Study 2 (Diversity Advocacy)
Anonymous
2025-09-04
Load Packages
Study 2
Confirmatory Factor Analysis
Two-Factor Model (Efficacy Scales)
TwoFactor_model <- '
# Factor 1: Bias-Awareness Efficacy
Awareness =~ DSE_Aware_1 + DSE_Aware_2 + DSE_Aware_3
# Factor 2: Intergroup-Management Efficacy
Management =~ DSE_Management_1 + DSE_Management_2 + DSE_Management_3 +
DSE_Management_4 + DSE_Management_5
'
TwoFactor_fit <- cfa(TwoFactor_model, Study_2_CFA, estimator = "ML")
# plot CFA results
semPaths(TwoFactor_fit, "std", weighted = FALSE, nCharNodes = 7,
shapeMan = "rectangle", sizeMan = 8, sizeMan2 = 5)
## Fit Indices:
##
## chisq df pvalue cfi srmr
## 63.101 19.000 0.000 0.957 0.036## Standardized Factor Loadings:
##
## Awrnss Mngmnt
## DSE_Aware_1 0.816 0.000
## DSE_Aware_2 0.785 0.000
## DSE_Aware_3 0.742 0.000
## DSE_Management_1 0.000 0.827
## DSE_Management_2 0.000 0.802
## DSE_Management_3 0.000 0.808
## DSE_Management_4 0.000 0.800
## DSE_Management_5 0.000 0.783
##
##
## Explained Variance (R²):
##
## DSE_Aware_1 DSE_Aware_2 DSE_Aware_3 DSE_Management_1
## 0.666 0.616 0.551 0.684
## DSE_Management_2 DSE_Management_3 DSE_Management_4 DSE_Management_5
## 0.643 0.652 0.640 0.613One-Factor Model (Efficacy Scales)
OneFactor_model <- '
# One Factor: Bias-Awareness & Intergroup-Management Efficacy
OneFactor =~ DSE_Aware_1 + DSE_Aware_2 + DSE_Aware_3 +
DSE_Management_1 + DSE_Management_2 + DSE_Management_3 +
DSE_Management_4 + DSE_Management_5
'
OneFactor_fit <- cfa(OneFactor_model, Study_2_CFA, estimator = "ML")## Fit Indices:
##
## chisq df pvalue cfi srmr
## 214.570 20.000 0.000 0.809 0.108## Standardized Factor Loadings:
##
## OnFctr
## DSE_Aware_1 0.545
## DSE_Aware_2 0.510
## DSE_Aware_3 0.512
## DSE_Management_1 0.825
## DSE_Management_2 0.787
## DSE_Management_3 0.793
## DSE_Management_4 0.794
## DSE_Management_5 0.785
##
##
## Explained Variance (R²):
##
## DSE_Aware_1 DSE_Aware_2 DSE_Aware_3 DSE_Management_1
## 0.297 0.260 0.262 0.681
## DSE_Management_2 DSE_Management_3 DSE_Management_4 DSE_Management_5
## 0.620 0.629 0.630 0.616##
##
## Three-Factor vs One-Factor Model:
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## TwoFactor_fit 19 4372.8 4431.3 63.101
## OneFactor_fit 20 4522.3 4577.3 214.570 151.47 0.80883 1 < 2.2e-16
##
## TwoFactor_fit
## OneFactor_fit ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Five-Factor Measurement Model (All Five Multi-Item Scales)
FiveFactor_model <- '
# Factor 1: Bias-Awareness Efficacy
Awareness =~ DSE_Aware_1 + DSE_Aware_2 + DSE_Aware_3
# Factor 2: Intergroup-Management Efficacy
Management =~ DSE_Management_1 + DSE_Management_2 + DSE_Management_3 +
DSE_Management_4 + DSE_Management_5
