Study 1 (Diversity Advocacy)
Anonymous
2025-08-14
Load Packages
Study 1
Confirmatory Factor Analysis
Three-Factor Model (Efficacy Scales)
ThreeFactor_model <- '
# Factor 1: Bias-Awareness Efficacy
Awareness =~ DSE_Aware_1_t2 + DSE_Aware_2_t2 + DSE_Aware_3_t2
# Factor 2: Self-Regulation Efficacy
Regulation =~ DSE_Regulate_1_t2 + DSE_Regulate_2_t2 + DSE_Regulate_3_t2 +
DSE_Regulate_4_t2 + DSE_Regulate_5_t2
# Factor 3: Intergroup-Management Efficacy
Management =~ DSE_Management_1_t2 + DSE_Management_2_t2 + DSE_Management_3_t2 +
DSE_Management_4_t2 + DSE_Management_5_t2
'
ThreeFactor_fit <- cfa(ThreeFactor_model, Study_1_CFA, estimator = "ML")
# plot CFA results
semPaths(ThreeFactor_fit, "std", weighted = FALSE, nCharNodes = 7,
shapeMan = "rectangle", sizeMan = 8, sizeMan2 = 5)
## Fit Indices:
##
## chisq df pvalue cfi srmr
## 178.794 62.000 0.000 0.957 0.042## Standardized Factor Loadings:
##
## Awrnss Regltn Mngmnt
## DSE_Aware_1_t2 0.894 0.000 0.000
## DSE_Aware_2_t2 0.866 0.000 0.000
## DSE_Aware_3_t2 0.912 0.000 0.000
## DSE_Regulate_1_t2 0.000 0.784 0.000
## DSE_Regulate_2_t2 0.000 0.847 0.000
## DSE_Regulate_3_t2 0.000 0.807 0.000
## DSE_Regulate_4_t2 0.000 0.814 0.000
## DSE_Regulate_5_t2 0.000 0.870 0.000
## DSE_Management_1_t2 0.000 0.000 0.891
## DSE_Management_2_t2 0.000 0.000 0.879
## DSE_Management_3_t2 0.000 0.000 0.912
## DSE_Management_4_t2 0.000 0.000 0.916
## DSE_Management_5_t2 0.000 0.000 0.866
##
##
## Explained Variance (R²):
##
## DSE_Aware_1_t2 DSE_Aware_2_t2 DSE_Aware_3_t2 DSE_Regulate_1_t2
## 0.799 0.750 0.832 0.614
## DSE_Regulate_2_t2 DSE_Regulate_3_t2 DSE_Regulate_4_t2 DSE_Regulate_5_t2
## 0.717 0.651 0.662 0.757
## DSE_Management_1_t2 DSE_Management_2_t2 DSE_Management_3_t2 DSE_Management_4_t2
## 0.793 0.773 0.831 0.839
## DSE_Management_5_t2
## 0.751One-Factor Model (Efficacy Scales)
OneFactor_model <- '
# One Factor: Bias-Awareness, Self-Regulation, & Intergroup-Management Efficacy
OneFactor =~ DSE_Aware_1_t2 + DSE_Aware_2_t2 + DSE_Aware_3_t2 +
DSE_Regulate_1_t2 + DSE_Regulate_2_t2 + DSE_Regulate_3_t2 +
DSE_Regulate_4_t2 + DSE_Regulate_5_t2 +
DSE_Management_1_t2 + DSE_Management_2_t2 + DSE_Management_3_t2 +
DSE_Management_4_t2 + DSE_Management_5_t2
'
OneFactor_fit <- cfa(OneFactor_model, Study_1_CFA, estimator = "ML")## Fit Indices:
##
## chisq df pvalue cfi srmr
## 783.767 65.000 0.000 0.738 0.125## Standardized Factor Loadings:
##
## OnFctr
## DSE_Aware_1_t2 0.782
## DSE_Aware_2_t2 0.799
## DSE_Aware_3_t2 0.794
## DSE_Regulate_1_t2 0.495
## DSE_Regulate_2_t2 0.580
## DSE_Regulate_3_t2 0.640
## DSE_Regulate_4_t2 0.589
## DSE_Regulate_5_t2 0.645
## DSE_Management_1_t2 0.885
## DSE_Management_2_t2 0.864
## DSE_Management_3_t2 0.871
## DSE_Management_4_t2 0.881
## DSE_Management_5_t2 0.865
##
##
## Explained Variance (R²):
##
## DSE_Aware_1_t2 DSE_Aware_2_t2 DSE_Aware_3_t2 DSE_Regulate_1_t2
## 0.611 0.639 0.631 0.245
## DSE_Regulate_2_t2 DSE_Regulate_3_t2 DSE_Regulate_4_t2 DSE_Regulate_5_t2
## 0.337 0.410 0.347 0.416
## DSE_Management_1_t2 DSE_Management_2_t2 DSE_Management_3_t2 DSE_Management_4_t2
## 0.783 0.746 0.758 0.777
## DSE_Management_5_t2
## 0.748##
##
## Three-Factor vs One-Factor Model:
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## ThreeFactor_fit 62 6180.3 6279.1 178.79
