Hypothesis 5a: People with stronger zero-sum mindsets will be less likely to embrace cooperation as a strategic response to scarcity.
Hypothesis 5b: People with a stronger zero-sum mindset will be more likely to embrace a “win-at-all-costs” attitude towards competitions.
Hypothesis 5c: People with stronger mindsets will be more likely to embrace a social dominance orientation towards group relationships.
For each hypothesis we first fit a baseline model predicting each generalized strategic preference from zero-sum mindset (i.e. zero-order correlations). Second, to ascertain the robustness of our finding, we add relevant control variables to the models. In Study 5a, we predict preference for cooperation from zero-sum mindset while controlling for all Big Five personality traits (most notably agreeableness) and primal world beliefs (which notably includes the general belief that the world is a cooperative place) as well as demographic characteristics. In Study 5b, we predict preference for cut-throat competition while controlling for all Big Five personality traits as well as other dimensions of competitiveness and demographic characteristics. In Study 5c, we predict preference for group-based dominance from zero-sum mindset while controlling for demographic characteristics (most notably sex, income, and political orientation) and measures of cognitive style (need for closure) that have established associations with SDO. Further to the broader question about whether zero-sum mindset should be considered as psychologically distinct from economic zero-sum beliefs, in Study 5b and 5c, we also compare these tests of the zero-sum mindset’s convergent validity to that of economic zero-sum beliefs.
cor.test(h5a$zsm_mean, h5a$cooperation_under_scarcity_mean)##
## Pearson's product-moment correlation
##
## data: h5a$zsm_mean and h5a$cooperation_under_scarcity_mean
## t = -6.7853, df = 497, p-value = 3.305e-11
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.3695104 -0.2087327
## sample estimates:
## cor
## -0.2911762cor_table_df <- select(h5a, zsm_mean, cooperation_under_scarcity_mean, starts_with("p_"), O, C, E, A, N, age, sex, political_lean, income, education, political_lean)