# Factor 3: Leader Diversity Advocacy
InclusiveLeadership =~ Inclusive_Leader_1 + Inclusive_Leader_2 +
Inclusive_Leader_3 + Inclusive_Leader_4
# Factor 4: Pro-Diversity Attitudes
ProDiversity =~ ProDiversity_1 + ProDiversity_2 +
ProDiversity_3 + ProDiversity_4
# Factor 5: Organizational Allyship
OrgAlly =~ Org_Allyship_1 + Org_Allyship_2 + Org_Allyship_3 +
Org_Allyship_4 + Org_Allyship_5 + Org_Allyship_6 +
Org_Allyship_7 + Org_Allyship_8 + Org_Allyship_9
'
FiveFactor_fit <- cfa(FiveFactor_model, Study_2_CFA, estimator = "ML")## Fit Indices:
##
## chisq df pvalue cfi srmr
## 528.693 265.000 0.000 0.940 0.046## Standardized Factor Loadings:
##
## Awrnss Mngmnt InclsL PrDvrs OrgAll
## DSE_Aware_1 0.817 0.000 0.000 0.000 0.000
## DSE_Aware_2 0.795 0.000 0.000 0.000 0.000
## DSE_Aware_3 0.743 0.000 0.000 0.000 0.000
## DSE_Management_1 0.000 0.821 0.000 0.000 0.000
## DSE_Management_2 0.000 0.805 0.000 0.000 0.000
## DSE_Management_3 0.000 0.812 0.000 0.000 0.000
## DSE_Management_4 0.000 0.809 0.000 0.000 0.000
## DSE_Management_5 0.000 0.784 0.000 0.000 0.000
## Inclusive_Leader_1 0.000 0.000 0.822 0.000 0.000
## Inclusive_Leader_2 0.000 0.000 0.872 0.000 0.000
## Inclusive_Leader_3 0.000 0.000 0.851 0.000 0.000
## Inclusive_Leader_4 0.000 0.000 0.901 0.000 0.000
## ProDiversity_1 0.000 0.000 0.000 0.882 0.000
## ProDiversity_2 0.000 0.000 0.000 0.872 0.000
## ProDiversity_3 0.000 0.000 0.000 0.822 0.000
## ProDiversity_4 0.000 0.000 0.000 0.830 0.000
## Org_Allyship_1 0.000 0.000 0.000 0.000 0.690
## Org_Allyship_2 0.000 0.000 0.000 0.000 0.838
## Org_Allyship_3 0.000 0.000 0.000 0.000 0.797
## Org_Allyship_4 0.000 0.000 0.000 0.000 0.819
## Org_Allyship_5 0.000 0.000 0.000 0.000 0.827
## Org_Allyship_6 0.000 0.000 0.000 0.000 0.871
## Org_Allyship_7 0.000 0.000 0.000 0.000 0.832
## Org_Allyship_8 0.000 0.000 0.000 0.000 0.871
## Org_Allyship_9 0.000 0.000 0.000 0.000 0.872
##
##
## Explained Variance (R²):
##
## DSE_Aware_1 DSE_Aware_2 DSE_Aware_3 DSE_Management_1
## 0.667 0.632 0.551 0.674
## DSE_Management_2 DSE_Management_3 DSE_Management_4 DSE_Management_5
## 0.649 0.660 0.654 0.614
## Inclusive_Leader_1 Inclusive_Leader_2 Inclusive_Leader_3 Inclusive_Leader_4
## 0.675 0.760 0.724 0.811
## ProDiversity_1 ProDiversity_2 ProDiversity_3 ProDiversity_4
## 0.779 0.760 0.675 0.689
## Org_Allyship_1 Org_Allyship_2 Org_Allyship_3 Org_Allyship_4
## 0.476 0.702 0.635 0.670
## Org_Allyship_5 Org_Allyship_6 Org_Allyship_7 Org_Allyship_8
## 0.684 0.759 0.692 0.759
## Org_Allyship_9
## 0.761Four-Factor Alternative Model #1 (Combine predictors into single factor)
FourFactor_model <- '
# Factor 1: Bias-Awareness Efficacy
Awareness =~ DSE_Aware_1 + DSE_Aware_2 + DSE_Aware_3