## OneFactor_fit 65 6779.3 6867.8 783.77 604.97 0.94858 3 < 2.2e-16
##
## ThreeFactor_fit
## OneFactor_fit ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Seven-Factor Measurement Model (All Seven Multi-Item Scales)
SevenFactor_model <- '
# Factor 1: Bias-Awareness Efficacy
Awareness =~ DSE_Aware_1_t2 + DSE_Aware_2_t2 + DSE_Aware_3_t2
# Factor 2: Self-Regulation Efficacy
Regulation =~ DSE_Regulate_1_t2 + DSE_Regulate_2_t2 + DSE_Regulate_3_t2 +
DSE_Regulate_4_t2 + DSE_Regulate_5_t2
# Factor 3: Intergroup-Management Efficacy
Management =~ DSE_Management_1_t2 + DSE_Management_2_t2 + DSE_Management_3_t2 +
DSE_Management_4_t2 + DSE_Management_5_t2
# Factor 4: Inclusive Leadership
InclusiveLeadership =~ Inclusive_Leader_1_t1 + Inclusive_Leader_2_t1 +
Inclusive_Leader_3_t1 + Inclusive_Leader_4_t1
# Factor 5: Pro-Diversity Attitudes
ProDiversity =~ ProDiversity_1_t1 + ProDiversity_2_t1 +
ProDiversity_3_t1 + ProDiversity_4_t1
# Factor 6: Relational Allyship
RelationalAlly =~ Relational_Allyship_1_t3 + Relational_Allyship_2_t3 +
Relational_Allyship_3_t3 + Relational_Allyship_4_t3 +
Relational_Allyship_5_t3 + Relational_Allyship_6_t3 +
Relational_Allyship_7_t3
# Factor 7: Organizational Allyship
OrgAlly =~ Org_Allyship_1_t3 + Org_Allyship_2_t3 + Org_Allyship_3_t3 +
Org_Allyship_4_t3 + Org_Allyship_5_t3 + Org_Allyship_6_t3 +
Org_Allyship_7_t3 + Org_Allyship_8_t3 + Org_Allyship_9_t3 +
'
SevenFactor_fit <- cfa(SevenFactor_model, Study_1_CFA, estimator = "ML")## Fit Indices:
##
## chisq df pvalue cfi srmr
## 1263.032 608.000 0.000 0.936 0.046## Standardized Factor Loadings:
##
## Awrnss Regltn Mngmnt InclsL PrDvrs RltnlA OrgAll
## DSE_Aware_1_t2 0.895 0.000 0.000 0.000 0.000 0.000 0.000
## DSE_Aware_2_t2 0.865 0.000 0.000 0.000 0.000 0.000 0.000
## DSE_Aware_3_t2 0.912 0.000 0.000 0.000 0.000 0.000 0.000
## DSE_Regulate_1_t2 0.000 0.791 0.000 0.000 0.000 0.000 0.000
## DSE_Regulate_2_t2 0.000 0.855 0.000 0.000 0.000 0.000 0.000
## DSE_Regulate_3_t2 0.000 0.790 0.000 0.000 0.000 0.000 0.000
## DSE_Regulate_4_t2 0.000 0.805 0.000 0.000 0.000 0.000 0.000
## DSE_Regulate_5_t2 0.000 0.878 0.000 0.000 0.000 0.000 0.000
## DSE_Management_1_t2 0.000 0.000 0.890 0.000 0.000 0.000 0.000
## DSE_Management_2_t2 0.000 0.000 0.878 0.000 0.000 0.000 0.000
## DSE_Management_3_t2 0.000 0.000 0.915 0.000 0.000 0.000 0.000
## DSE_Management_4_t2 0.000 0.000 0.919 0.000 0.000 0.000 0.000
## DSE_Management_5_t2 0.000 0.000 0.870 0.000 0.000 0.000 0.000
## Inclusive_Leader_1_t1 0.000 0.000 0.000 0.884 0.000 0.000 0.000
## Inclusive_Leader_2_t1 0.000 0.000 0.000 0.948 0.000 0.000 0.000
## Inclusive_Leader_3_t1 0.000 0.000 0.000 0.932 0.000 0.000 0.000
## Inclusive_Leader_4_t1 0.000 0.000 0.000 0.936 0.000 0.000 0.000
## ProDiversity_1_t1 0.000 0.000 0.000 0.000 0.901 0.000 0.000
## ProDiversity_2_t1 0.000 0.000 0.000 0.000 0.932 0.000 0.000
## ProDiversity_3_t1 0.000 0.000 0.000 0.000 0.864 0.000 0.000
## ProDiversity_4_t1 0.000 0.000 0.000 0.000 0.902 0.000 0.000
## Relational_Allyship_1_t3 0.000 0.000 0.000 0.000 0.000 0.879 0.000
## Relational_Allyship_2_t3 0.000 0.000 0.000 0.000 0.000 0.877 0.000
## Relational_Allyship_3_t3 0.000 0.000 0.000 0.000 0.000 0.918 0.000
## Relational_Allyship_4_t3 0.000 0.000 0.000 0.000 0.000 0.924 0.000
## Relational_Allyship_5_t3 0.000 0.000 0.000 0.000 0.000 0.907 0.000
## Relational_Allyship_6_t3 0.000 0.000 0.000 0.000 0.000 0.820 0.000
## Relational_Allyship_7_t3 0.000 0.000 0.000 0.000 