031 1.092 0.275205
## scale(p_hierarchical) -0.004210 0.039398 -0.107 0.914945
## scale(p_improvable) -0.032156 0.044382 -0.725 0.469118
## scale(A) -0.095163 0.038798 -2.453 0.014559 *
## scale(O) 0.035232 0.037215 0.947 0.344293
## scale(C) -0.015467 0.040544 -0.381 0.703034
## scale(E) 0.050295 0.041059 1.225 0.221246
## scale(N) -0.024007 0.048509 -0.495 0.620915
## scale(income) -0.063132 0.036817 -1.715 0.087088 .
## scale(age) -0.044430 0.038539 -1.153 0.249588
## scale(education) 0.007457 0.035902 0.208 0.835568
## as.factor(race)Black/African American 0.167589 0.173858 0.964 0.335598
## as.factor(race)Latinx 0.064839 0.169449 0.383 0.702164
## as.factor(race)Mixed -0.142739 0.188992 -0.755 0.450489
## as.factor(race)Other 0.175380 0.271550 0.646 0.518711
## as.factor(race)White -0.107280 0.127108 -0.844 0.399120
## as.factor(sex)Male -0.026999 0.074589 -0.362 0.717545
## as.factor(political_lean)Liberal -0.035434 0.114610 -0.309 0.757339
## as.factor(political_lean)Moderate -0.067549 0.118739 -0.569 0.569722
## as.factor(political_lean)N/A -0.663074 0.319241 -2.077 0.038372 *
## as.factor(political_lean)Other -0.197602 0.191930 -1.030 0.303778
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7211 on 445 degrees of freedom
## Multiple R-squared: 0.5076, Adjusted R-squared: 0.48
## F-statistic: 18.35 on 25 and 445 DF, p-value: < 2.2e-16# Compute VIF for each predictor
vif_values <- car::vif(test_2)
# Check if any VIF values are greater than 10
high_vif <- which(vif_values > 10)
# Generate a message based on the results
if(length(high_vif) == 0) {
message <- "Based on the Variance Inflation Factor (VIF) values, there is no indication of problematic multicollinearity in the model."
} else {
problematic_vars <- names(vif_values)[high_vif]
message <- paste("Based on the Variance Inflation Factor (VIF) values, there is an indication of problematic multicollinearity for the following variables:",
paste(problematic_vars, collapse = ", "), ". Consider examining the relationships among these variables or potentially revising the model.")
}
# Print the message
print(message)## [1] "Based on the Variance Inflation Factor (VIF) values, there is no indication of problematic multicollinearity in the model."# Regression Tables
#table <-apaTables::apa.reg.table(test_1, test_2, filename = "Study4_H4a_reg_table2.doc")Resources examined: jobs, empathy, respect, status
# Creating dataframe with zero-sum beliefs
zs_df <- select(s6, starts_with("zs_"), -contains("mean"))
colnames(zs_df)## [1] "zs_empathy_group_2" "zs_empathy_group_1" "zs_empathy_ind_1"
## [4] "zs_empathy_ind_2" "zs_jobs_group" "zs_jobs_ind"
## [7] "zs_status_group_1" "zs_respect_group_1" "zs_respect_ind_2"
## [10] "zs_status_ind_2"psych::alpha(zs_df)##
## Reliability analysis
## Call: psych::alpha(x = zs_df)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.93 0.93 0.95 0.58 14 0.0046 2.9 1.2 0.57
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.92 0.93 0.94
## Duhachek 0.92 0.93 0.94
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r
## zs_empathy_group_2 0.92 0.93 0.94 0.58 12 0.0053 0.0116
## zs_empathy_group_1 0.92 0.93 0.94 0.58 12 0.0053 0.0111
## zs_empathy_ind_1 0.93 0.93 0.94 0.59 13 0.0050 0.0115
## zs_empathy_ind_2 0.92 0.92 0.93 0.57 12 0.0054 0.0105
## zs_jobs_group 0.93 0.93 0.94 0.60 14 0.0048 0.0124
## zs_jobs_ind 0.93 0.93 0.94 0.61 14 0.0046 0.0092
## zs_status_group_1 0.92 0.93 0.94 0.58 13 0.0052 0.0128
## zs_respect_group_1 0.92 0.92 0.93 0.57 12 0.0054 0.0112
## zs_respect_ind_2 0.92 0.92 0.93 0.58 12 0.0053 0.0106
## zs_status_ind_2 0.92 0.93 0.94 0.58 12 0.0052 0.0117
## med.r
## zs_empathy_group_2 0.57
## zs_empathy_group_1 0.57
## zs_empathy_ind_1 0.58
## zs_empathy_ind_2 0.56
## zs_jobs_group 0.59
## zs_jobs_ind 0.59
## zs_status_group_1 0.57
## zs_respect_group_1 0.57
## zs_respect_ind_2 0.57
## zs_status_ind_2 0.57
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## zs_empathy_group_2 499 0.81 0.81 0.79 0.76 2.9 1.7
## zs_empathy_group_1 499 0.82 0.82 0.80 0.77 2.7 1.5
## zs_empathy_ind_1 499 0.75 0.75 0.72 0.69 2.9 1.6
## zs_empathy_ind_2 499 0.85 0.85 0.85 0.81 2.6 1.5
## zs_jobs_group 499 0.73 0.72 0.68 0.65 3.6 1.7
## zs_jobs_ind 499 0.67 0.66 0.61 0.59 3.2 1.6
## zs_status_group_1 499 0.80 0.80 0.78 0.75 3.0 1.5
## zs_respect_group_1 499 0.84 0.85 0.84 0.80 2.5 1.4
## zs_respect_ind_2 499 0.82 0.83 0.83 0.78 2.3 1.3
## zs_status_ind_2 499 0.81 0.81 0.80 0.76 2.7 1.5
##
## Non missing response frequency for each item
## 1 2 3 4 5 6 7 miss
## zs_empathy_group_2 0.21 0.31 0.15 0.09 0.15 0.08 0.01 0
## zs_empathy_group_1 0.22 0.35 0.15 0.09 0.12 0.06 0.01 0
## zs_empathy_ind_1 0.21 0.30 0.19 0.07 0.15 0.06 0.02 0
## zs_empathy_ind_2 0.24 0.37 0.14 0.07 0.12 0.05 0.01 0
## zs_jobs_group 0.13 0.19 0.16 0.13 0.22 0.14 0.02 0
## zs_jobs_ind 0.15 0.28 0.20 0.12 0.15 0.08 0.02 0
## zs_status_group_1 0.16 0.30 0.21 0.12 0.14 0.05 0.01 0
## zs_respect_group_1 0.22 0.39 0.19 0.06 0.08 0.03 0.01 0
## zs_respect_ind_2 0.26 0.42 0.15 0.07 0.06 0.03 0.00 0
## zs_status_ind_2 0.20 0.38 0.18 0.08 0.12 0.04 0.01 0zs_means <- select(s6, zsm_mean, starts_with("zs_" ) & contains("mean") )
colnames(zs_means)## [1] "zsm_mean" "zs_empathy_mean" "zs_jobs_mean" "zs_status_mean"