apa.cor.table(cor_table_df)##
##
## Means, standard deviations, and correlations with confidence intervals
##
##
## Variable M SD 1 2
## 1. zsm_mean 2.67 1.02
##
## 2. cooperation_under_scarcity_mean 5.00 0.99 -.29**
## [-.37, -.21]
##
## 3. p_changing 3.49 0.81 .01 .12**
## [-.08, .10] [.03, .20]
##
## 4. p_interconnected 3.47 0.97 -.11* .15**
## [-.20, -.02] [.06, .23]
##
## 5. p_abundant 3.20 0.89 -.35** .04
## [-.42, -.27] [-.05, .13]
##
## 6. p_hierarchical 2.50 0.96 .26** -.28**
## [.18, .34] [-.36, -.20]
##
## 7. p_just 2.44 0.95 -.15** -.10*
## [-.24, -.06] [-.19, -.01]
##
## 8. p_cooperative 2.51 1.05 -.37** .20**
## [-.44, -.29] [.11, .28]
##
## 9. p_improvable 3.32 0.80 -.30** .08
## [-.38, -.22] [-.01, .16]
##
## 10. p_harmless 2.13 1.00 -.23** .05
## [-.31, -.14] [-.04, .14]
##
## 11. O 3.96 0.80 -.09* .13**
## [-.18, -.01] [.04, .21]
##
## 12. C 3.33 0.98 -.05 -.09*
## [-.14, .04] [-.18, -.01]
##
## 13. E 2.71 0.95 -.03 -.02
## [-.12, .05] [-.10, .07]
##
## 14. A 3.76 0.63 -.32** .26**
## [-.39, -.23] [.18, .34]
##
## 15. N 3.06 0.97 .09 .12**
## [-.00, .17] [.03, .21]
##
## 16. age 33.67 12.33 -.14** .03
## [-.22, -.05] [-.06, .12]
##
## 17. income 6.30 3.22 -.05 -.07
## [-.14, .04] [-.16, .01]
##
## 18. education 4.02 1.40 -.06 -.07
## [-.14, .03] [-.16, .02]
##
## 3 4 5 6 7 8
##
##
##
##
##
##
##
##
## .25**
## [.17, .33]
##
## -.12** .15**
## [-.21, -.04] [.06, .23]
##
## .06 -.07 -.06
## [-.02, .15] [-.15, .02] [-.15, .03]
##
## -.11* .04 .53** .15**
## [-.20, -.03] [-.05, .13] [.46, .59] [.06, .24]
##
## -.25** .05 .49** -.33** .41**
## [-.33, -.17] [-.04, .14] [.42, .55] [-.41, -.25] [.33, .48]
##
## .03 .31** .57** -.03 .47** .39**
## [-.06, .12] [.23, .38] [.50, .62] [-.11, .06] [.40, .54] [.32, .47]
##
## -.32** .04 .38** -.18** .34** .58**
## [-.40, -.24] [-.04, .13] [.30, .45] [-.27, -.10] [.26, .41] [.52, .63]
##
## .12** .27** .11* -.18** -.06 .06
## [.03, .21] [.18, .34] [.02, .20] [-.26, -.09] [-.15, .03] [-.03, .14]
##
## -.08 .05 .14** .12** .19** .04
## [-.17, .01] [-.03, .14] [.06, .23] [.04, .21] [.11, .28] [-.05, .12]
##
## -.10* .08 .28** .04 .25** .13**
## [-.19, -.02] [-.01, .17] [.20, .36] [-.05, .13] [.17, .33] [.05, .22]
##
## .05 .19** .23** -.16** .19** .29**
## [-.04, .13] [.10, .27] [.15, .31] [-.25, -.08] [.10, .27] [.21, .37]
##
## .15** -.02 -.38** -.03 -.35** -.26**
## [.07, .24] [-.11, .07] [-.45, -.30] [-.11, .06] [-.42, -.27] [-.34, -.17]
##
## -.05 .09* .14** -.03 .05 .05
## [-.14, .04] [.00, .18] [.05, .22] [-.12, .06] [-.04, .14] [-.04, .14]
##
## -.17** -.07 .14** .06 .18** .08
## [-.25, -.08] [-.16, .01] [.06, .23] [-.03, .14] [.09, .26] [-.01, .17]
##
## -.06 .07 .04 -.04 -.01 .07
## [-.15, .03] [-.02, .15] [-.05, .13] [-.13, .04] [-.10, .08] [-.02, .15]
##
## 9 10 11 12 13 14
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## .32**
## [.24, .40]
##
## .18** -.05
## [.10, .27] [-.13, .04]
##
## .17** .02 -.01
## [.09, .26] [-.07, .11] [-.10, .08]
##
## .28** .14** .20** .33**
## [.20, .36] [.06, .23] [.11, .28] [.25, .41]
##
## .28** .28** .16** .16** .15**
## [.20, .36] [.19, .36] [.07, .24] [.07, .24] [.07, .24]
##
## -.33** -.31** -.09 -.47** -.50** -.25**
## [-.41, -.25] [-.39, -.23] [-.17, .00] [-.53, -.40] [-.57, -.44] [-.33, -.16]
##
## .12* .14** .02 .22** .17** .15**
## [.03, .21] [.05, .23] [-.07, .11] [.13, .30] [.08, .25] [.06, .24]
##
## .03 .11* -.09* .12** .14** -.04
## [-.05, .12] [.02, .20] [-.18, -.01] [.04, .21] [.06, .23] [-.13, .05]
##
## .08 .15** .05 .15** .11* .01
## [-.00, .17] [.06, .23] [-.04, .13] [.07, .24] [.02, .19] [-.08, .10]
##
## 15 16 17
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## -.23**
## [-.31, -.14]
##
## -.15** -.14**
## [-.23, -.06] [-.22, -.05]
##
## -.14** .14** .19**
## [-.22, -.05] [.05, .23] [.11, .28]
##
##
## 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.
## # Controlling for demographics
test <- lm(scale(h5a$cooperation_under_scarcity_mean) ~ scale(h5a$zsm_mean) + scale(h5a$age) + scale(h5a$income) + scale(h5a$education) + as.factor(h5a$race) + as.factor(h5a$political_lean))
summary(test)##
## Call:
## lm(formula = scale(h5a$cooperation_under_scarcity_mean) ~ scale(h5a$zsm_mean) +
## scale(h5a$age) + scale(h5a$income) + scale(h5a$education) +
## as.factor(h5a$race) + as.factor(h5a$political_lean))
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.2491 -0.4300 0.0917 0.6683 2.0046
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.85793 0.18969 -4.523 7.79e-06
## scale(h5a$zsm_mean) -0.27919 0.04425 -6.310 6.59e-10
## scale(h5a$age) 0.02185 0.04696 0.465 0.6420
## scale(h5a$income) -0.01992 0.04626 -0.430 0.6670
## scale(h5a$education) -0.07284 0.04572 -1.593 0.1118
## as.factor(h5a$race)Black/African American 0.43884 0.21942 2.000 0.0461
## as.factor(h5a$race)Latinx 0.37216 0.21666 1.718 0.0865
## as.factor(h5a$race)Mixed 0.26340 0.24024 1.096 0.2735
## as.factor(h5a$race)Other 0.63768 0.34920 1.826 0.0685
## as.factor(h5a$race)White 0.36827 0.16020 2.299 0.0220
## as.factor(h5a$political_lean)Liberal 0.68536 0.13595 5.041 6.67e-07
## as.factor(h5a$political_lean)Moderate 0.35696 0.14989 2.381 0.0177
## as.factor(h5a$political_lean)N/A 0.64039 0.40849 1.568 0.1176
## as.factor(h5a$political_lean)Other 0.74096 0.24167 3.066 0.0023
##
## (Intercept) ***
## scale(h5a$zsm_mean) ***
## scale(h5a$age)
## scale(h5a$income)
## scale(h5a$education)
## as.factor(h5a$race)Black/African American *
## as.factor(h5a$race)Latinx .
## as.factor(h5a$race)Mixed
## as.factor(h5a$race)Other .
## as.factor(h5a$race)White *
## as.factor(h5a$political_lean)Liberal ***
## as.factor(h5a$political_lean)Moderate *
## as.factor(h5a$political_lean)N/A
## as.factor(h5a$political_lean)Other **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9359 on 458 degrees of freedom
## (27 observations deleted due to missingness)
## Multiple R-squared: 0.1688, Adjusted R-squared: 0.1452
## F-statistic: 7.153 on 13 and 458 DF, p-value: 9.405e-13# Controlling for primal world beliefs
test <- lm(scale(h5a$cooperation_under_scarcity_mean) ~ scale(h5a$zsm_mean) + scale(h5a$p_changing) + scale(h5a$p_interconnected) + scale(h5a$p_abundant) + scale(h5a$p_hierarchical) + scale(h5a$p_just) + scale(h5a$p_cooperative) + scale(h5a$p_improvable) + scale(h5a$p_harmless))
summary(test)##
## Call:
## lm(formula = scale(h5a$cooperation_under_scarcity_mean) ~ scale(h5a$zsm_mean) +
## scale(h5a$p_changing) + scale(h5a$p_interconnected) + scale(h5a$p_abundant) +
## scale(h5a$p_hierarchical) + scale(h5a$p_just) + scale(h5a$p_cooperative) +
## scale(h5a$p_improvable) + scale(h5a$p_harmless))
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.3499 -0.4206 0.0928 0.5596 1.8161
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -4.242e-16 4.083e-02 0.000 1.000000
## scale(h5a$zsm_mean) -2.147e-01 4.634e-02 -4.634 4.61e-06 ***
## scale(h5a$p_changing) 1.215e-01 4.566e-02 2.661 0.008056 **
## scale(h5a$p_interconnected) 8.510e-02 4.477e-02 1.901 0.057885 .
## scale(h5a$p_abundant) -4.930e-02 5.647e-02 -0.873 0.383076
## scale(h5a$p_hierarchical) -1.512e-01 4.675e-02 -3.234 0.001302 **
## scale(h5a$p_just) -1.450e-01 5.338e-02 -2.717 0.006831 **
## scale(h5a$p_cooperative) 2.010e-01 5.929e-02 3.390 0.000755 ***
## scale(h5a$p_improvable) 6.914e-03 5.477e-02 0.126 0.899596
## scale(h5a$p_harmless) -4.095e-02 5.250e-02 -0.780 0.435799
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9122 on 489 degrees of freedom
## Multiple R-squared: 0.183, Adjusted R-squared: 0.1679
## F-statistic: 12.17 on 9 and 489 DF, p-value: < 2.2e-16# Controlling for BFI
test <- lm(scale(h5a$cooperation_under_scarcity_mean) ~ scale(h5a$zsm_mean) + scale(h5a$O) + scale(h5a$C) + scale(h5a$E)+ scale(h5a$A) + scale(h5a$N))
summary(test)##
## Call:
## lm(formula = scale(h5a$cooperation_under_scarcity_mean) ~ scale(h5a$zsm_mean) +
## scale(h5a$O) + scale(h5a$C) + scale(h5a$E) + scale(h5a$A) +
## scale(h5a$N))
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.2509 -0.4524 0.0703 0.6388 1.7235
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -6.097e-16 4.112e-02 0.000 1.000000