0.000 0.852 0.000
## Org_Allyship_1_t3 0.000 0.000 0.000 0.000 0.000 0.000 0.929
## Org_Allyship_2_t3 0.000 0.000 0.000 0.000 0.000 0.000 0.920
## Org_Allyship_3_t3 0.000 0.000 0.000 0.000 0.000 0.000 0.933
## Org_Allyship_4_t3 0.000 0.000 0.000 0.000 0.000 0.000 0.917
## Org_Allyship_5_t3 0.000 0.000 0.000 0.000 0.000 0.000 0.930
## Org_Allyship_6_t3 0.000 0.000 0.000 0.000 0.000 0.000 0.930
## Org_Allyship_7_t3 0.000 0.000 0.000 0.000 0.000 0.000 0.918
## Org_Allyship_8_t3 0.000 0.000 0.000 0.000 0.000 0.000 0.921
## Org_Allyship_9_t3 0.000 0.000 0.000 0.000 0.000 0.000 0.934
##
##
## Explained Variance (R²):
##
## DSE_Aware_1_t2 DSE_Aware_2_t2 DSE_Aware_3_t2
## 0.801 0.748 0.831
## DSE_Regulate_1_t2 DSE_Regulate_2_t2 DSE_Regulate_3_t2
## 0.625 0.732 0.624
## DSE_Regulate_4_t2 DSE_Regulate_5_t2 DSE_Management_1_t2
## 0.648 0.771 0.792
## DSE_Management_2_t2 DSE_Management_3_t2 DSE_Management_4_t2
## 0.770 0.837 0.844
## DSE_Management_5_t2 Inclusive_Leader_1_t1 Inclusive_Leader_2_t1
## 0.758 0.782 0.899
## Inclusive_Leader_3_t1 Inclusive_Leader_4_t1 ProDiversity_1_t1
## 0.869 0.875 0.812
## ProDiversity_2_t1 ProDiversity_3_t1 ProDiversity_4_t1
## 0.868 0.746 0.813
## Relational_Allyship_1_t3 Relational_Allyship_2_t3 Relational_Allyship_3_t3
## 0.773 0.769 0.843
## Relational_Allyship_4_t3 Relational_Allyship_5_t3 Relational_Allyship_6_t3
## 0.853 0.823 0.672
## Relational_Allyship_7_t3 Org_Allyship_1_t3 Org_Allyship_2_t3
## 0.725 0.864 0.846
## Org_Allyship_3_t3 Org_Allyship_4_t3 Org_Allyship_5_t3
## 0.870 0.841 0.865
## Org_Allyship_6_t3 Org_Allyship_7_t3 Org_Allyship_8_t3
## 0.865 0.842 0.848
## Org_Allyship_9_t3
## 0.872Reliability Estimates (Cronbach Alpha) - Study 1 Measures
# Reliability estimates for self-efficacy scales
awareness_alpha <- alpha(Study_1_CFA[, c("DSE_Aware_1_t2", "DSE_Aware_2_t2", "DSE_Aware_3_t2")])
regulation_alpha <- alpha(Study_1_CFA[, c("DSE_Regulate_1_t2", "DSE_Regulate_2_t2", "DSE_Regulate_3_t2", "DSE_Regulate_4_t2", "DSE_Regulate_5_t2")])
management_alpha <- alpha(Study_1_CFA[, c("DSE_Management_1_t2", "DSE_Management_2_t2", "DSE_Management_3_t2", "DSE_Management_4_t2", "DSE_Management_5_t2")])
cat("Alpha for bias-awareness efficacy: ", awareness_alpha$total$raw_alpha, "\n",
"Alpha for self-regulation efficacy: ", regulation_alpha$total$raw_alpha, "\n",
"Alpha for intergroup-management efficacy:", management_alpha$total$raw_alpha, "\n") ## Alpha for bias-awareness efficacy: 0.9173952
## Alpha for self-regulation efficacy: 0.9139933
## Alpha for intergroup-management efficacy: 0.9512536# Reliability estimates for ally work scales
rel_ally_alpha <- alpha(Study_1_CFA[, c("Relational_Allyship_1_t3", "Relational_Allyship_2_t3", "Relational_Allyship_3_t3", "Relational_Allyship_4_t3", "Relational_Allyship_5_t3", "Relational_Allyship_6_t3", "Relational_Allyship_7_t3")])
org_ally_alpha <- alpha(Study_1_CFA[, c("Org_Allyship_1_t3", "Org_Allyship_2_t3", "Org_Allyship_3_t3", "Org_Allyship_4_t3", "Org_Allyship_5_t3", "Org_Allyship_6_t3", "Org_Allyship_7_t3", "Org_Allyship_8_t3", "Org_Allyship_9_t3")])
cat("Alpha for relational ally work:", rel_ally_alpha$total$raw_alpha, "\n",
"Alpha for organizational ally work:", org_ally_alpha$total$raw_alpha, "\n")## Alpha for relational ally work: 0.9608815