## [5] "zs_respect_mean"# Zero-Order Correlations between Zero-sum mindset and specific zero-sum beliefs
apaTables::apa.cor.table(zs_means)##
##
## Means, standard deviations, and correlations with confidence intervals
##
##
## Variable M SD 1 2 3 4
## 1. zsm_mean 2.67 1.02
##
## 2. zs_empathy_mean 2.80 1.41 .61**
## [.55, .66]
##
## 3. zs_jobs_mean 3.39 1.50 .48** .58**
## [.41, .54] [.52, .63]
##
## 4. zs_status_mean 2.83 1.37 .63** .69** .62**
## [.57, .68] [.65, .74] [.57, .67]
##
## 5. zs_respect_mean 2.43 1.27 .61** .72** .57** .80**
## [.55, .66] [.68, .76] [.51, .63] [.77, .83]
##
##
## Note. M and SD are used to represent mean and standard deviation, respectively.
## Values in square brackets indicate the 95% confidence interval.
## The confidence interval is a plausible range of population correlations
## that could have caused the sample correlation (Cumming, 2014).
## * indicates p < .05. ** indicates p < .01.
## Domains = American Society, Government, Job Market, Politics, Healthcare, Education, Innovation, Natural Resources, Happiness, Relationships
s13$participant_id <- 1:nrow(s13)
zs_means <- select(s13, starts_with("zsb_" ) & !contains("econ"), participant_id)
zs_means <- filter(zs_means, complete.cases(zs_means))
# Reshape the data using pivot_longer()
reshaped_data <- zs_means %>%
pivot_longer(cols = starts_with("zsb_"),
names_to = "belief_domain",
values_to = "score")
# Print the reshaped data
print(reshaped_data)## # A tibble: 21,600 × 3
## participant_id belief_domain score
## <int> <chr> <dbl>
## 1 1 zsb_american_society_1 3
## 2 1 zsb_happiness_2 3
## 3 1 zsb_government_3 3
## 4 1 zsb_politics_4 3
## 5 1 zsb_healthcare_5 3
## 6 1 zsb_innovation_6 3
## 7 1 zsb_nat_resources_7 3
## 8 1 zsb_relationships_8 3
## 9 1 zsb_job_market_9 3
## 10 1 zsb_education_10 3
## # ℹ 21,590 more rows# Load the necessary package
library(ez)
# Perform repeated measures ANOVA using ezANOVA()
anova_result <- ezANOVA(data = reshaped_data, dv = score,
wid = participant_id, within = belief_domain, detailed = TRUE)
# Print the ANOVA table
print(anova_result)## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05 ges
## 1 (Intercept) 1 2159 154016.28 20471.32 16243.2701 0 * 0.81711747
## 2 belief_domain 9 19431 2096.68 13999.72 323.3445 0 * 0.05733692
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 2 belief_domain 0.4955362 1.231432e-288 *
##
## $`Sphericity Corrections`
## Effect GGe p[GG] p[GG]<.05 HFe p[HF] p[HF]<.05
## 2 belief_domain 0.8315415 0 * 0.8347172 0 *# Perform repeated measures ANOVA using ezANOVA()
anova_result <- ezANOVA(data = reshaped_data, dv = score,
wid = participant_id, within = belief_domain, detailed = TRUE)
# Print the ANOVA table
print(anova_result)## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05 ges
## 1 (Intercept) 1 2159 154016.28 20471.32 16243.2701 0 * 0.81711747
## 2 belief_domain 9 19431 2096.68 13999.72 323.3445 0 * 0.05733692
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 2 belief_domain 0.4955362 1.231432e-288 *
##
## $`Sphericity Corrections`
## Effect GGe p[GG] p[GG]<.05 HFe p[HF] p[HF]<.05
## 2 belief_domain 0.8315415 0 * 0.8347172 0 *# The corrected p-values obtained from these corrections are both less than the chosen significance level (p < 0.05), indicating a significant effect of belief_domain on the scores even after accounting for the violation of sphericity.
# The results suggest that there are significant differences in scores across the belief domains within participants, regardless of the specific correction method used.Here we create a composite of
# As composite -- describing variance explained
domain_specific_zs_beliefs_df <- select(s13, starts_with("zsb") & !contains("econ"))
s13$domain_specific_zsbeliefs_mean <- rowMeans(domain_specific_zs_beliefs_df)
psych::alpha(domain_specific_zs_beliefs_df)##
## Reliability analysis
## Call: psych::alpha(x = domain_specific_zs_beliefs_df)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.92 0.92 0.92 0.55 12 0.0024 2.7 0.97 0.53
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.92 0.92 0.93
## Duhachek 0.92 0.92 0.93
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se
## zsb_american_society_1 0.91 0.91 0.91 0.54 10 0.0028
## zsb_happiness_2 0.91 0.91 0.91 0.54 11 0.0028
## zsb_government_3 0.92 0.92 0.92 0.57 12 0.0025
## zsb_politics_4 0.92 0.92 0.92 0.57 12 0.0025
## zsb_healthcare_5 0.91 0.91 0.91 0.54 10 0.0028
## zsb_innovation_6 0.91 0.91 0.91 0.54 10 0.0028
## zsb_nat_resources_7 0.92 0.92 0.92 0.57 12 0.0025
## zsb_relationships_8 0.91 0.91 0.91 0.54 11 0.0028
## zsb_job_market_9 0.91 0.91 0.91 0.54 11 0.0027
## zsb_education_10 0.91 0.91 0.91 0.54 10 0.0028
## var.r med.r
## zsb_american_society_1 0.0118 0.50
## zsb_happiness_2 0.0090 0.50
## zsb_government_3 0.0099 0.61
## zsb_politics_4 0.0102 0.61
## zsb_healthcare_5 0.0114 0.50
## zsb_innovation_6 0.0101 0.50
## zsb_nat_resources_7 0.0107 0.61
## zsb_relationships_8 0.0089 0.50
## zsb_job_market_9 0.0120 0.50
## zsb_education_10 0.0096 0.50
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## zsb_american_society_1 2160 0.82 0.82 0.79 0.77 2.6 1.3
## zsb_happiness_2 2160 0.81 0.81 0.80 0.76 2.3 1.3
## zsb_government_3 2160 0.66 0.66 0.61 0.58 3.1 1.2
## zsb_politics_4 2160 0.66 0.67 0.61 0.58 3.2 1.2
## zsb_healthcare_5 2160 0.82 0.82 0.80 0.77 2.6 1.3
## zsb_innovation_6 2160 0.82 0.82 0.80 0.77 2.5 1.2
## zsb_nat_resources_7 2160 0.67 0.67 0.62 0.59 3.0 1.2
## zsb_relationships_8 2160 0.81 0.81 0.80 0.76 2.3 1.3
## zsb_job_market_9 2160 0.79 0.79 0.76 0.73 2.7 1.3
## zsb_education_10 2160 0.83 0.82 0.81 0.78 2.4 1.3
##
## Non missing response frequency for each item
## 1 2 3 4 5 miss
## zsb_american_society_1 0.23 0.28 0.21 0.18 0.10 0
## zsb_happiness_2 0.35 0.26 0.18 0.13 0.08 0
## zsb_government_3 0.12 0.21 0.23 0.30 0.14 0
## zsb_politics_4 0.11 0.21 0.23 0.30 0.15 0
## zsb_healthcare_5 0.26 0.28 0.20 0.17 0.10 0
## zsb_innovation_6 0.25 0.30 0.21 0.17 0.08 0
## zsb_nat_resources_7 0.14 0.22 0.24 0.27 0.12 0
## zsb_relationships_8 0.34 0.28 0.19 0.11 0.08 0
## zsb_job_market_9 0.21 0.29 0.21 0.20 0.09 0
## zsb_education_10 0.34 0.27 0.18 0.14 0.08 0psych::omega(domain_specific_zs_beliefs_df, nfactors = 1)## Omega
## Call: omegah(m = m, nfactors = nfactors, fm = fm, key = key, flip = flip,
## digits = digits, title = title, sl = sl, labels = labels,
## plot = plot, n.obs = n.obs, rotate = rotate, Phi = Phi, option = option,
## covar = covar)
## Alpha: 0.92
## G.6: 0.92
## Omega Hierarchical: 0.92
## Omega H asymptotic: 1
## Omega Total 0.93
##
## Schmid Leiman Factor loadings greater than 0.2
## g F1* h2 u2 p2
## zsb_american_society_1 0.80 0.64 0.36 1
## zsb_happiness_2 0.80 0.64 0.36 1
## zsb_government_3 0.59 0.35 0.65 1
## zsb_politics_4 0.60 0.36 0.64 1
## zsb_healthcare_5 0.80 0.64 0.36 1
## zsb_innovation_6 0.81 0.66 0.34 1
## zsb_nat_resources_7 0.61 0.38 0.62 1
## zsb_relationships_8 0.80 0.64 0.36 1
## zsb_job_market_9 0.77 0.59 0.41 1
## zsb_education_10 0.82 0.67 0.33 1
##
## With Sums of squares of:
## g F1*
## 5.6 0.0
##
## general/max 1.002054e+17 max/min = 1
## mean percent general = 1 with sd = 