## scale(h5a$zsm_mean) -2.302e-01 4.346e-02 -5.296 1.78e-07 ***
## scale(h5a$O) 7.900e-02 4.259e-02 1.855 0.064199 .
## scale(h5a$C) -6.475e-02 4.717e-02 -1.373 0.170472
## scale(h5a$E) 4.802e-02 4.895e-02 0.981 0.327006
## scale(h5a$A) 2.293e-01 4.501e-02 5.095 4.98e-07 ***
## scale(h5a$N) 1.978e-01 5.206e-02 3.800 0.000163 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9185 on 492 degrees of freedom
## Multiple R-squared: 0.1665, Adjusted R-squared: 0.1563
## F-statistic: 16.38 on 6 and 492 DF, p-value: < 2.2e-16# Controlling for primals and BFI and demographics
test <- lm(scale(h5a$cooperation_under_scarcity_mean) ~ scale(h5a$zsm_mean) + scale(h5a$p_changing) + scale(h5a$p_interconnected) + scale(h5a$p_abundant) + scale(h5a$p_hierarchical) + scale(h5a$p_just) + scale(h5a$p_cooperative) + scale(h5a$p_improvable) + scale(h5a$p_harmless) + scale(h5a$O) + scale(h5a$C) + scale(h5a$E)+ scale(h5a$A) + scale(h5a$N) + scale(h5a$age) + scale(h5a$income) + scale(h5a$education) + as.factor(h5a$race) + as.factor(h5a$political_lean))
summary(test)##
## Call:
## lm(formula = scale(h5a$cooperation_under_scarcity_mean) ~ scale(h5a$zsm_mean) +
## scale(h5a$p_changing) + scale(h5a$p_interconnected) + scale(h5a$p_abundant) +
## scale(h5a$p_hierarchical) + scale(h5a$p_just) + scale(h5a$p_cooperative) +
## scale(h5a$p_improvable) + scale(h5a$p_harmless) + scale(h5a$O) +
## scale(h5a$C) + scale(h5a$E) + scale(h5a$A) + scale(h5a$N) +
## scale(h5a$age) + scale(h5a$income) + scale(h5a$education) +
## as.factor(h5a$race) + as.factor(h5a$political_lean))
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.0116 -0.4396 0.0731 0.5677 2.0460
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.537361 0.193417 -2.778 0.005696
## scale(h5a$zsm_mean) -0.161177 0.048566 -3.319 0.000979
## scale(h5a$p_changing) 0.101719 0.047401 2.146 0.032419
## scale(h5a$p_interconnected) 0.030849 0.047092 0.655 0.512754
## scale(h5a$p_abundant) -0.007393 0.058761 -0.126 0.899930
## scale(h5a$p_hierarchical) -0.124568 0.048076 -2.591 0.009882
## scale(h5a$p_just) -0.129261 0.056004 -2.308 0.021454
## scale(h5a$p_cooperative) 0.174232 0.061053 2.854 0.004522
## scale(h5a$p_improvable) 0.010621 0.057294 0.185 0.853020
## scale(h5a$p_harmless) -0.027681 0.055447 -0.499 0.617865
## scale(h5a$O) -0.015959 0.046934 -0.340 0.733995
## scale(h5a$C) -0.021352 0.049013 -0.436 0.663316
## scale(h5a$E) 0.068990 0.050641 1.362 0.173776
## scale(h5a$A) 0.197747 0.047443 4.168 3.69e-05
## scale(h5a$N) 0.149936 0.057266 2.618 0.009140
## scale(h5a$age) 0.040856 0.047201 0.866 0.387189
## scale(h5a$income) 0.031362 0.045798 0.685 0.493833
## scale(h5a$education) -0.067721 0.044352 -1.527 0.127495
## as.factor(h5a$race)Black/African American 0.326819 0.212707 1.536 0.125132
## as.factor(h5a$race)Latinx 0.306677 0.208564 1.470 0.142155
## as.factor(h5a$race)Mixed 0.250385 0.232379 1.077 0.281847
## as.factor(h5a$race)Other 0.472011 0.334472 1.411 0.158880
## as.factor(h5a$race)White 0.203725 0.156969 1.298 0.195005
## as.factor(h5a$political_lean)Liberal 0.406080 0.142980 2.840 0.004716
## as.factor(h5a$political_lean)Moderate 0.241268 0.146988 1.641 0.101419
## as.factor(h5a$political_lean)N/A 0.585572 0.395878 1.479 0.139801
## as.factor(h5a$political_lean)Other 0.528775 0.239356 2.209 0.027673
##
## (Intercept) **
## scale(h5a$zsm_mean) ***
## scale(h5a$p_changing) *
## scale(h5a$p_interconnected)
## scale(h5a$p_abundant)
## scale(h5a$p_hierarchical) **
## scale(h5a$p_just) *
## scale(h5a$p_cooperative) **
## scale(h5a$p_improvable)
## scale(h5a$p_harmless)
## scale(h5a$O)
## scale(h5a$C)
## scale(h5a$E)
## scale(h5a$A) ***
## scale(h5a$N) **
## scale(h5a$age)
## scale(h5a$income)
## scale(h5a$education)
## as.factor(h5a$race)Black/African American
## as.factor(h5a$race)Latinx
## as.factor(h5a$race)Mixed
## as.factor(h5a$race)Other
## as.factor(h5a$race)White
## as.factor(h5a$political_lean)Liberal **
## as.factor(h5a$political_lean)Moderate
## as.factor(h5a$political_lean)N/A
## as.factor(h5a$political_lean)Other *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8897 on 445 degrees of freedom
## (27 observations deleted due to missingness)
## Multiple R-squared: 0.2702, Adjusted R-squared: 0.2275
## F-statistic: 6.335 on 26 and 445 DF, p-value: < 2.2e-16vif_values <- car::vif(test)
# 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."comp_df <- select(h5b, zsm_mean, starts_with("comp") & ends_with("mean"))
apa.cor.table(comp_df)##
##
## Means, standard deviations, and correlations with confidence intervals
##
##
## Variable M SD 1 2 3 4
## 1. zsm_mean 2.97 1.18
##
## 2. comp_lack_mean 3.22 0.93 .13**
## [.09, .17]
##
## 3. comp_hyper_mean 2.32 1.08 .58** .05*
## [.55, .60] [.01, .09]
##
## 4. comp_anx_mean 3.03 0.98 .28** .58** .24**
## [.24, .32] [.55, .61] [.20, .28]
##
## 5. comp_dev_mean 3.36 0.99 .21** -.40** .46** -.25**
## [.16, .25] [-.43, -.36] [.42, .49] [-.29, -.21]
##
##
## 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.
## # Exploring unique relationships with Zero-Sum Mindset when partialling out shared variance among dimensions
test <- lm(h5b$zsm_mean ~ h5b$comp_anx_mean + h5b$comp_lack_mean + h5b$comp_dev_mean + h5b$comp_hyper_mean)
summary(test)##
## Call:
## lm(formula = h5b$zsm_mean ~ h5b$comp_anx_mean + h5b$comp_lack_mean +
## h5b$comp_dev_mean + h5b$comp_hyper_mean)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6481 -0.6150 -0.0430 0.6002 4.6005
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.995901 0.135585 7.345 2.90e-13 ***
## h5b$comp_anx_mean 0.166007 0.026822 6.189 7.22e-10 ***
## h5b$comp_lack_mean 0.029491 0.028481 1.035 0.301
## h5b$comp_dev_mean 0.001825 0.026764 0.068 0.946
## h5b$comp_hyper_mean 0.590254 0.023296 25.337 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.947 on 2155 degrees of freedom
## Multiple R-squared: 0.3555, Adjusted R-squared: 0.3543
## F-statistic: 297.2 on 4 and 2155 DF, p-value: < 2.2e-16# Weighted Regression
test <- lm(h5b$zsm_mean ~ h5b$comp_anx_mean + h5b$comp_lack_mean + h5b$comp_dev_mean + h5b$comp_hyper_mean, weights =h5b$weight )
summary(test)##
## Call:
## lm(formula = h5b$zsm_mean ~ h5b$comp_anx_mean + h5b$comp_lack_mean +
## h5b$comp_dev_mean + h5b$comp_hyper_mean, weights = h5b$weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -5.5991 -0.4646 -0.0176 0.4873 4.4882
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.022561 0.127141 8.043 1.44e-15 ***
## h5b$comp_anx_mean 0.232347 0.025815 9.001 < 2e-16 ***
## h5b$comp_lack_mean -0.028319 0.027241 -1.040 0.299
## h5b$comp_dev_mean -0.009198 0.025136 -0.366 0.714
## h5b$comp_hyper_mean 0.583352 0.022597 25.816 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9172 on 2155 degrees of freedom
## Multiple R-squared: 0.376, Adjusted R-squared: 0.3748
## F-statistic: 324.6 on 4 and 2155 DF, p-value: < 2.2e-16nrow(h5b)## [1] 2160vif_values <- car::vif(test)
# Check if any VIF values are greater than 10
high_vif <- which(vif_values > 10)
# Generate a message based on the results
if(length(high_vif) == 0) {
message <- "Based on the Variance Inflation Factor (VIF) values, there is no indication of problematic multicollinearity in the model."