## Alpha for organizational ally work: 0.9817662# Reliability estimates for leader diversity advocacy and pro-diversity
incl_leader_alpha <- alpha(Study_1_CFA[, c("Inclusive_Leader_1_t1", "Inclusive_Leader_2_t1", "Inclusive_Leader_3_t1", "Inclusive_Leader_4_t1")])
prodiversity_alpha <- alpha(Study_1_CFA[, c("ProDiversity_1_t1", "ProDiversity_2_t1", "ProDiversity_3_t1", "ProDiversity_4_t1")])
cat("Alpha for leader diversity advocacy:", incl_leader_alpha$total$raw_alpha, "\n",
"Alpha for pro-diversity attitudes:", prodiversity_alpha$total$raw_alpha, "\n")## Alpha for leader diversity advocacy: 0.9596095
## Alpha for pro-diversity attitudes: 0.9409475Table 1: Descriptives & Correlations
##
##
## Means, standard deviations, and correlations with confidence intervals
##
##
## Variable M SD 1 2 3 4
## 1. Male 0.59 0.49
##
## 2. White 0.71 0.46 -.06
## [-.19, .07]
##
## 3. Ideology 3.31 1.88 .15* .10
## [.02, .28] [-.03, .23]
##
## 4. LdrAdvocacy 3.27 1.23 -.11 -.11 -.06
## [-.24, .02] [-.24, .02] [-.19, .07]
##
## 5. PDB 4.32 0.98 -.24** -.08 -.48** .45**
## [-.36, -.12] [-.20, .06] [-.57, -.37] [.34, .55]
##
## 6. AWARE 3.69 1.08 -.14* .00 -.23** .38**
## [-.26, -.01] [-.13, .13] [-.35, -.10] [.26, .48]
##
## 7. REGULATE 4.28 0.77 -.15* .08 -.16* .29**
## [-.27, -.02] [-.05, .21] [-.28, -.03] [.17, .41]
##
## 8. MANAGE 3.41 1.20 -.12 -.03 -.19** .51**
## [-.24, .01] [-.16, .11] [-.31, -.06] [.41, .61]
##
## 9. OrgAlly 2.56 1.28 -.09 -.03 -.12 .56**
## [-.22, .04] [-.17, .10] [-.25, .01] [.46, .64]
##
## 10. RelAlly 3.55 0.95 -.16* -.03 -.27** .55**
## [-.29, -.03] [-.16, .10] [-.38, -.14] [.45, .63]
##
## 5 6 7 8 9
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## .41**
## [.30, .51]
##
## .37** .58**
## [.26, .48] [.49, .66]
##
## .41** .77** .57**
## [.30, .52] [.72, .82] [.48, .65]
##
## .41** .48** .25** .59**
## [.30, .52] [.38, .58] [.12, .37] [.50, .67]
##
## .61** .51** .51** .54** .68**
## [.51, .68] [.41, .60] [.41, .60] [.44, .63] [.61, .75]
##
##
## 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.
## Grand-Mean Center Predictor Variables
Table 2 (Step 1, A-Path): Leader Diversity Advocacy and Efficacy Beliefs
###effects of leader diversity advocacy on employee efficacy beliefs
model.AWARE <- lm(AWARE ~ PDB_c + LdrAdvocacy_c, Study1_vars)
model.REGULATE <- lm(REGULATE ~ PDB_c + LdrAdvocacy_c, Study1_vars)
model.MANAGE <- lm(MANAGE ~ PDB_c + LdrAdvocacy_c, Study1_vars)
tab_model(model.AWARE, model.REGULATE, model.MANAGE,
show.p = TRUE,
show.se = TRUE,
show.stat = TRUE,
digits = 3,
title = "Leader Diversity Advocacy and Efficacy Beliefs")| Â | AWARE | REGULATE | MANAGE | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Estimates | std. Error | CI | Statistic | p | Estimates | std. Error | CI | Statistic | p | Estimates | std. Error | CI | Statistic | p |
| (Intercept) | 3.690 | 0.064 | 3.564 – 3.817 | 57.379 | <0.001 | 4.278 | 0.047 | 4.184 – 4.371 | 90.271 | <0.001 | 3.409 | 0.067 | 3.277 – 3.541 | 50.733 | <0.001 |
| PDB c | 0.335 | 0.074 | 0.189 – 0.481 | 4.528 | <0.001 | 0.240 | 0.055 | 0.133 – 0.348 | 4.405 | <0.001 | 0.281 | 0.077 | 0.129 – 0.433 | 3.637 | <0.001 |
| LdrAdvocacy c | 0.212 | 0.059 | 0.096 – 0.328 | 3.611 | <0.001 | 0.099 | 0.043 | 0.014 – 0.184 | 2.284 | 0.023 | 0.404 | 0.061 | 0.283 – 0.524 | 6.578 | <0.001 |
| Observations | 224 | 224 | 224 | ||||||||||||
| R2 / R2 adjusted | 0.215 / 0.208 | 0.160 / 0.153 | 0.307 / 0.300 | ||||||||||||