0 and cv of 0
## Explained Common Variance of the general factor = 1
##
## The degrees of freedom are 35 and the fit is 0.35
## The number of observations was 2160 with Chi Square = 752.13 with prob < 1.8e-135
## The root mean square of the residuals is 0.05
## The df corrected root mean square of the residuals is 0.06
## RMSEA index = 0.097 and the 10 % confidence intervals are 0.091 0.104
## BIC = 483.41
##
## Compare this with the adequacy of just a general factor and no group factors
## The degrees of freedom for just the general factor are 35 and the fit is 0.35
## The number of observations was 2160 with Chi Square = 752.13 with prob < 1.8e-135
## The root mean square of the residuals is 0.05
## The df corrected root mean square of the residuals is 0.06
##
## RMSEA index = 0.097 and the 10 % confidence intervals are 0.091 0.104
## BIC = 483.41
##
## Measures of factor score adequacy
## g F1*
## Correlation of scores with factors 0.97 0
## Multiple R square of scores with factors 0.93 0
## Minimum correlation of factor score estimates 0.87 -1
##
## Total, General and Subset omega for each subset
## g F1*
## Omega total for total scores and subscales 0.93 0.92
## Omega general for total scores and subscales 0.92 0.92
## Omega group for total scores and subscales 0.00 0.00# Model Comparison
#Filtering out missing values for model comparison
s13_complete <- s13 %>%
filter(complete.cases(select(., sex, income, education, age, political_lean, race, zsm_mean, A, O, C, N, E, domain_specific_zsbeliefs_mean)))
nrow(s13)## [1] 2160nrow(s13_complete)## [1] 2160s13_complete$sex <- if_else(s13_complete$sex == 1, "Male", "Female")
s13_complete$sex <- as.factor(s13_complete$sex)
levels(s13_complete$sex)## [1] "Female" "Male"# Simple Model
test_1a <- lm(scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean), data = s13_complete)
summary(test_1a)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean),
## data = s13_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9839 -0.4917 -0.0809 0.4725 3.3908
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.404e-14 1.645e-02 0.00 1
## scale(zsm_mean) 6.448e-01 1.645e-02 39.19 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7645 on 2158 degrees of freedom
## Multiple R-squared: 0.4158, Adjusted R-squared: 0.4155
## F-statistic: 1536 on 1 and 2158 DF, p-value: < 2.2e-16summary(test_1a)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean),
## data = s13_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9839 -0.4917 -0.0809 0.4725 3.3908
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.404e-14 1.645e-02 0.00 1
## scale(zsm_mean) 6.448e-01 1.645e-02 39.19 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7645 on 2158 degrees of freedom
## Multiple R-squared: 0.4158, Adjusted R-squared: 0.4155
## F-statistic: 1536 on 1 and 2158 DF, p-value: < 2.2e-16apa.reg.table(test_1a)##
##
## Regression results using scale(domain_specific_zsbeliefs_mean) as the criterion
##
##
## Predictor b b_95%_CI beta beta_95%_CI sr2 sr2_95%_CI r
## (Intercept) 0.00 [-0.03, 0.03]
## scale(zsm_mean) 0.64** [0.61, 0.68] 0.64 [0.61, 0.68] .42 [.39, .44] .64**
##
##
##
## Fit
##
##
## R2 = .416**
## 95% CI[.39,.44]
##
##
## Note. A significant b-weight indicates the beta-weight and semi-partial correlation are also significant.
## b represents unstandardized regression weights. beta indicates the standardized regression weights.
## sr2 represents the semi-partial correlation squared. r represents the zero-order correlation.
## Square brackets are used to enclose the lower and upper limits of a confidence interval.
## * indicates p < .05. ** indicates p < .01.
## # Simple Model - Weighted Regression (For Nationally Representative Sample)
test_1b <- lm(scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean), weights = weight, data = s13_complete)
summary(test_1b)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean),
## data = s13_complete, weights = weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -5.3869 -0.3782 -0.0562 0.3432 6.0149
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.00444 0.01681 -0.264 0.792
## scale(zsm_mean) 0.64087 0.01707 37.538 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7808 on 2158 degrees of freedom
## Multiple R-squared: 0.395, Adjusted R-squared: 0.3948
## F-statistic: 1409 on 1 and 2158 DF, p-value: < 2.2e-16# Full Model
test_2a <- lm(scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean) + scale(A) + scale(O) + scale(C) + scale(E) + scale(N) + scale(income) + scale(age) + scale(education) + as.factor(race) + as.factor(sex) + as.factor(political_lean), data = s13_complete)
summary(test_2a)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean) +
## scale(A) + scale(O) + scale(C) + scale(E) + scale(N) + scale(income) +
## scale(age) + scale(education) + as.factor(race) + as.factor(sex) +
## as.factor(political_lean), data = s13_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9223 -0.4700 -0.0397 0.4340 3.3803
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.12366 0.04720 2.620 0.00886 **
## scale(zsm_mean) 0.56548 0.01792 31.564 < 2e-16 ***
## scale(A) 0.03521 0.01769 1.990 0.04671 *
## scale(O) -0.02212 0.01772 -1.248 0.21208
## scale(C) -0.04843 0.01966 -2.463 0.01385 *
## scale(E) 0.08882 0.01777 4.998 6.26e-07 ***
## scale(N) 0.09877 0.01992 4.959 7.66e-07 ***
## scale(income) 0.02720 0.01949 1.395 0.16302
## scale(age) -0.11933 0.01833 -6.510 9.33e-11 ***
## scale(education) 0.02508 0.01910 1.313 0.18916
## as.factor(race)2 0.08551 0.05835 1.465 0.14297
## as.factor(race)3 0.08960 0.07376 1.215 0.22460
## as.factor(race)4 -0.12811 0.09972 -1.285 0.19903
## as.factor(race)5 -0.20905 0.17062 -1.225 0.22061
## as.factor(race)6 -0.18468 0.26243 -0.704 0.48167
## as.factor(race)7 -0.29682 0.36904 -0.804 0.42131
## as.factor(race)8 0.10050 0.12306 0.817 0.41420
## as.factor(race)9 0.21517 0.27958 0.770 0.44162
## as.factor(sex)Male 0.02891 0.03432 0.842 0.39961
## as.factor(political_lean)2 -0.18273 0.05831 -3.134 0.00175 **
## as.factor(political_lean)3 -0.14795 0.05040 -2.936 0.00336 **
## as.factor(political_lean)4 -0.20199 0.05944 -3.399 0.00069 ***
## as.factor(political_lean)5 -0.17049 0.06290 -2.710 0.00678 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7349 on 2137 degrees of freedom
## Multiple R-squared: 0.4654, Adjusted R-squared: 0.4599
## F-statistic: 84.58 on 22 and 2137 DF, p-value: < 2.2e-16# Full Model Weighted Regression
test_2b <- lm(scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean) + scale(A) + scale(O) + scale(C) + scale(E) + scale(N) + scale(income) + scale(age) + scale(education) + as.factor(sex) + as.factor(race),weights = weight, data = s13_complete)
summary(test_2b)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean) +
## scale(A) + scale(O) + scale(C) + scale(E) + scale(N) + scale(income) +
## scale(age) + scale(education) + as.factor(sex) + as.factor(race),
## data = s13_complete, weights = weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -4.9575 -0.3572 -0.0389 0.3266 5.1383
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.02312 0.02640 -0.876 0.3812