} else {
problematic_vars <- names(vif_values)[high_vif]
message <- paste("Based on the Variance Inflation Factor (VIF) values, there is an indication of problematic multicollinearity for the following variables:",
paste(problematic_vars, collapse = ", "), ". Consider examining the relationships among these variables or potentially revising the model.")
}
# Print the message
print(message)## [1] "Based on the Variance Inflation Factor (VIF) values, there is no indication of problematic multicollinearity in the model."# ZSM Alone Weighted Regression
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean), weights = h5b$weight)
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean),
## weights = h5b$weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -3.1046 -0.4313 -0.0429 0.3818 5.4271
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.01008 0.01725 -0.585 0.559
## scale(h5b$zsm_mean) 0.58844 0.01752 33.596 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8011 on 2158 degrees of freedom
## Multiple R-squared: 0.3434, Adjusted R-squared: 0.3431
## F-statistic: 1129 on 1 and 2158 DF, p-value: < 2.2e-16# ZSM + Demographics Weighted Regression
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) + as.factor(h5b$sex) + scale(h5b$age) + scale(h5b$income) + scale(h5b$education) + as.factor(h5b$race), weights = h5b$weight)
# (Demographics + BFI Weighted Regression
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) + as.factor(h5b$sex) + scale(h5b$age) + scale(h5b$income) + scale(h5b$education) + as.factor(h5b$race) + scale(h5b$A) + scale(h5b$O) + scale(h5b$E) + scale(h5b$N) + scale(h5b$C), weights = h5b$weight)
# Full Model (Demographics + BFI + shared variance of other competitive dimensions) Weighted Regression
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) + as.factor(h5b$sex) + scale(h5b$age) + scale(h5b$income) + scale(h5b$education) + as.factor(h5b$race) + scale(h5b$political_lean) + scale(h5b$A) + scale(h5b$O) + scale(h5b$E) + scale(h5b$N) + scale(h5b$C) + scale(h5b$comp_anx_mean) + scale(h5b$comp_lack_mean) + scale(h5b$comp_dev_mean), weights = h5b$weight)
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) +
## as.factor(h5b$sex) + scale(h5b$age) + scale(h5b$income) +
## scale(h5b$education) + as.factor(h5b$race) + scale(h5b$political_lean) +
## scale(h5b$A) + scale(h5b$O) + scale(h5b$E) + scale(h5b$N) +
## scale(h5b$C) + scale(h5b$comp_anx_mean) + scale(h5b$comp_lack_mean) +
## scale(h5b$comp_dev_mean), weights = h5b$weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -3.2868 -0.3328 -0.0114 0.3254 3.6582
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.113861 0.024001 4.744 2.23e-06 ***
## scale(h5b$zsm_mean) 0.341064 0.016802 20.299 < 2e-16 ***
## as.factor(h5b$sex)2 -0.193993 0.030637 -6.332 2.94e-10 ***
## scale(h5b$age) -0.181497 0.016526 -10.982 < 2e-16 ***
## scale(h5b$income) 0.016384 0.015308 1.070 0.28461
## scale(h5b$education) 0.104268 0.018022 5.786 8.28e-09 ***
## as.factor(h5b$race)2 0.105499 0.047373 2.227 0.02605 *
## as.factor(h5b$race)3 0.002375 0.059766 0.040 0.96831
## as.factor(h5b$race)4 0.035745 0.093826 0.381 0.70326
## as.factor(h5b$race)5 0.227302 0.171096 1.329 0.18415
## as.factor(h5b$race)6 0.270605 0.216333 1.251 0.21112
## as.factor(h5b$race)7 -0.699947 0.375172 -1.866 0.06222 .
## as.factor(h5b$race)8 -0.054986 0.106995 -0.514 0.60737
## as.factor(h5b$race)9 0.069881 0.334789 0.209 0.83468
## scale(h5b$political_lean) 0.017316 0.014822 1.168 0.24281
## scale(h5b$A) -0.073824 0.015727 -4.694 2.85e-06 ***
## scale(h5b$O) -0.081928 0.015797 -5.186 2.35e-07 ***
## scale(h5b$E) 0.127161 0.017297 7.352 2.78e-13 ***
## scale(h5b$N) -0.080590 0.018502 -4.356 1.39e-05 ***
## scale(h5b$C) -0.075747 0.018352 -4.127 3.81e-05 ***
## scale(h5b$comp_anx_mean) 0.170140 0.019543 8.706 < 2e-16 ***
## scale(h5b$comp_lack_mean) 0.054425 0.018102 3.007 0.00267 **
## scale(h5b$comp_dev_mean) 0.316998 0.017750 17.859 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6469 on 2137 degrees of freedom
## Multiple R-squared: 0.576, Adjusted R-squared: 0.5717
## F-statistic: 132 on 22 and 2137 DF, p-value: < 2.2e-16# Full Model (Demographics + BFI + shared variance of other competitive dimensions)- Unweighted Regression
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) + as.factor(h5b$sex) + scale(h5b$age) + scale(h5b$income) + scale(h5b$education) + as.factor(h5b$race) + scale(h5b$A) + scale(h5b$O) + scale(h5b$E) + scale(h5b$N) + scale(h5b$C) + scale(h5b$comp_anx_mean) + scale(h5b$comp_lack_mean) + scale(h5b$comp_dev_mean))
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) +
## as.factor(h5b$sex) + scale(h5b$age) + scale(h5b$income) +
## scale(h5b$education) + as.factor(h5b$race) + scale(h5b$A) +
## scale(h5b$O) + scale(h5b$E) + scale(h5b$N) + scale(h5b$C) +
## scale(h5b$comp_anx_mean) + scale(h5b$comp_lack_mean) + scale(h5b$comp_dev_mean))
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.41549 -0.43037 0.00014 0.42393 2.89094
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.09223 0.02359 3.909 9.55e-05 ***