Table 2 (B-Path): Efficacy Beliefs and Ally Work
##effects of efficacy beliefs on employee diversity effort
model.ALLY_R <- lm(RelAlly ~ Ideology_c + PDB_c + LdrAdvocacy_c + AWARE + REGULATE, Study1_vars)
model.ALLY_O <- lm(OrgAlly ~ Ideology_c + PDB_c + LdrAdvocacy_c + AWARE + MANAGE, Study1_vars)
tab_model(model.ALLY_R, model.ALLY_O,
show.p = TRUE,
show.se = TRUE,
show.stat = TRUE,
digits = 3,
title = "Efficacy Beliefs and Allyship Behavior") | Â | RelAlly | OrgAlly | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Estimates | std. Error | CI | Statistic | p | Estimates | std. Error | CI | Statistic | p |
| (Intercept) | 1.913 | 0.270 | 1.381 – 2.445 | 7.085 | <0.001 | 1.071 | 0.263 | 0.552 – 1.590 | 4.069 | <0.001 |
| Ideology c | -0.013 | 0.027 | -0.066 – 0.040 | -0.469 | 0.640 | 0.024 | 0.040 | -0.054 – 0.103 | 0.613 | 0.541 |
| PDB c | 0.318 | 0.060 | 0.200 – 0.436 | 5.329 | <0.001 | 0.165 | 0.088 | -0.007 – 0.338 | 1.890 | 0.060 |
| LdrAdvocacy c | 0.215 | 0.042 | 0.133 – 0.297 | 5.183 | <0.001 | 0.318 | 0.066 | 0.188 – 0.447 | 4.834 | <0.001 |
| AWARE | 0.115 | 0.052 | 0.012 – 0.217 | 2.204 | 0.029 | 0.077 | 0.096 | -0.112 – 0.265 | 0.801 | 0.424 |
| REGULATE | 0.281 | 0.070 | 0.143 – 0.420 | 4.000 | <0.001 | |||||
| MANAGE | 0.358 | 0.092 | 0.178 – 0.538 | 3.911 | <0.001 | |||||
| Observations | 224 | 224 | ||||||||
| R2 / R2 adjusted | 0.542 / 0.532 | 0.447 / 0.435 | ||||||||
Hypothesis 1a: Mediation Analysis
# Extract coefficients
a_est <- coef(model.AWARE)["LdrAdvocacy_c"] # Effect of X on M (a-path)
b_est <- coef(model.ALLY_R)["AWARE"] # Effect of M on Y (b-path)
# Extract standard errors
a_se <- summary(model.AWARE)$coefficients["LdrAdvocacy_c", "Std. Error"]
b_se <- summary(model.ALLY_R)$coefficients["AWARE", "Std. Error"]
# Compute Monte Carlo confidence interval
mc_ci <- medci(mu.x = a_est, mu.y = b_est, se.x = a_se, se.y = b_se,
rho = 0, alpha = .05, sims = 10000, method = "parametric")
# Coefficients for Indirect Effect
cat("Indirect effect estimate:", mc_ci$Estimate, "\n")## Indirect effect estimate: 0.02430963cat("Indirect effect standard error:", mc_ci$SE, "\n")## Indirect effect standard error: 0.01328022# Monte Carlo CI: Advocacy -> Bias-Awareness -> Relational Allyship
cat("Monte Carlo 95% CI: [", mc_ci$`95% CI`[1], ",", mc_ci$`95% CI`[2], "]\n")## Monte Carlo 95% CI: [ 0.002251457 , 0.05389142 ]Hypothesis 1b: Mediation Analysis (Not Supported)
# Extract coefficients
a_est <- coef(model.AWARE)["LdrAdvocacy_c"] # Effect of X on M (a-path)
b_est <- coef(model.ALLY_O)["AWARE"] # Effect of M on Y (b-path)
# Extract standard errors
a_se <- summary(model.AWARE)$coefficients["LdrAdvocacy_c", "Std. Error"]
b_se <- summary(model.ALLY_O)$coefficients["AWARE", "Std. Error"]
# Compute Monte Carlo confidence interval
mc_ci <- medci(mu.x = a_est, mu.y = b_est, se.x = a_se, se.y = b_se,
rho = 0, alpha = .10, sims = 10000, method = "parametric")
# Coefficients for Indirect Effect
cat("Indirect effect estimate:", mc_ci$Estimate, "\n")## Indirect effect estimate: 0.01625865cat("Indirect effect standard error:", mc_ci$SE, "\n")## Indirect effect standard error: 0.02154227# Print Monte Carlo CI: Advocacy -> Bias-Awareness -> Relational Allyship
cat("Monte Carlo 90% CI: [", mc_ci$`90% CI`[1], ",", mc_ci$`90% CI`[2], "]\n")## Monte Carlo 90% CI: [ -0.01687366 , 0.05350855 ]Hypothesis 2: Mediation Analysis