## scale(zsm_mean) 0.54481 0.01836 29.667 < 2e-16 ***
## scale(A) 0.03426 0.01779 1.926 0.0542 .
## scale(O) -0.01788 0.01770 -1.010 0.3125
## scale(C) -0.04943 0.02055 -2.406 0.0162 *
## scale(E) 0.10250 0.01869 5.484 4.64e-08 ***
## scale(N) 0.12658 0.02044 6.192 7.11e-10 ***
## scale(income) 0.03961 0.01750 2.263 0.0237 *
## scale(age) -0.12899 0.01874 -6.885 7.58e-12 ***
## scale(education) 0.04576 0.02046 2.236 0.0254 *
## as.factor(sex)Male 0.02402 0.03463 0.694 0.4880
## as.factor(race)2 0.12334 0.05377 2.294 0.0219 *
## as.factor(race)3 0.32548 0.06856 4.747 2.20e-06 ***
## as.factor(race)4 -0.19826 0.10753 -1.844 0.0654 .
## as.factor(race)5 -0.13217 0.19622 -0.674 0.5006
## as.factor(race)6 -0.20162 0.24819 -0.812 0.4167
## as.factor(race)7 -0.69065 0.42956 -1.608 0.1080
## as.factor(race)8 0.07289 0.12212 0.597 0.5507
## as.factor(race)9 0.49340 0.38406 1.285 0.1990
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7424 on 2141 degrees of freedom
## Multiple R-squared: 0.4575, Adjusted R-squared: 0.4529
## F-statistic: 100.3 on 18 and 2141 DF, p-value: < 2.2e-16#apa.reg.table(test_2b, filename = "Sample N - Domain-Specific Zero-Sum Beliefs.doc")
# Comparing with BFI only
test_2c <- lm(scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean) + scale(A) + scale(O) + scale(C) + scale(E) + scale(N), data = s13_complete)
summary(test_2c)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean) +
## scale(A) + scale(O) + scale(C) + scale(E) + scale(N), data = s13_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8486 -0.4805 -0.0628 0.4510 3.1649
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.451e-14 1.608e-02 0.000 1.000000
## scale(zsm_mean) 6.015e-01 1.745e-02 34.478 < 2e-16 ***
## scale(A) 3.269e-02 1.783e-02 1.833 0.066889 .
## scale(O) 1.214e-02 1.744e-02 0.696 0.486553
## scale(C) -6.821e-02 1.971e-02 -3.460 0.000551 ***
## scale(E) 1.190e-01 1.755e-02 6.783 1.52e-11 ***
## scale(N) 1.185e-01 1.911e-02 6.198 6.84e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7475 on 2153 degrees of freedom
## Multiple R-squared: 0.4428, Adjusted R-squared: 0.4413
## F-statistic: 285.2 on 6 and 2153 DF, p-value: < 2.2e-16test_2d <- lm(scale(domain_specific_zsbeliefs_mean) ~ scale(A) + scale(O) + scale(C) + scale(E) + scale(N), data = s13_complete)
summary(test_2d)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(A) +
## scale(O) + scale(C) + scale(E) + scale(N), data = s13_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5314 -0.6741 -0.0659 0.5815 3.2327
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.109e-15 2.003e-02 0.000 1.0000
## scale(A) -5.400e-02 2.199e-02 -2.456 0.0141 *
## scale(O) -5.500e-02 2.159e-02 -2.548 0.0109 *
## scale(C) -1.950e-01 2.412e-02 -8.085 1.03e-15 ***
## scale(E) 2.391e-01 2.142e-02 11.164 < 2e-16 ***
## scale(N) 1.697e-01 2.373e-02 7.151 1.18e-12 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.931 on 2154 degrees of freedom