## scale(h5b$zsm_mean) 0.33026 0.01675 19.721 < 2e-16 ***
## as.factor(h5b$sex)2 -0.17102 0.03106 -5.506 4.12e-08 ***
## scale(h5b$age) -0.15059 0.01636 -9.207 < 2e-16 ***
## scale(h5b$income) 0.07511 0.01747 4.299 1.79e-05 ***
## scale(h5b$education) 0.05706 0.01701 3.355 0.000807 ***
## as.factor(h5b$race)2 0.07432 0.05208 1.427 0.153703
## as.factor(h5b$race)3 -0.02918 0.06592 -0.443 0.658032
## as.factor(h5b$race)4 -0.04126 0.08892 -0.464 0.642641
## as.factor(h5b$race)5 0.14691 0.15273 0.962 0.336213
## as.factor(h5b$race)6 -0.02878 0.23448 -0.123 0.902323
## as.factor(h5b$race)7 -0.42916 0.33026 -1.299 0.193918
## as.factor(h5b$race)8 -0.06032 0.11003 -0.548 0.583616
## as.factor(h5b$race)9 -0.09131 0.25009 -0.365 0.715055
## scale(h5b$A) -0.07842 0.01598 -4.907 9.95e-07 ***
## scale(h5b$O) -0.08192 0.01585 -5.167 2.60e-07 ***
## scale(h5b$E) 0.11581 0.01695 6.833 1.08e-11 ***
## scale(h5b$N) -0.07692 0.01846 -4.167 3.21e-05 ***
## scale(h5b$C) -0.07575 0.01794 -4.222 2.53e-05 ***
## scale(h5b$comp_anx_mean) 0.19373 0.01971 9.830 < 2e-16 ***
## scale(h5b$comp_lack_mean) 0.05965 0.01852 3.222 0.001293 **
## scale(h5b$comp_dev_mean) 0.35427 0.01837 19.283 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6576 on 2138 degrees of freedom
## Multiple R-squared: 0.5718, Adjusted R-squared: 0.5676
## F-statistic: 136 on 21 and 2138 DF, p-value: < 2.2e-16# Comparing Simple Models
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean), weights = h5b$weight)
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean),
## weights = h5b$weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -3.1046 -0.4313 -0.0429 0.3818 5.4271
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.01008 0.01725 -0.585 0.559
## scale(h5b$zsm_mean) 0.58844 0.01752 33.596 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8011 on 2158 degrees of freedom
## Multiple R-squared: 0.3434, Adjusted R-squared: 0.3431
## F-statistic: 1129 on 1 and 2158 DF, p-value: < 2.2e-16test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$econ_zsb_mean), weights = h5b$weight)
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$econ_zsb_mean),
## weights = h5b$weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -2.8545 -0.5721 -0.0885 0.5450 5.1246
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.006059 0.020205 -0.30 0.764
## scale(h5b$econ_zsb_mean) 0.315739 0.020004 15.78 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9361 on 2158 degrees of freedom
## Multiple R-squared: 0.1035, Adjusted R-squared: 0.1031
## F-statistic: 249.1 on 1 and 2158 DF, p-value: < 2.2e-16# Unweighted
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$econ_zsb_mean))
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$econ_zsb_mean))
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.8138 -0.6980 -0.1425 0.6446 3.1030
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.838e-15 2.043e-02 0.00 1
## scale(h5b$econ_zsb_mean) 3.141e-01 2.044e-02 15.37 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9496 on 2158 degrees of freedom
## Multiple R-squared: 0.09866, Adjusted R-squared: 0.09825
## F-statistic: 236.2 on 1 and 2158 DF, p-value: < 2.2e-16#Weighted Regression accounting for shared variance
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) + scale(h5b$econ_zsb_mean), weights = h5b$weight)
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) +
## scale(h5b$econ_zsb_mean), weights = h5b$weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -3.1301 -0.4276 -0.0435 0.3802 5.3818
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.008799 0.017291 -0.509 0.611
## scale(h5b$zsm_mean) 0.577117 0.020537 28.101 <2e-16 ***
## scale(h5b$econ_zsb_mean) 0.021192 0.020073 1.056 0.291
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8011 on 2157 degrees of freedom
## Multiple R-squared: 0.3437, Adjusted R-squared: 0.3431
## F-statistic: 564.9 on 2 and 2157 DF, p-value: < 2.2e-16#Unweighted Regression accounting for shared variance
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) + scale(h5b$econ_zsb_mean), weights = h5b$weight)
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) +
## scale(h5b$econ_zsb_mean), weights = h5b$weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -3.1301 -0.4276 -0.0435 0.3802 5.3818
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.008799 0.017291 -0.509 0.611
## scale(h5b$zsm_mean) 0.577117 0.020537 28.101 <2e-16 ***
## scale(h5b$econ_zsb_mean) 0.021192 0.020073 1.056 0.291
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8011 on 2157 degrees of freedom
## Multiple R-squared: 0.3437, Adjusted R-squared: 0.3431
## F-statistic: 564.9 on 2 and 2157 DF, p-value: < 2.2e-16# ZSM + Economic ZSB, Demographics + BFI - Weighted Regression
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) + scale(h5b$econ_zsb_mean) + as.factor(h5b$sex) + scale(h5b$age) + scale(h5b$income) + scale(h5b$education) + as.factor(h5b$race) + scale(h5b$A) + scale(h5b$O) + scale(h5b$E) + scale(h5b$N) + scale(h5b$C), weights = h5b$weight)
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) +
## scale(h5b$econ_zsb_mean) + as.factor(h5b$sex) + scale(h5b$age) +
## scale(h5b$income) + scale(h5b$education) + as.factor(h5b$race) +
## scale(h5b$A) + scale(h5b$O) + scale(h5b$E) + scale(h5b$N) +
## scale(h5b$C), weights = h5b$weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -3.1439 -0.3648 -0.0350 0.3495 4.0434
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.161234 0.025768 6.257 4.72e-10 ***