# Factor 2: Intergroup-Management Efficacy
Management =~ DSE_Management_1 + DSE_Management_2 + DSE_Management_3 +
DSE_Management_4 + DSE_Management_5
# Factor 3: Leader Diversity Advocacy & Pro-Diversity Attitudes
Predictors =~ Inclusive_Leader_1 + Inclusive_Leader_2 +
Inclusive_Leader_3 + Inclusive_Leader_4 +
ProDiversity_1 + ProDiversity_2 +
ProDiversity_3 + ProDiversity_4
# Factor 4: Organizational Allyship
OrgAlly =~ Org_Allyship_1 + Org_Allyship_2 + Org_Allyship_3 +
Org_Allyship_4 + Org_Allyship_5 + Org_Allyship_6 +
Org_Allyship_7 + Org_Allyship_8 + Org_Allyship_9
'
FourFactor_fit <- cfa(FourFactor_model, Study_2_CFA, estimator = "ML")Three-Factor Alternative Model #2 (Combine predictors and outcome into single factor)
ThreeFactor_model <- '
# Factor 1: Bias-Awareness Efficacy
Awareness =~ DSE_Aware_1 + DSE_Aware_2 + DSE_Aware_3
# Factor 2: Self-Regulation Efficacy
Regulation =~ DSE_Regulate_1 + DSE_Regulate_2 + DSE_Regulate_3 +
DSE_Regulate_4 + DSE_Regulate_5
# Factor 3: Intergroup-Management Efficacy
Management =~ DSE_Management_1 + DSE_Management_2 + DSE_Management_3 +
DSE_Management_4 + DSE_Management_5
# Factor 4: Leader Diversity Advocacy & Pro-Diversity Attitudes
Predictors_Outcome =~ Inclusive_Leader_1 + Inclusive_Leader_2 +
Inclusive_Leader_3 + Inclusive_Leader_4 +
ProDiversity_1 + ProDiversity_2 +
ProDiversity_3 + ProDiversity_4 +
Org_Allyship_1 + Org_Allyship_2 + Org_Allyship_3 +
Org_Allyship_4 + Org_Allyship_5 + Org_Allyship_6 +
Org_Allyship_7 + Org_Allyship_8 + Org_Allyship_9
'
ThreeFactor_fit <- cfa(ThreeFactor_model, Study_2_CFA, estimator = "ML")Table 4: Model Comparison
Alternative_Model_5vs4 <- anova(FiveFactor_fit,
FourFactor_fit)
Alternative_Model_5vs3 <- anova(FiveFactor_fit,
ThreeFactor_fit)
# extract values based on column indices
Measurement_Model <- Alternative_Model_5vs4[1, ]
Alt_Model1_4f <- Alternative_Model_5vs4[2, ]
Alt_Model2_3f <- Alternative_Model_5vs3[2, ]
discriminant_model_comparisons <- rbind(Measurement_Model,
Alt_Model1_4f,
Alt_Model2_3f
)
# Print the data frame
print(discriminant_model_comparisons)##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## FiveFactor_fit 265 13894 14100 528.69
## FourFactor_fit 269 14382 14574 1025.09 496.4 0.73478 4 < 2.2e-16
## ThreeFactor_fit 399 16807 17032 1930.63 1401.9 0.20372 134 < 2.2e-16
##
## FiveFactor_fit
## FourFactor_fit ***
## ThreeFactor_fit ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# Extract fit indices for each model
fits <- list(
FiveFactor_fit,
FourFactor_fit,
ThreeFactor_fit)
# Get CFI and SRMR from each fit
fit_indices <- lapply(fits, function(x) {
fitMeasures(x, c("cfi", "srmr"))
})