## Multiple R-squared: 0.1352, Adjusted R-squared: 0.1332
## F-statistic: 67.33 on 5 and 2154 DF, p-value: < 2.2e-16apa.reg.table(test_2d, test_2c)##
##
## Regression results using scale(domain_specific_zsbeliefs_mean) as the criterion
##
##
## Predictor b b_95%_CI beta beta_95%_CI sr2 sr2_95%_CI
## (Intercept) 0.00 [-0.04, 0.04]
## scale(A) -0.05* [-0.10, -0.01] -0.05 [-0.10, -0.01] .00 [-.00, .01]
## scale(O) -0.05* [-0.10, -0.01] -0.05 [-0.10, -0.01] .00 [-.00, .01]
## scale(C) -0.20** [-0.24, -0.15] -0.20 [-0.24, -0.15] .03 [.01, .04]
## scale(E) 0.24** [0.20, 0.28] 0.24 [0.20, 0.28] .05 [.03, .07]
## scale(N) 0.17** [0.12, 0.22] 0.17 [0.12, 0.22] .02 [.01, .03]
##
##
##
## (Intercept) 0.00 [-0.03, 0.03]
## scale(zsm_mean) 0.60** [0.57, 0.64] 0.60 [0.57, 0.64] .31 [.28, .34]
## scale(A) 0.03 [-0.00, 0.07] 0.03 [-0.00, 0.07] .00 [-.00, .00]
## scale(O) 0.01 [-0.02, 0.05] 0.01 [-0.02, 0.05] .00 [-.00, .00]
## scale(C) -0.07** [-0.11, -0.03] -0.07 [-0.11, -0.03] .00 [-.00, .01]
## scale(E) 0.12** [0.08, 0.15] 0.12 [0.08, 0.15] .01 [.01, .02]
## scale(N) 0.12** [0.08, 0.16] 0.12 [0.08, 0.16] .01 [.00, .02]
##
##
##
## r Fit Difference
##
## -.16**
## -.07**
## -.26**
## .14**
## .22**
## R2 = .135**
## 95% CI[.11,.16]
##
##
## .64**
## -.16**
## -.07**
## -.26**
## .14**
## .22**
## R2 = .443** Delta R2 = .308**
## 95% CI[.41,.47] 95% CI[.28, .34]
##
##
## Note. A significant b-weight indicates the beta-weight and semi-partial correlation are also significant.
## b represents unstandardized regression weights. beta indicates the standardized regression weights.
## sr2 represents the semi-partial correlation squared. r represents the zero-order correlation.
## Square brackets are used to enclose the lower and upper limits of a confidence interval.
## * indicates p < .05. ** indicates p < .01.
## test_2d <- lm(scale(zsm_mean) ~ scale(A) + scale(O) + scale(C) + scale(E) + scale(N), data = s13_complete)
summary(test_2d)##
## Call:
## lm(formula = scale(zsm_mean) ~ scale(A) + scale(O) + scale(C) +
## scale(E) + scale(N), data = s13_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.2471 -0.6709 -0.0514 0.5935 3.5101
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.396e-14 1.986e-02 0.000 1e+00
## scale(A) -1.441e-01 2.180e-02 -6.611 4.80e-11 ***
## scale(O) -1.116e-01 2.141e-02 -5.214 2.02e-07 ***
## scale(C) -2.108e-01 2.392e-02 -8.814 < 2e-16 ***
## scale(E) 1.997e-01 2.124e-02 9.402 < 2e-16 ***
## scale(N) 8.521e-02 2.353e-02 3.621 3e-04 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9232 on 2154 degrees of freedom
## Multiple R-squared: 0.1498, Adjusted R-squared: 0.1478
## F-statistic: 75.88 on 5 and 2154 DF, p-value: < 2.2e-16levels(s13_complete$sex)## [1] "Female" "Male"# Simple Model - Weighted Regression (For Nationally Representative Sample)
test_1b <- lm(scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean), weights = weight, data = s13_complete)
summary(test_1b)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ scale(zsm_mean),
## data = s13_complete, weights = weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -5.3869 -0.3782 -0.0562 0.3432 6.0149
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.00444 0.01681 -0.264 0.792
## scale(zsm_mean) 0.64087 0.01707 37.538 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7808 on 2158 degrees of freedom
## Multiple R-squared: 0.395, Adjusted R-squared: 0.3948
## F-statistic: 1409 on 1 and 2158 DF, p-value: < 2.2e-16# Comparing ZSM and Econ Domain
test_3a <- lm(scale(domain_specific_zsbeliefs_mean) ~ econ_zsb_mean, weights = weight, data = s13_complete)
summary(test_3a)##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ econ_zsb_mean,
## data = s13_complete, weights = weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -5.0705 -0.4314 -0.0315 0.3980 7.7945
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.45579 0.04888 -29.78 <2e-16 ***
## econ_zsb_mean 0.36252 0.01154 31.40 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8317 on 2158 degrees of freedom
## Multiple R-squared: 0.3136, Adjusted R-squared: 0.3133
## F-statistic: 986 on 1 and 2158 DF, p-value: < 2.2e-16test_3b <- lm(scale(domain_specific_zsbeliefs_mean) ~ zsm_mean + econ_zsb_mean, weights = weight, data = s13_complete)
summary(test_3b) ##
## Call:
## lm(formula = scale(domain_specific_zsbeliefs_mean) ~ zsm_mean +
## econ_zsb_mean, data = s13_complete, weights = weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -5.9151 -0.3381 -0.0359 0.2822 7.2114
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2.00976 0.04833 -41.58 <2e-16 ***
## zsm_mean 0.39981 0.01592 25.11 <2e-16 ***
## econ_zsb_mean 0.20632 0.01191 17.32 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7318 on 2157 degrees of freedom
## Multiple R-squared: 0.4689, Adjusted R-squared: 0.4684
## F-statistic: 952.3 on 2 and 2157 DF, p-value: < 2.2e-16apa.reg.table(test_3b)##
##
## Regression results using scale(domain_specific_zsbeliefs_mean) as the criterion
##
##
## Predictor b b_95%_CI sr2 sr2_95%_CI r Fit
## (Intercept) -2.01** [-2.10, -1.91]
## zsm_mean 0.40** [0.37, 0.43] .16 [.13, .18] .64**
## econ_zsb_mean 0.21** [0.18, 0.23] .07 [.06, .09] .57**
## R2 = .469**
## 95% CI[.44,.49]
##
##
## Note. A significant b-weight indicates the semi-partial correlation is also significant.
## b represents unstandardized regression weights. sr2 represents the semi-partial correlation squared.
## r represents the zero-order correlation.
## Square brackets are used to enclose the lower and upper limits of a confidence interval.
## * indicates p < .05. ** indicates p < .01.
## Compared to the simple model, which explains 40% of the variance in these broader zero-sum beliefs, adding economic zero-sum beliefs explains only an additional 7% of variance. When examining their unique variance
# Compute VIF for each predictor
vif_values <- car::vif(test_3b)
# Check if any VIF values are greater than 10
high_vif <- which(vif_values > 10)
# Generate a message based on the results
if(length(high_vif) == 0) {
message <- "Based on the Variance Inflation Factor (VIF) values, there is no indication of problematic multicollinearity in the model."
} else {
problematic_vars <- names(vif_values)[high_vif]
message <- paste("Based on the Variance Inflation Factor (VIF) values, there is an indication of problematic multicollinearity for the following variables:",
paste(problematic_vars, collapse = ", "), ". Consider examining the relationships among these variables or potentially revising the model.")
}
# Print the message
print(message)## [1] "Based on the Variance Inflation Factor (VIF) values, there is no indication of problematic multicollinearity in the model."# Regression Tables
#table <-apaTables::apa.reg.table(test_1, test_2, filename = "Study4_H4a_reg_table_X.doc")A zero-sum mindset will predict specific zero-sum beliefs about different kinds of intragroup and intergroup relationships in the US,Pakistan and India(4b).