## scale(h5b$zsm_mean) 0.439523 0.019358 22.705 < 2e-16 ***
## scale(h5b$econ_zsb_mean) -0.025177 0.018524 -1.359 0.17424
## as.factor(h5b$sex)2 -0.257474 0.032733 -7.866 5.77e-15 ***
## scale(h5b$age) -0.210831 0.017944 -11.750 < 2e-16 ***
## scale(h5b$income) 0.034191 0.016565 2.064 0.03914 *
## scale(h5b$education) 0.147038 0.019404 7.578 5.20e-14 ***
## as.factor(h5b$race)2 0.094454 0.050826 1.858 0.06325 .
## as.factor(h5b$race)3 0.004988 0.064809 0.077 0.93866
## as.factor(h5b$race)4 0.022236 0.102006 0.218 0.82746
## as.factor(h5b$race)5 0.148550 0.185504 0.801 0.42334
## as.factor(h5b$race)6 0.239415 0.234784 1.020 0.30797
## as.factor(h5b$race)7 -0.945519 0.406022 -2.329 0.01997 *
## as.factor(h5b$race)8 -0.101713 0.115453 -0.881 0.37842
## as.factor(h5b$race)9 0.131701 0.363538 0.362 0.71718
## scale(h5b$A) -0.032949 0.016818 -1.959 0.05023 .
## scale(h5b$O) -0.053967 0.016810 -3.210 0.00135 **
## scale(h5b$E) 0.206506 0.017674 11.684 < 2e-16 ***
## scale(h5b$N) -0.036295 0.019401 -1.871 0.06150 .
## scale(h5b$C) -0.123875 0.019480 -6.359 2.48e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7017 on 2140 degrees of freedom
## Multiple R-squared: 0.5005, Adjusted R-squared: 0.4961
## F-statistic: 112.9 on 19 and 2140 DF, p-value: < 2.2e-16# Full Model (Demographics + BFI + shared variance of other competitive dimensions) Weighted Regression
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) + scale(h5b$econ_zsb_mean) + as.factor(h5b$sex) + scale(h5b$age) + scale(h5b$income) + scale(h5b$education) + as.factor(h5b$race) + scale(h5b$A) + scale(h5b$O) + scale(h5b$E) + scale(h5b$N) + scale(h5b$C) + scale(h5b$comp_anx_mean) + scale(h5b$comp_lack_mean) + scale(h5b$comp_dev_mean), weights = h5b$weight)
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) +
## scale(h5b$econ_zsb_mean) + as.factor(h5b$sex) + scale(h5b$age) +
## scale(h5b$income) + scale(h5b$education) + as.factor(h5b$race) +
## scale(h5b$A) + scale(h5b$O) + scale(h5b$E) + scale(h5b$N) +
## scale(h5b$C) + scale(h5b$comp_anx_mean) + scale(h5b$comp_lack_mean) +
## scale(h5b$comp_dev_mean), weights = h5b$weight)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -3.2179 -0.3339 -0.0141 0.3291 3.7055
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.116834 0.023938 4.881 1.13e-06 ***
## scale(h5b$zsm_mean) 0.360517 0.018335 19.663 < 2e-16 ***
## scale(h5b$econ_zsb_mean) -0.047105 0.017245 -2.731 0.00636 **
## as.factor(h5b$sex)2 -0.196074 0.030595 -6.409 1.80e-10 ***
## scale(h5b$age) -0.186257 0.016580 -11.234 < 2e-16 ***
## scale(h5b$income) 0.012876 0.015293 0.842 0.39990
## scale(h5b$education) 0.106622 0.018018 5.918 3.80e-09 ***
## as.factor(h5b$race)2 0.096424 0.046911 2.055 0.03995 *
## as.factor(h5b$race)3 0.003185 0.059667 0.053 0.95743
## as.factor(h5b$race)4 0.007642 0.093969 0.081 0.93519
## as.factor(h5b$race)5 0.216449 0.170898 1.267 0.20546
## as.factor(h5b$race)6 0.246660 0.216228 1.141 0.25411
## as.factor(h5b$race)7 -0.719097 0.374382 -1.921 0.05490 .
## as.factor(h5b$race)8 -0.057443 0.106475 -0.539 0.58960
## as.factor(h5b$race)9 0.118659 0.334845 0.354 0.72310
## scale(h5b$A) -0.074406 0.015698 -4.740 2.28e-06 ***
## scale(h5b$O) -0.079034 0.015783 -5.008 5.96e-07 ***
## scale(h5b$E) 0.125667 0.017264 7.279 4.69e-13 ***
## scale(h5b$N) -0.079046 0.018480 -4.277 1.97e-05 ***
## scale(h5b$C) -0.076643 0.018300 -4.188 2.93e-05 ***
## scale(h5b$comp_anx_mean) 0.174520 0.019596 8.906 < 2e-16 ***
## scale(h5b$comp_lack_mean) 0.057275 0.018103 3.164 0.00158 **
## scale(h5b$comp_dev_mean) 0.318097 0.017724 17.947 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.646 on 2137 degrees of freedom
## Multiple R-squared: 0.5772, Adjusted R-squared: 0.5729
## F-statistic: 132.6 on 22 and 2137 DF, p-value: < 2.2e-16# Full Model (Demographics + BFI + shared variance of other competitive dimensions)- Unweighted Regression
test <- lm(scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) + scale(h5b$econ_zsb_mean) + as.factor(h5b$sex) + scale(h5b$age) + scale(h5b$income) + scale(h5b$education) + as.factor(h5b$race) + scale(h5b$A) + scale(h5b$O) + scale(h5b$E) + scale(h5b$N) + scale(h5b$C) + scale(h5b$comp_anx_mean) + scale(h5b$comp_lack_mean) + scale(h5b$comp_dev_mean))
summary(test)##
## Call:
## lm(formula = scale(h5b$comp_hyper_mean) ~ scale(h5b$zsm_mean) +
## scale(h5b$econ_zsb_mean) + as.factor(h5b$sex) + scale(h5b$age) +
## scale(h5b$income) + scale(h5b$education) + as.factor(h5b$race) +
## scale(h5b$A) + scale(h5b$O) + scale(h5b$E) + scale(h5b$N) +
## scale(h5b$C) + scale(h5b$comp_anx_mean) + scale(h5b$comp_lack_mean) +
## scale(h5b$comp_dev_mean))
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.40050 -0.42828 -0.00068 0.42451 2.87372
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.09281 0.02360 3.933 8.64e-05 ***