# Extract coefficients
a_est <- coef(model.REGULATE)["LdrAdvocacy_c"] # Effect of X on M (a-path)
b_est <- coef(model.ALLY_R)["REGULATE"] # Effect of M on Y (b-path)
# Extract standard errors
a_se <- summary(model.REGULATE)$coefficients["LdrAdvocacy_c", "Std. Error"]
b_se <- summary(model.ALLY_R)$coefficients["REGULATE", "Std. Error"]
# Compute Monte Carlo confidence interval
mc_ci <- medci(mu.x = a_est, mu.y = b_est, se.x = a_se, se.y = b_se,
rho = 0, alpha = .05, sims = 10000, method = "parametric")
# Coefficients for Indirect Effect
cat("Indirect effect estimate:", mc_ci$Estimate, "\n")## Indirect effect estimate: 0.02780824cat("Indirect effect standard error:", mc_ci$SE, "\n")## Indirect effect standard error: 0.01434579# Print Monte Carlo CI: Advocacy -> Self-Regulation -> Relational Allyship
cat("Monte Carlo 95% CI: [", mc_ci$`95% CI`[1], ",", mc_ci$`95% CI`[2], "]\n")## Monte Carlo 95% CI: [ 0.003482145 , 0.05941749 ]Hypothesis 3: Mediation Analysis
# Extract coefficients
a_est <- coef(model.MANAGE)["LdrAdvocacy_c"] # Effect of X on M (a-path)
b_est <- coef(model.ALLY_O)["MANAGE"] # Effect of M on Y (b-path)
# Extract standard errors
a_se <- summary(model.MANAGE)$coefficients["LdrAdvocacy_c", "Std. Error"]
b_se <- summary(model.ALLY_O)$coefficients["MANAGE", "Std. Error"]
# Compute Monte Carlo confidence interval
mc_ci <- medci(mu.x = a_est, mu.y = b_est, se.x = a_se, se.y = b_se,
rho = 0, alpha = .01, sims = 10000, method = "parametric")
# Coefficients for Indirect Effect
cat("Indirect effect estimate:", mc_ci$Estimate, "\n")## Indirect effect estimate: 0.1444608cat("Indirect effect standard error:", mc_ci$SE, "\n")## Indirect effect standard error: 0.04333847# Print Monte Carlo CI: Advocacy -> Diversity Management -> Organizational Allyship
cat("Monte Carlo 99% CI: [", mc_ci$`99% CI`[1], ",", mc_ci$`99% CI`[2], "]\n")## Monte Carlo 99% CI: [ 0.04570033 , 0.2700162 ]Table 2 (Step 2, A-Path): Moderation Analyses
Leader Diversity Advocacy & Pro-Diversity Attitudes
###moderation
model_AWARE <- lm(AWARE ~ LdrAdvocacy_c*PDB_c, Study1_vars)
model_REGULATE <- lm(REGULATE ~ LdrAdvocacy_c*PDB_c, Study1_vars)
model_MANAGE <- lm(MANAGE ~ LdrAdvocacy_c*PDB_c, Study1_vars)
tab_model(model_AWARE, model_REGULATE, model_MANAGE,
show.p = TRUE,
show.se = TRUE,
show.stat = TRUE,
digits = 3,
title = "Regression Results (Interaction)") | Â | AWARE | REGULATE | MANAGE | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Estimates | std. Error | CI | Statistic | p | Estimates | std. Error | CI | Statistic | p | Estimates | std. Error | CI | Statistic | p |
| (Intercept) | 3.587 | 0.070 | 3.449 – 3.724 | 51.308 | <0.001 | 4.233 | 0.052 | 4.130 – 4.336 | 80.808 | <0.001 | 3.294 | 0.073 | 3.151 – 3.437 | 45.248 | <0.001 |
| LdrAdvocacy c | 0.172 | 0.059 | 0.057 – 0.288 | 2.941 | 0.004 | 0.082 | 0.044 | -0.005 – 0.168 | 1.861 | 0.064 | 0.360 | 0.061 | 0.239 – 0.480 | 5.896 | <0.001 |
| PDB c | 0.531 | 0.093 | 0.349 – 0.714 | 5.739 | <0.001 | 0.325 | 0.069 | 0.188 – 0.461 | 4.681 | <0.001 | 0.498 | 0.096 | 0.308 – 0.688 | 5.167 | <0.001 |
| LdrAdvocacy c × PDB c | 0.194 | 0.057 | 0.081 – 0.307 | 3.394 | 0.001 | 0.084 | 0.043 | -0.001 – 0.168 | 1.952 | 0.052 | 0.215 | 0.060 | 0.097 – 0.332 | 3.604 | <0.001 |
| Observations | 224 | 224 | 224 | ||||||||||||
| R2 / R2 adjusted | 0.254 / 0.244 | 0.174 / 0.163 | 0.345 / 0.336 | ||||||||||||