# Renaming and Scaling for Table Output
s3$Openness <- scale(s3$O_mean)
s3$Conscientiousness <- scale(s3$C_mean)
s3$Extraversion <- scale(s3$E_mean)
s3$Agreeableness <- scale(s3$A_mean)
s3$Neuroticism <- scale(s3$N_mean)
s3$`Need for Cognitive Closure` <- scale(s3$nfc_mean)
s3$`Zero-Sum Mindset` <- scale(s3$zsm_mean)
s3$Education <- scale(s3$education)
s3$Income <- scale(s3$income)
s3$Sex <- as.factor(s3$sex)
s3$Race <- as.factor(s3$race)
s3$`Political Orientation` <- scale(s3$political_orientatio)
s3$zs_beliefs_US_politics_mean <- scale(s3$zs_beliefs_US_politics_mean)
# Note: Missing age data at T1
s3_complete <- s3 %>%
filter(complete.cases(select(., `Zero-Sum Mindset`, Agreeableness, Openness, Conscientiousness, Extraversion, Neuroticism, `Need for Cognitive Closure`,`Political Orientation`, Sex, Race, Income, Education)))
nrow(s3)## [1] 509nrow(s3_complete)## [1] 496model_1 <- lm(zs_beliefs_US_politics_mean ~ `Zero-Sum Mindset`, data = s3_complete)
model_2 <- lm(zs_beliefs_US_politics_mean ~ `Zero-Sum Mindset`+ Agreeableness+ Openness+ Conscientiousness+ Extraversion+ Neuroticism+ `Need for Cognitive Closure`+ Race + Sex + Income + Education + `Political Orientation`, data = s3_complete)
#apa.reg.table(model_1, model_2, filename = "Study4_H4b_US_2.doc")
summary(model_1)##
## Call:
## lm(formula = zs_beliefs_US_politics_mean ~ `Zero-Sum Mindset`,
## data = s3_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.75073 -0.62566 0.00097 0.59485 2.49728
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.004922 0.039215 -0.126 0.9
## `Zero-Sum Mindset` 0.482621 0.039561 12.199 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8733 on 494 degrees of freedom
## Multiple R-squared: 0.2315, Adjusted R-squared: 0.23
## F-statistic: 148.8 on 1 and 494 DF, p-value: < 2.2e-16summary(model_2)##
## Call:
## lm(formula = zs_beliefs_US_politics_mean ~ `Zero-Sum Mindset` +
## Agreeableness + Openness + Conscientiousness + Extraversion +
## Neuroticism + `Need for Cognitive Closure` + Race + Sex +
## Income + Education + `Political Orientation`, data = s3_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.48897 -0.61813 -0.00677 0.55558 2.43587
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.09688 0.12190 0.795 0.427
## `Zero-Sum Mindset` 0.37465 0.04428 8.460 3.29e-16 ***
## Agreeableness 0.02924 0.04033 0.725 0.469
## Openness -0.05742 0.04377 -1.312 0.190
## Conscientiousness 0.04059 0.04662 0.871 0.384
## Extraversion 0.04613 0.04507 1.023 0.307
## Neuroticism -0.01783 0.04755 -0.375 0.708
## `Need for Cognitive Closure` 0.18824 0.04520 4.165 3.70e-05 ***
## RaceEast Asian -0.34326 0.20765 -1.653 0.099 .
## RaceIndigenous 0.11937 0.61806 0.193 0.847
## RaceLatinx -0.05395 0.20742 -0.260 0.795
## RaceMiddle Eastern -0.85824 0.86695 -0.990 0.323
## RaceMixed -0.31608 0.21751 -1.453 0.147
## RaceOther -0.32713 0.51048 -0.641 0.522
## RaceWhite -0.17135 0.12925 -1.326 0.186
## Sex2 0.10944 0.08328 1.314 0.189
## Income -0.01193 0.04367 -0.273 0.785
## Education 0.06056 0.04391 1.379 0.168
## `Political Orientation` -0.04260 0.04205 -1.013 0.312
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8546 on 477 degrees of freedom
## Multiple R-squared: 0.2895, Adjusted R-squared: 0.2626
## F-statistic: 10.8 on 18 and 477 DF, p-value: < 2.2e-16anova(model_1, model_2)## Analysis of Variance Table
##
## Model 1: zs_beliefs_US_politics_mean ~ `Zero-Sum Mindset`
## Model 2: zs_beliefs_US_politics_mean ~ `Zero-Sum Mindset` + Agreeableness +
## Openness + Conscientiousness + Extraversion + Neuroticism +
## `Need for Cognitive Closure` + Race + Sex + Income + Education +
## `Political Orientation`
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 494 376.74
## 2 477 348.34 17 28.403 2.2878 0.00248 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1vif_values <- car::vif(model_2)
# Exclude degrees of freedom from the check
predictors <- names(vif_values)[-1]
vif_values <- vif_values[-1]
# Set the VIF threshold
vif_threshold <- 5
# Check if any predictors have a VIF greater than the threshold
high_vif_predictors <- predictors[vif_values > vif_threshold]
# Print the results
if (length(high_vif_predictors) > 0) {
message("Multicollinearity detected. Predictors with VIF > ", vif_threshold, ": ", paste(high_vif_predictors, collapse = ", "))
} else {
message("No significant multicollinearity detected.")
}## No significant multicollinearity detected.describe(s8$zs_beliefs_India_Pakistan)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 255 4.27 1.35 4.62 4.37 1.3 1 6.38 5.38 -0.59 -0.76 0.08# Renaming and Scaling for Table Output
s8$Openness <- scale(s8$O_mean)
s8$Conscientiousness <- scale(s8$C_mean)
s8$Extraversion <- scale(s8$E_mean)
s8$Agreeableness <- scale(s8$A_mean)
s8$Neuroticism <- scale(s8$N_mean)
s8$`Need for Cognitive Closure` <- scale(s8$nfc_mean)
s8$`Zero-Sum Mindset` <- scale(s8$zsm_mean)
s8$Age <- scale(s8$age)
s8$Education <- scale(s8$education)
s8$Income <- scale(s8$income)
s8$Sex <- as.factor(s8$sex)
s8_complete <- s8 %>%
filter(complete.cases(select(., `Zero-Sum Mindset`, Agreeableness, Openness, Conscientiousness, Extraversion, Neuroticism, `Need for Cognitive Closure`, Sex, Age, Income, Education)))
nrow(s8)## [1] 256nrow(s8_complete)## [1] 250model_1 <- lm(scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset`, data = s8_complete)
model_2 <- lm(scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset`+ Agreeableness+ Openness+ Conscientiousness+ Extraversion+ Neuroticism+ `Need for Cognitive Closure`+ Sex + Age + Income + Education, data = s8_complete)
summary(model_1)##
## Call:
## lm(formula = scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset`,
## data = s8_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.7838 -0.4008 0.1988 0.5103 2.7356
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.001489 0.051707 0.029 0.977
## `Zero-Sum Mindset` 0.575383 0.051561 11.159 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8176 on 248 degrees of freedom