## scale(h5b$zsm_mean) 0.33862 0.01823 18.574 < 2e-16 ***
## scale(h5b$econ_zsb_mean) -0.02001 0.01725 -1.160 0.246214
## as.factor(h5b$sex)2 -0.17208 0.03107 -5.538 3.44e-08 ***
## scale(h5b$age) -0.15309 0.01650 -9.280 < 2e-16 ***
## scale(h5b$income) 0.07423 0.01748 4.246 2.27e-05 ***
## scale(h5b$education) 0.05827 0.01704 3.420 0.000638 ***
## as.factor(h5b$race)2 0.07514 0.05208 1.443 0.149243
## as.factor(h5b$race)3 -0.02864 0.06592 -0.434 0.664028
## as.factor(h5b$race)4 -0.04613 0.08901 -0.518 0.604337
## as.factor(h5b$race)5 0.14402 0.15274 0.943 0.345820
## as.factor(h5b$race)6 -0.03696 0.23457 -0.158 0.874828
## as.factor(h5b$race)7 -0.43374 0.33025 -1.313 0.189201
## as.factor(h5b$race)8 -0.05650 0.11007 -0.513 0.607802
## as.factor(h5b$race)9 -0.07997 0.25026 -0.320 0.749335
## scale(h5b$A) -0.07815 0.01598 -4.890 1.08e-06 ***
## scale(h5b$O) -0.07989 0.01595 -5.010 5.90e-07 ***
## scale(h5b$E) 0.11600 0.01695 6.844 1.00e-11 ***
## scale(h5b$N) -0.07532 0.01851 -4.069 4.89e-05 ***
## scale(h5b$C) -0.07621 0.01795 -4.247 2.26e-05 ***
## scale(h5b$comp_anx_mean) 0.19630 0.01983 9.898 < 2e-16 ***
## scale(h5b$comp_lack_mean) 0.06090 0.01855 3.284 0.001041 **
## scale(h5b$comp_dev_mean) 0.35441 0.01837 19.292 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6575 on 2137 degrees of freedom
## Multiple R-squared: 0.5721, Adjusted R-squared: 0.5677
## F-statistic: 129.9 on 22 and 2137 DF, p-value: < 2.2e-16apa.reg.table(test)##
##
## Regression results using scale(h5b$comp_hyper_mean) as the criterion
##
##
## Predictor b b_95%_CI sr2 sr2_95%_CI
## (Intercept) 0.09** [0.05, 0.14]
## scale(h5b$zsm_mean) 0.34** [0.30, 0.37] .07 [.05, .08]
## scale(h5b$econ_zsb_mean) -0.02 [-0.05, 0.01] .00 [-.00, .00]
## as.factor(h5b$sex)2 -0.17** [-0.23, -0.11] .01 [.00, .01]
## scale(h5b$age) -0.15** [-0.19, -0.12] .02 [.01, .02]
## scale(h5b$income) 0.07** [0.04, 0.11] .00 [.00, .01]
## scale(h5b$education) 0.06** [0.02, 0.09] .00 [-.00, .01]
## as.factor(h5b$race)2 0.08 [-0.03, 0.18] .00 [-.00, .00]
## as.factor(h5b$race)3 -0.03 [-0.16, 0.10] .00 [-.00, .00]
## as.factor(h5b$race)4 -0.05 [-0.22, 0.13] .00 [-.00, .00]
## as.factor(h5b$race)5 0.14 [-0.16, 0.44] .00 [-.00, .00]
## as.factor(h5b$race)6 -0.04 [-0.50, 0.42] .00 [-.00, .00]
## as.factor(h5b$race)7 -0.43 [-1.08, 0.21] .00 [-.00, .00]
## as.factor(h5b$race)8 -0.06 [-0.27, 0.16] .00 [-.00, .00]
## as.factor(h5b$race)9 -0.08 [-0.57, 0.41] .00 [-.00, .00]
## scale(h5b$A) -0.08** [-0.11, -0.05] .00 [.00, .01]
## scale(h5b$O) -0.08** [-0.11, -0.05] .01 [.00, .01]
## scale(h5b$E) 0.12** [0.08, 0.15] .01 [.00, .01]
## scale(h5b$N) -0.08** [-0.11, -0.04] .00 [.00, .01]
## scale(h5b$C) -0.08** [-0.11, -0.04] .00 [.00, .01]
## scale(h5b$comp_anx_mean) 0.20** [0.16, 0.24] .02 [.01, .03]
## scale(h5b$comp_lack_mean) 0.06** [0.02, 0.10] .00 [-.00, .00]
## scale(h5b$comp_dev_mean) 0.35** [0.32, 0.39] .07 [.06, .09]
##
##
##
## Fit
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## R2 = .572**
## 95% CI[.54,.59]
##
##
## Note. A significant b-weight indicates the semi-partial correlation is also significant.
## b represents unstandardized regression weights.
## sr2 represents the semi-partial correlation squared.
## Square brackets are used to enclose the lower and upper limits of a confidence interval.
## * indicates p < .05. ** indicates p < .01.
## #Study 5c: Social Dominance Orientation
cor.test(h5c$zsm_mean, h5c$sdo_mean)##
## Pearson's product-moment correlation
##
## data: h5c$zsm_mean and h5c$sdo_mean
## t = 10.775, df = 819, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.2909671 0.4108883
## sample estimates:
## cor
## 0.3523733test <- lm(scale(h5c$sdo_mean) ~ scale(h5c$zsm_mean))
summary(test)##
## Call:
## lm(formula = scale(h5c$sdo_mean) ~ scale(h5c$zsm_mean))
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.2394 -0.6725 -0.0779 0.6483 3.9654
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8.407e-16 3.268e-02 0.00 1
## scale(h5c$zsm_mean) 3.524e-01 3.270e-02 10.78 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9364 on 819 degrees of freedom
## Multiple R-squared: 0.1242, Adjusted R-squared: 0.1231
## F-statistic: 116.1 on 1 and 819 DF, p-value: < 2.2e-16test <- lm(scale(h5c$sdo_mean) ~ scale(h5c$zsm_mean) + as.factor(h5c$sex) + scale(h5c$age) + scale(h5c$income) + scale(h5c$education) + as.factor(h5c$race) + h5c$political_orientation)
summary(test)##
## Call:
## lm(formula = scale(h5c$sdo_mean) ~ scale(h5c$zsm_mean) + as.factor(h5c$sex) +
## scale(h5c$age) + scale(h5c$income) + scale(h5c$education) +
## as.factor(h5c$race) + h5c$political_orientation)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4023 -0.5788 -0.0889 0.5248 3.9581
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.541020 0.089859 -6.021 2.65e-09 ***
## scale(h5c$zsm_mean) 0.280238 0.031963 8.768 < 2e-16 ***
## as.factor(h5c$sex)Male 0.230774 0.058901 3.918 9.70e-05 ***
## as.factor(h5c$sex)Other -0.150074 0.338997 -0.443 0.6581
## scale(h5c$age) 0.022823 0.030236 0.755 0.4506
## scale(h5c$income) 0.062738 0.030933 2.028 0.0429 *
## scale(h5c$education) 0.001727 0.030600 0.056 0.9550
## as.factor(h5c$race)East Asian 0.237181 0.164977 1.438 0.1509
## as.factor(h5c$race)Indigenous -0.744459 0.825355 -0.902 0.3673
## as.factor(h5c$race)Latinx 0.130941 0.142901 0.916 0.3598
## as.factor(h5c$race)Middle Eastern 0.067172 0.831517 0.081 0.9356
## as.factor(h5c$race)Mixed -0.039389 0.157844 -0.250 0.8030
## as.factor(h5c$race)Other 0.662492 0.345845 1.916 0.0558 .
## as.factor(h5c$race)White 0.037805 0.089534 0.422 0.6730
## h5c$political_orientationModerate 0.456691 0.076824 5.945 4.15e-09 ***
## h5c$political_orientationRight 0.999319 0.070906 14.094 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8185 on 795 degrees of freedom