# Compare Models: Significant change in R²?
anova(model.AWARE, model_AWARE)## Analysis of Variance Table
##
## Model 1: AWARE ~ PDB_c + LdrAdvocacy_c
## Model 2: AWARE ~ LdrAdvocacy_c * PDB_c
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 221 204.78
## 2 220 194.60 1 10.19 11.52 0.0008166 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1anova(model.REGULATE, model_REGULATE)## Analysis of Variance Table
##
## Model 1: REGULATE ~ PDB_c + LdrAdvocacy_c
## Model 2: REGULATE ~ LdrAdvocacy_c * PDB_c
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 221 111.16
## 2 220 109.27 1 1.8925 3.8102 0.05221 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1anova(model.MANAGE, model_MANAGE)## Analysis of Variance Table
##
## Model 1: MANAGE ~ PDB_c + LdrAdvocacy_c
## Model 2: MANAGE ~ LdrAdvocacy_c * PDB_c
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 221 223.51
## 2 220 211.05 1 12.46 12.989 0.0003876 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Simple Slopes Analyses
sim_slopes(model_AWARE, pred = "LdrAdvocacy_c", modx = "PDB_c", modx.values = c(-.98, 0, .98))## JOHNSON-NEYMAN INTERVAL
##
## When PDB_c is OUTSIDE the interval [-2.64, -0.25], the slope of
## LdrAdvocacy_c is p < .05.
##
## Note: The range of observed values of PDB_c is [-3.32, 0.68]
##
## SIMPLE SLOPES ANALYSIS
##
## Slope of LdrAdvocacy_c when PDB_c = -0.98:
##
## Est. S.E. t val. p
## ------- ------ -------- ------
## -0.02 0.09 -0.20 0.84
##
## Slope of LdrAdvocacy_c when PDB_c = 0.00:
##
## Est. S.E. t val. p
## ------ ------ -------- ------
## 0.17 0.06 2.94 0.00
##
## Slope of LdrAdvocacy_c when PDB_c = 0.98:
##
## Est. S.E. t val. p
## ------ ------ -------- ------
## 0.36 0.07 5.00 0.00sim_slopes(model_REGULATE, pred = "LdrAdvocacy_c", modx = "PDB_c", modx.values = c(-.98, 0, .98))## JOHNSON-NEYMAN INTERVAL
##
## When PDB_c is INSIDE the interval [0.05, 122.21], the slope of
## LdrAdvocacy_c is p < .05.
##
## Note: The range of observed values of PDB_c is [-3.32, 0.68]
##
## SIMPLE SLOPES ANALYSIS
##
## Slope of LdrAdvocacy_c when PDB_c = -0.98:
##
## Est. S.E. t val. p
## ------- ------ -------- ------
## -0.00 0.07 -0.00 1.00
##
## Slope of LdrAdvocacy_c when PDB_c = 0.00:
##
## Est. S.E. t val. p
## ------ ------ -------- ------
## 0.08 0.04 1.86 0.06
##
## Slope of LdrAdvocacy_c when PDB_c = 0.98:
##
## Est. S.E. t val. p
## ------ ------ -------- ------
## 0.16 0.05 3.01 0.00sim_slopes(model_MANAGE, pred = "LdrAdvocacy_c", modx = "PDB_c", modx.values = c(-.98, 0, .98))## JOHNSON-NEYMAN INTERVAL
##
## When PDB_c is OUTSIDE the interval [-4.08, -0.87], the slope of
## LdrAdvocacy_c is p < .05.
##
## Note: The range of observed values of PDB_c is [-3.32, 0.68]
##
## SIMPLE SLOPES ANALYSIS
##
## Slope of LdrAdvocacy_c when PDB_c = -0.98:
##
## Est. S.E. t val. p
## ------ ------ -------- ------
## 0.15 0.09 1.61 0.11
##
## Slope of LdrAdvocacy_c when PDB_c = 0.00:
##
## Est. S.E. t val. p
## ------ ------ -------- ------
## 0.36 0.06 5.90 0.00
##
## Slope of LdrAdvocacy_c when PDB_c = 0.98:
##
## Est. S.E. t val. p
## ------ ------ -------- ------
## 0.57 0.08 7.55 0.00## Warning: 0.97508025323059 is outside the observed range of PDB_c
## 0.97508025323059 is outside the observed range of PDB_c
## 0.97508025323059 is outside the observed range of PDB_c
Figures 1 & 2: Create J-N interaction plots
# Generate Johnson-Neyman plots and add custom titles
## Figure 1
plot1 <- johnson_neyman(model_AWARE, pred = "LdrAdvocacy_c", modx = "PDB_c", plot = TRUE)$plot +
labs(x = "Leader Diversity Advocacy", y = "Bias-Awareness Efficacy",title = NULL)
## Not significant at .05 alpha level
plot2 <- johnson_neyman(model_REGULATE, pred = "LdrAdvocacy_c", modx = "PDB_c", plot = TRUE)$plot + labs(x = "Leader Diversity Advocacy", y = "Self-Regulation Efficacy",title = NULL)
## Figure 2
plot3 <- johnson_neyman(model_MANAGE, pred = "LdrAdvocacy_c", modx = "PDB_c", plot = TRUE)$plot +
labs(x = "Leader Diversity Advocacy", y = "Intergroup-Management Efficacy",title = NULL)