## Multiple R-squared: 0.3343, Adjusted R-squared: 0.3316
## F-statistic: 124.5 on 1 and 248 DF, p-value: < 2.2e-16summary(model_2)##
## Call:
## lm(formula = scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset` +
## Agreeableness + Openness + Conscientiousness + Extraversion +
## Neuroticism + `Need for Cognitive Closure` + Sex + Age +
## Income + Education, data = s8_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4138 -0.3387 0.1512 0.4278 2.6954
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.04447 0.09671 0.460 0.6460
## `Zero-Sum Mindset` 0.30846 0.05824 5.297 2.68e-07 ***
## Agreeableness 0.11287 0.05593 2.018 0.0447 *
## Openness 0.05579 0.05981 0.933 0.3518
## Conscientiousness 0.12294 0.06897 1.783 0.0759 .
## Extraversion 0.10666 0.05639 1.891 0.0598 .
## Neuroticism 0.09216 0.06892 1.337 0.1824
## `Need for Cognitive Closure` 0.13573 0.05848 2.321 0.0211 *
## SexMale -0.05426 0.11127 -0.488 0.6263
## Age -0.02638 0.05415 -0.487 0.6266
## Income -0.10721 0.05401 -1.985 0.0483 *
## Education -0.04658 0.05157 -0.903 0.3673
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7267 on 238 degrees of freedom
## Multiple R-squared: 0.4952, Adjusted R-squared: 0.4719
## F-statistic: 21.22 on 11 and 238 DF, p-value: < 2.2e-16anova(model_1, model_2)## Analysis of Variance Table
##
## Model 1: scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset`
## Model 2: scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset` + Agreeableness +
## Openness + Conscientiousness + Extraversion + Neuroticism +
## `Need for Cognitive Closure` + Sex + Age + Income + Education
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 248 165.76
## 2 238 125.70 10 40.067 7.5863 1.731e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1#apa.reg.table(model_1, model_2, filename = "h4b_India.doc")
apa.reg.table(model_1, model_2)##
##
## Regression results using scale(zs_beliefs_India_Pakistan) as the criterion
##
##
## Predictor b b_95%_CI sr2 sr2_95%_CI
## (Intercept) 0.00 [-0.10, 0.10]
## `Zero-Sum Mindset` 0.58** [0.47, 0.68] .33 [.24, .42]
##
##
##
## (Intercept) 0.04 [-0.15, 0.23]
## `Zero-Sum Mindset` 0.31** [0.19, 0.42] .06 [.02, .10]
## Agreeableness 0.11* [0.00, 0.22] .01 [-.01, .03]
## Openness 0.06 [-0.06, 0.17] .00 [-.01, .01]
## Conscientiousness 0.12 [-0.01, 0.26] .01 [-.01, .02]
## Extraversion 0.11 [-0.00, 0.22] .01 [-.01, .02]
## Neuroticism 0.09 [-0.04, 0.23] .00 [-.01, .01]
## `Need for Cognitive Closure` 0.14* [0.02, 0.25] .01 [-.01, .03]
## SexMale -0.05 [-0.27, 0.16] .00 [-.00, .00]
## Age -0.03 [-0.13, 0.08] .00 [-.00, .00]
## Income -0.11* [-0.21, -0.00] .01 [-.01, .02]
## Education -0.05 [-0.15, 0.06] .00 [-.01, .01]
##
##
##
## Fit Difference
##
##
## R2 = .334**
## 95% CI[.24,.42]
##
##
##
##
##
##
##
##
##
##
##
##
##
## R2 = .495** Delta R2 = .161**
## 95% CI[.38,.55] 95% CI[.09, .23]
##
##
## Note. A significant b-weight indicates the semi-partial correlation is also significant.
## b represents unstandardized regression weights.
## sr2 represents the semi-partial correlation squared.
## Square brackets are used to enclose the lower and upper limits of a confidence interval.
## * indicates p < .05. ** indicates p < .01.
## ## Comparing with BFI only
model_1 <- lm(scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset`, data = s8_complete)
model_3 <- lm(scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset`+ Agreeableness+ Openness+ Conscientiousness+ Extraversion+ Neuroticism, data = s8_complete)
apa.reg.table(model_1, model_3)##
##
## Regression results using scale(zs_beliefs_India_Pakistan) as the criterion
##
##
## Predictor b b_95%_CI sr2 sr2_95%_CI Fit
## (Intercept) 0.00 [-0.10, 0.10]
## `Zero-Sum Mindset` 0.58** [0.47, 0.68] .33 [.24, .42]
## R2 = .334**
## 95% CI[.24,.42]
##
## (Intercept) 0.00 [-0.09, 0.10]
## `Zero-Sum Mindset` 0.37** [0.26, 0.47] .10 [.04, .15]
## Agreeableness 0.14* [0.03, 0.25] .01 [-.01, .03]
## Openness 0.06 [-0.06, 0.17] .00 [-.01, .01]
## Conscientiousness 0.17** [0.05, 0.29] .02 [-.01, .04]
## Extraversion 0.13* [0.02, 0.24] .01 [-.01, .03]
## Neuroticism 0.14* [0.02, 0.27] .01 [-.01, .03]
## R2 = .472**
## 95% CI[.37,.53]
##
## Difference
##
##
##
##
##
##
##
##
##
##
##
##
## Delta R2 = .137**
## 95% CI[.07, .20]
##
##
## Note. A significant b-weight indicates the semi-partial correlation is also significant.
## b represents unstandardized regression weights.
## sr2 represents the semi-partial correlation squared.
## Square brackets are used to enclose the lower and upper limits of a confidence interval.
## * indicates p < .05. ** indicates p < .01.
## summary(model_3)##
## Call:
## lm(formula = scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset` +
## Agreeableness + Openness + Conscientiousness + Extraversion +
## Neuroticism, data = s8_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.3196 -0.3385 0.1446 0.4304 2.8044
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.004631 0.046539 0.100 0.92082
## `Zero-Sum Mindset` 0.365326 0.055194 6.619 2.29e-10 ***
## Agreeableness 0.137359 0.055529 2.474 0.01406 *
## Openness 0.055076 0.060116 0.916 0.36049
## Conscientiousness 0.170804 0.061271 2.788 0.00573 **
## Extraversion 0.134716 0.055774 2.415 0.01646 *
## Neuroticism 0.144113 0.063748 2.261 0.02467 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7357 on 243 degrees of freedom
## Multiple R-squared: 0.4718, Adjusted R-squared: 0.4587
## F-statistic: 36.17 on 6 and 243 DF, p-value: < 2.2e-16model_3 <- lm(scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset`+ Agreeableness+ Openness+ Conscientiousness+ Extraversion+ Neuroticism, data = s8_complete)
model_3 <- lm(scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset`+ Agreeableness+ Openness+ Conscientiousness+ Extraversion+ Neuroticism + acq_index, data = s8_complete)
summary(model_3)##
## Call:
## lm(formula = scale(zs_beliefs_India_Pakistan) ~ `Zero-Sum Mindset` +
## Agreeableness + Openness + Conscientiousness + Extraversion +
## Neuroticism + acq_index, data = s8_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.18262 -0.32695 0.09566 0.44775 2.38515
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.416660 0.320031 -4.427 1.45e-05 ***
## `Zero-Sum Mindset` 0.310254 0.054543 5.688 3.69e-08 ***
## Agreeableness 0.112335 0.053756 2.090 0.0377 *
## Openness 0.002382 0.059063 0.040 0.9679
## Conscientiousness 0.142513 0.059331 2.402 0.0171 *
## Extraversion 0.073166 0.055427 1.320 0.1881
## Neuroticism 0.102119 0.062090 1.645 0.1013
## acq_index 0.400750 0.089348 4.485 1.13e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7084 on 242 degrees of freedom
## Multiple R-squared: 0.5123, Adjusted R-squared: 0.4982
## F-statistic: 36.31 on 7 and 242 DF, p-value: < 2.2e-16# Compute VIF for each predictor
vif_values <- car::vif(model_2)
if (any(vif_values > 5)) {
# Print a message indicating predictors with high VIF
high_vif_predictors <- names(vif_values[vif_values > 5])
message("Multicollinearity detected. Predictors with VIF > 5: ", paste(high_vif_predictors, collapse = ", "))
} else {
message("No significant multicollinearity detected.")