## (10 observations deleted due to missingness)
## Multiple R-squared: 0.3424, Adjusted R-squared: 0.33
## F-statistic: 27.6 on 15 and 795 DF, p-value: < 2.2e-16apa.reg.table(test)##
##
## Regression results using scale(h5c$sdo_mean) as the criterion
##
##
## Predictor b b_95%_CI sr2 sr2_95%_CI
## (Intercept) -0.54** [-0.72, -0.36]
## scale(h5c$zsm_mean) 0.28** [0.22, 0.34] .06 [.04, .09]
## as.factor(h5c$sex)Male 0.23** [0.12, 0.35] .01 [.00, .03]
## as.factor(h5c$sex)Other -0.15 [-0.82, 0.52] .00 [-.00, .00]
## scale(h5c$age) 0.02 [-0.04, 0.08] .00 [-.00, .00]
## scale(h5c$income) 0.06* [0.00, 0.12] .00 [-.00, .01]
## scale(h5c$education) 0.00 [-0.06, 0.06] .00 [-.00, .00]
## as.factor(h5c$race)East Asian 0.24 [-0.09, 0.56] .00 [-.00, .01]
## as.factor(h5c$race)Indigenous -0.74 [-2.36, 0.88] .00 [-.00, .00]
## as.factor(h5c$race)Latinx 0.13 [-0.15, 0.41] .00 [-.00, .00]
## as.factor(h5c$race)Middle Eastern 0.07 [-1.57, 1.70] .00 [-.00, .00]
## as.factor(h5c$race)Mixed -0.04 [-0.35, 0.27] .00 [-.00, .00]
## as.factor(h5c$race)Other 0.66 [-0.02, 1.34] .00 [-.00, .01]
## as.factor(h5c$race)White 0.04 [-0.14, 0.21] .00 [-.00, .00]
## h5c$political_orientationModerate 0.46** [0.31, 0.61] .03 [.01, .05]
## h5c$political_orientationRight 1.00** [0.86, 1.14] .16 [.12, .21]
##
##
##
## Fit
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## R2 = .342**
## 95% CI[.28,.38]
##
##
## Note. A significant b-weight indicates the semi-partial correlation is also significant.
## b represents unstandardized regression weights.
## sr2 represents the semi-partial correlation squared.
## Square brackets are used to enclose the lower and upper limits of a confidence interval.
## * indicates p < .05. ** indicates p < .01.
## # ZS Econ Simple
test <- lm(scale(h5c$sdo_mean) ~ scale(h5c$zs_econ_mean))
summary(test)##
## Call:
## lm(formula = scale(h5c$sdo_mean) ~ scale(h5c$zs_econ_mean))
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7134 -0.7903 -0.0767 0.7993 3.7094
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.314e-16 3.473e-02 0.000 1.0000
## scale(h5c$zs_econ_mean) -1.038e-01 3.475e-02 -2.987 0.0029 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9952 on 819 degrees of freedom
## Multiple R-squared: 0.01078, Adjusted R-squared: 0.009572
## F-statistic: 8.925 on 1 and 819 DF, p-value: 0.002897# ZS Econ In Full Model
test <- lm(scale(h5c$sdo_mean) ~ scale(h5c$zs_econ_mean) + as.factor(h5c$sex) + scale(h5c$age) + scale(h5c$income) + scale(h5c$education) + as.factor(h5c$race) + h5c$political_orientation)
summary(test)##
## Call:
## lm(formula = scale(h5c$sdo_mean) ~ scale(h5c$zs_econ_mean) +
## as.factor(h5c$sex) + scale(h5c$age) + scale(h5c$income) +
## scale(h5c$education) + as.factor(h5c$race) + h5c$political_orientation)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4038 -0.6269 -0.0418 0.5335 3.7110
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.45259 0.09428 -4.800 1.89e-06 ***
## scale(h5c$zs_econ_mean) -0.03554 0.03205 -1.109 0.2678
## as.factor(h5c$sex)Male 0.30099 0.06128 4.912 1.10e-06 ***
## as.factor(h5c$sex)Other 0.06146 0.35469 0.173 0.8625
## scale(h5c$age) -0.03584 0.03128 -1.146 0.2522
## scale(h5c$income) 0.01497 0.03244 0.461 0.6446
## scale(h5c$education) 0.02791 0.03200 0.872 0.3834
## as.factor(h5c$race)East Asian 0.20926 0.17264 1.212 0.2258
## as.factor(h5c$race)Indigenous -0.59050 0.86375 -0.684 0.4944
## as.factor(h5c$race)Latinx -0.05860 0.14872 -0.394 0.6937
## as.factor(h5c$race)Middle Eastern -0.24942 0.86930 -0.287 0.7742
## as.factor(h5c$race)Mixed -0.19012 0.16452 -1.156 0.2482
## as.factor(h5c$race)Other 0.41983 0.36084 1.163 0.2450
## as.factor(h5c$race)White -0.15419 0.09166 -1.682 0.0929 .
## h5c$political_orientationModerate 0.43383 0.08088 5.364 1.07e-07 ***
## h5c$political_orientationRight 1.12481 0.07339 15.327 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8565 on 795 degrees of freedom
## (10 observations deleted due to missingness)
## Multiple R-squared: 0.2799, Adjusted R-squared: 0.2664
## F-statistic: 20.61 on 15 and 795 DF, p-value: < 2.2e-16# ZS Econ controlling for shared variance with ZSM
test <- lm(scale(h5c$sdo_mean) ~ scale(h5c$zs_econ_mean) + scale(h5c$zsm_mean))
summary(test)##
## Call:
## lm(formula = scale(h5c$sdo_mean) ~ scale(h5c$zs_econ_mean) +
## scale(h5c$zsm_mean))
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6923 -0.6053 -0.0340 0.6003 3.5142
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.780e-15 3.089e-02 0.000 1
## scale(h5c$zs_econ_mean) -3.487e-01 3.509e-02 -9.938 <2e-16 ***
## scale(h5c$zsm_mean) 5.174e-01 3.509e-02 14.746 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8851 on 818 degrees of freedom
## Multiple R-squared: 0.2185, Adjusted R-squared: 0.2166
## F-statistic: 114.4 on 2 and 818 DF, p-value: < 2.2e-16# ZS Econ Full Model controlling for shared variance with ZSM
test <- lm(scale(h5c$sdo_mean) ~ scale(h5c$zs_econ_mean) + scale(h5c$zsm_mean) + as.factor(h5c$sex) + scale(h5c$age) + scale(h5c$income) + scale(h5c$education) + as.factor(h5c$race) + h5c$political_orientation)
summary(test)##
## Call:
## lm(formula = scale(h5c$sdo_mean) ~ scale(h5c$zs_econ_mean) +
## scale(h5c$zsm_mean) + as.factor(h5c$sex) + scale(h5c$age) +
## scale(h5c$income) + scale(h5c$education) + as.factor(h5c$race) +
## h5c$political_orientation)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9097 -0.5262 -0.0570 0.5174 3.5859
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.49453 0.08815 -5.610 2.79e-08 ***
## scale(h5c$zs_econ_mean) -0.21006 0.03400 -6.178 1.03e-09 ***
## scale(h5c$zsm_mean) 0.38417 0.03548 10.827 < 2e-16 ***
## as.factor(h5c$sex)Male 0.23393 0.05757 4.063 5.32e-05 ***
## as.factor(h5c$sex)Other -0.07735 0.33155 -0.233 0.816
## scale(h5c$age) 0.01449 0.02958 0.490 0.624
## scale(h5c$income) 0.04283 0.03041 1.409 0.159
## scale(h5c$education) 0.01009 0.02994 0.337 0.736
## as.factor(h5c$race)East Asian 0.22444 0.16126 1.392 0.164
## as.factor(h5c$race)Indigenous -0.66370 0.80682 -0.823 0.411
## as.factor(h5c$race)Latinx 0.10512 0.13974 0.752 0.452
## as.factor(h5c$race)Middle Eastern 0.18139 0.81294 0.223 0.823
## as.factor(h5c$race)Mixed -0.04148 0.15428 -0.269 0.788
## as.factor(h5c$race)Other 0.71399 0.33813 2.112 0.035 *
## as.factor(h5c$race)White 0.04200 0.08751 0.480 0.631
## h5c$political_orientationModerate 0.40235 0.07560 5.322 1.34e-07 ***
## h5c$political_orientationRight 0.86548 0.07261 11.919 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8 on 794 degrees of freedom
## (10 observations deleted due to missingness)
## Multiple R-squared: 0.3726, Adjusted R-squared: 0.3599
## F-statistic: 29.47 on 16 and 794 DF, p-value: < 2.2e-16vif_values <- car::vif(test)
# 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."