# Arrange in 2×2 grid (with one blank space if only 3 plots)
gridExtra::grid.arrange(plot1, plot2, plot3, ncol = 2)
Hypothesis 4a: Moderated Mediation (Bias-Awareness Efficacy and Relational Ally Work)
# Extract coefficients
a_int <- coef(model_AWARE)["LdrAdvocacy_c:PDB_c"] # Effect of XW on M (a-path)
b_est <- coef(model.ALLY_R)["AWARE"] # Effect of M on Y (b-path)
# Extract standard errors
a_int_se <- summary(model_AWARE)$coefficients["LdrAdvocacy_c:PDB_c", "Std. Error"]
b_se <- summary(model.ALLY_R)$coefficients["AWARE", "Std. Error"]
# Compute Monte Carlo confidence interval
mc_ci <- medci(mu.x = a_int, mu.y = b_est, se.x = a_int_se, se.y = b_se,
rho = 0, alpha = .05, sims = 10000, method = "parametric")##
## --- Index of Moderated Mediation ---## Estimate: 0.02224868## Standard error: 0.01240032## Monte Carlo 95% CI: [ 0.001943587 , 0.05005854 ]##
## --- Conditional Indirect Effects ---## At LOW PDB (-1 SD):## Indirect effect estimate: -0.002## Standard error (LOW PDB): 0.01## Monte Carlo 90% CI: [ -0.02 , 0.014 ]## At HIGH PDB (+1 SD):## Indirect effect estimate: 0.042## Standard error (HIGH PDB): 0.021## Monte Carlo 95% CI: [ 0.004 , 0.088 ]Hypothesis 4b: Moderated Mediation (Self-Regulation Efficacy and Relational Ally Work)
# Extract coefficients
a_int <- coef(model_REGULATE)["LdrAdvocacy_c:PDB_c"] # Effect of XW on M (a-path)
b_est <- coef(model.ALLY_R)["REGULATE"] # Effect of M on Y (b-path)
# Extract standard errors
a_int_se <- summary(model_REGULATE)$coefficients["LdrAdvocacy_c:PDB_c", "Std. Error"]
b_se <- summary(model.ALLY_R)$coefficients["REGULATE", "Std. Error"]
# Compute Monte Carlo confidence interval (alpha = .10)
mc_ci <- medci(mu.x = a_int, mu.y = b_est, se.x = a_int_se, se.y = b_se,
rho = 0, alpha = .10, sims = 10000, method = "parametric")##
## --- Index of Moderated Mediation ---## Estimate: 0.02353364## Standard error: 0.01374995## Monte Carlo 90% CI: [ 0.00331021 , 0.04793587 ]##
## --- Conditional Indirect Effects ---## At LOW PDB (-1 SD):## Indirect effect estimate: -8e-05## Standard error (LOW PDB): 0.018## Monte Carlo 90% CI: [ -0.029 , 0.029 ]## At HIGH PDB (+1 SD):## Indirect effect estimate: 0.046## Standard error (HIGH PDB): 0.021## Monte Carlo 95% CI: [ 0.011 , 0.092 ]Hypothesis 5a: Moderated Mediation (Bias-Awareness Efficacy and Organizational Ally Work)
# Extract coefficients
a_int <- coef(model_AWARE)["LdrAdvocacy_c:PDB_c"] # Effect of XW on M (a-path)
b_est <- coef(model.ALLY_O)["AWARE"] # Effect of M on Y (b-path)
# Extract standard errors
a_int_se <- summary(model_AWARE)$coefficients["LdrAdvocacy_c:PDB_c", "Std. Error"]
b_se <- summary(model.ALLY_O)$coefficients["AWARE", "Std. Error"]
# Compute Monte Carlo confidence interval
mc_ci <- medci(mu.x = a_int, mu.y = b_est, se.x = a_int_se, se.y = b_se,
rho = 0, alpha = .10, sims = 10000, method = "parametric")##
## --- Index of Moderated Mediation ---## Estimate: 0.01488025## Standard error: 0.01986081## Monte Carlo 90% CI: [ -0.01542985 , 0.04939741 ]Hypothesis 5b: Moderated Mediation (Intergroup-Management Efficacy and Organizational Ally Work)
# Extract coefficients
a_int <- coef(model_MANAGE)["LdrAdvocacy_c:PDB_c"] # Effect of XW on M (a-path)
b_est <- coef(model.ALLY_O)["MANAGE"] # Effect of M on Y (b-path)
# Extract standard errors
a_int_se <- summary(model_MANAGE)$coefficients["LdrAdvocacy_c:PDB_c", "Std. Error"]
b_se <- summary(model.ALLY_O)$coefficients["MANAGE", "Std. Error"]
# Compute Monte Carlo confidence interval
mc_ci <- medci(mu.x = a_int, mu.y = b_est, se.x = a_int_se, se.y = b_se,
rho = 0, alpha = .01, sims = 10000, method = "parametric")##
## --- Index of Moderated Mediation ---## Estimate: 0.07682129## Standard error: 0.02949443## Monte Carlo 99% CI: [ 0.01593752 , 0.1671988 ]##
## --- Conditional Indirect Effects ---## At LOW PDB (-1 SD):## Indirect effect estimate: 0.05342## Standard error (LOW PDB): 0.03405## Monte Carlo 90% CI: [ 0.003 , 0.114 ]## At HIGH PDB (+1 SD):## Indirect effect estimate: 0.204## Standard error (HIGH PDB): 0.06077## Monte Carlo 99% CI: [ 0.065 , 0.38 ]