}## No significant multicollinearity detected.describe(s9$zs_beliefs_India_Pakistan_mean)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 649 4.06 1.23 4 4.05 1.24 1 7 6 0.08 -0.54 0.05# Renaming and Scaling for Table Output
s9$Openness <- scale(s9$O_mean)
s9$Conscientiousness <- scale(s9$C_mean)
s9$Extraversion <- scale(s9$E_mean)
s9$Agreeableness <- scale(s9$A_mean)
s9$Neuroticism <- scale(s9$N_mean)
s9$`Need for Cognitive Closure` <- scale(s9$nfc_mean)
s9$`Zero-Sum Mindset` <- scale(s9$zsm_mean)
s9$Age <- scale(s9$age)
s9$Education <- scale(s9$education)
s9$Income <- scale(s9$income)
s9$Sex <- as.factor(s9$sex)
s9_complete <- s9 %>%
filter(complete.cases(select(., `Zero-Sum Mindset`, Agreeableness, Openness, Conscientiousness, Extraversion, Neuroticism, `Need for Cognitive Closure`, Sex, Age, Income, Education)))
nrow(s9)## [1] 649nrow(s9_complete)## [1] 647model_1 <- lm(scale(zs_beliefs_India_Pakistan_mean) ~ `Zero-Sum Mindset`, data = s9_complete)
summary(model_1)##
## Call:
## lm(formula = scale(zs_beliefs_India_Pakistan_mean) ~ `Zero-Sum Mindset`,
## data = s9_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.46278 -0.66684 -0.03968 0.63305 2.96871
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0002388 0.0368267 0.006 0.995
## `Zero-Sum Mindset` 0.3514735 0.0368013 9.551 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9367 on 645 degrees of freedom
## Multiple R-squared: 0.1239, Adjusted R-squared: 0.1225
## F-statistic: 91.21 on 1 and 645 DF, p-value: < 2.2e-16model_2 <- lm(scale(zs_beliefs_India_Pakistan_mean) ~ `Zero-Sum Mindset`+ Agreeableness+ Openness+ Conscientiousness+ Extraversion+ Neuroticism+ `Need for Cognitive Closure`+ Sex + Age + Income+ Education, data = s9_complete)
summary(model_2)##
## Call:
## lm(formula = scale(zs_beliefs_India_Pakistan_mean) ~ `Zero-Sum Mindset` +
## Agreeableness + Openness + Conscientiousness + Extraversion +
## Neuroticism + `Need for Cognitive Closure` + Sex + Age +
## Income + Education, data = s9_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6614 -0.6405 0.0227 0.6306 2.7333
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.029083 0.063372 -0.459 0.6464
## `Zero-Sum Mindset` 0.315387 0.037181 8.482 < 2e-16 ***
## Agreeableness 0.035344 0.040021 0.883 0.3775
## Openness 0.001277 0.039155 0.033 0.9740
## Conscientiousness 0.038270 0.039928 0.958 0.3382
## Extraversion 0.075662 0.042517 1.780 0.0756 .
## Neuroticism 0.003641 0.044624 0.082 0.9350
## `Need for Cognitive Closure` 0.188332 0.041564 4.531 7.01e-06 ***
## SexMale 0.043533 0.079807 0.545 0.5856
## Age 0.043927 0.037509 1.171 0.2420
## Income 0.008737 0.037005 0.236 0.8134
## Education 0.030947 0.037443 0.827 0.4088
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.911 on 635 degrees of freedom
## Multiple R-squared: 0.1842, Adjusted R-squared: 0.17
## F-statistic: 13.03 on 11 and 635 DF, p-value: < 2.2e-16anova(model_1, model_2)## Analysis of Variance Table
##
## Model 1: scale(zs_beliefs_India_Pakistan_mean) ~ `Zero-Sum Mindset`
## Model 2: scale(zs_beliefs_India_Pakistan_mean) ~ `Zero-Sum Mindset` +
## Agreeableness + Openness + Conscientiousness + Extraversion +
## Neuroticism + `Need for Cognitive Closure` + Sex + Age +
## Income + Education
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 645 565.96
## 2 635 527.03 10 38.933 4.6909 1.737e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1#apa.reg.table(model_1, model_2, filename = "h4b_Pakistan.doc")
## Comparing with BFI only
model_3 <- lm(scale(zs_beliefs_India_Pakistan_mean) ~ `Zero-Sum Mindset`+ Agreeableness + Openness + Conscientiousness + Extraversion + Neuroticism, data = s9_complete)
summary(model_3)##
## Call:
## lm(formula = scale(zs_beliefs_India_Pakistan_mean) ~ `Zero-Sum Mindset` +
## Agreeableness + Openness + Conscientiousness + Extraversion +
## Neuroticism, data = s9_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.54747 -0.64208 -0.00169 0.62336 2.91550
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -6.494e-05 3.633e-02 -0.002 0.99857
## `Zero-Sum Mindset` 3.297e-01 3.704e-02 8.901 < 2e-16 ***
## Agreeableness 6.968e-02 3.964e-02 1.758 0.07925 .
## Openness 1.135e-02 3.885e-02 0.292 0.77019
## Conscientiousness 8.313e-02 3.908e-02 2.127 0.03376 *
## Extraversion 1.158e-01 4.191e-02 2.764 0.00587 **
## Neuroticism 3.369e-02 4.330e-02 0.778 0.43683
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9241 on 640 degrees of freedom
## Multiple R-squared: 0.154, Adjusted R-squared: 0.1461
## F-statistic: 19.42 on 6 and 640 DF, p-value: < 2.2e-16# With acquiescence index
model_4 <- lm(scale(zs_beliefs_India_Pakistan_mean) ~ `Zero-Sum Mindset`+ Agreeableness + Openness + Conscientiousness + Extraversion + Neuroticism + acq_index, data = s9_complete)
summary(model_4)##
## Call:
## lm(formula = scale(zs_beliefs_India_Pakistan_mean) ~ `Zero-Sum Mindset` +
## Agreeableness + Openness + Conscientiousness + Extraversion +
## Neuroticism + acq_index, data = s9_complete)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4534 -0.6344 0.0043 0.6141 2.8131
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.825074 0.315564 -2.615 0.00914 **
## `Zero-Sum Mindset` 0.320650 0.037030 8.659 < 2e-16 ***
## Agreeableness 0.073048 0.039480 1.850 0.06474 .
## Openness 0.002041 0.038832 0.053 0.95811
## Conscientiousness 0.052447 0.040606 1.292 0.19696
## Extraversion 0.087416 0.043092 2.029 0.04292 *
## Neuroticism 0.003436 0.044612 0.077 0.93863
## acq_index 0.190801 0.072500 2.632 0.00870 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9198 on 639 degrees of freedom
## Multiple R-squared: 0.1631, Adjusted R-squared: 0.1539
## F-statistic: 17.79 on 7 and 639 DF, p-value: < 2.2e-16# Compute VIF for each predictor
vif_values <- car::vif(model_2)
if (any(vif_values > 5)) {
# Print a message indicating predictors with high VIF
high_vif_predictors <- names(vif_values[vif_values > 5])
message("Multicollinearity detected. Predictors with VIF > 5: ", paste(high_vif_predictors, collapse = ", "))
} else {
message("No significant multicollinearity detected.")
}## No significant multicollinearity detected.#India
s8_corr_table <- select(s8, zsm_mean, O_mean, C_mean, E_mean, A_mean, N_mean)
#apa.cor.table(s8_corr_table, filename = "India - BFI Correlation Table.doc") #Note that this does not partial out acquiescence index
#Pakistan
s9_corr_table <- select(s9, zsm_mean, O_mean, C_mean, E_mean, A_mean, N_mean)
#apa.cor.table(s9_corr_table, filename = "Pakistan - BFI Correlation Table.doc") #Note that this does not partial out acquiescence index