# Convert to a data frame
fit_indices_df <- do.call(rbind, fit_indices)
rownames(fit_indices_df) <- c("FiveFactor", "FourFactor_Alt1", "ThreeFactor_Alt2")
fit_indices_df## cfi srmr
## FiveFactor 0.9404892 0.04577072
## FourFactor_Alt1 0.8293646 0.08850493
## ThreeFactor_Alt2 0.7065158 0.14433903Reliability Estimates (Cronbach Alpha) - Study 1 Measures
# Reliability estimates for self-efficacy scales
awareness_alpha <- alpha(Study_2_CFA[, c("DSE_Aware_1", "DSE_Aware_2", "DSE_Aware_3")])
management_alpha <- alpha(Study_2_CFA[, c("DSE_Management_1", "DSE_Management_2", "DSE_Management_3", "DSE_Management_4", "DSE_Management_5")])
cat("Alpha for bias-awareness efficacy:", awareness_alpha$total$raw_alpha, "\n",
"Alpha for intergroup-management efficacy:", management_alpha$total$raw_alpha, "\n") ## Alpha for bias-awareness efficacy: 0.8230046
## Alpha for intergroup-management efficacy: 0.9015689org_ally_alpha <- alpha(Study_2_CFA[, c("Org_Allyship_1", "Org_Allyship_2", "Org_Allyship_3", "Org_Allyship_4", "Org_Allyship_5", "Org_Allyship_6", "Org_Allyship_7", "Org_Allyship_8", "Org_Allyship_9")])
cat("Alpha for organizational ally work:", org_ally_alpha$total$raw_alpha, "\n")## Alpha for organizational ally work: 0.9499809# Reliability estimates for leader diversity advocacy and pro-diversity
incl_leader_alpha <- alpha(Study_2_CFA[, c("Inclusive_Leader_1", "Inclusive_Leader_2", "Inclusive_Leader_3", "Inclusive_Leader_4")])
prodiversity_alpha <- alpha(Study_2_CFA[, c("ProDiversity_1", "ProDiversity_2", "ProDiversity_3", "ProDiversity_4")])
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: 0.917747
## Alpha for pro-diversity attitudes: 0.9107846Table 5: Descriptives & Correlations
##
##
## Means, standard deviations, and correlations with confidence intervals
##
##
## Variable M SD 1 2 3
## 1. Male 0.50 0.50
##
## 2. White 0.59 0.49 -.00
## [-.13, .13]
##
## 3. Ideology 3.79 1.59 .01 .22**
## [-.12, .14] [.09, .34]
##
## 4. LdrAdvocacy 3.75 1.09 .03 -.14* -.24**
## [-.10, .15] [-.26, -.01] [-.36, -.11]
##
## 5. PDB 5.63 1.19 -.03 -.10 -.23**
## [-.16, .10] [-.23, .03] [-.35, -.10]
##
## 6. AWARE 3.83 0.93 .04 -.20** -.23**
## [-.09, .17] [-.32, -.07] [-.34, -.10]
##
## 7. REGULATE 4.12 0.72 .09 -.09 -.12
## [-.04, .22] [-.21, .04] [-.25, .00]
##
## 8. MANAGE 3.85 0.85 .05 -.16* -.24**
## [-.08, .17] [-.29, -.04] [-.36, -.12]
##
## 9. OrgAlly 3.11 1.05 .02 -.04 -.25**
## [-.10, .15] [-.17, .09] [-.37, -.13]
##
## 10. Diversity_Voice 4.82 1.42 .05 -.05 -.15*
## [-.08, .18] [-.18, .08] [-.27, -.02]
##
## 11. Interracial_Contact 4.16 0.76 .00 .02 -.01
## [-.12, .13] [-.11, .14] [-.14, .12]
##
## 12. Familiarity 3.18 0.86 .17* -.01 .05
## [.04, .29] [-.14, .12] [-.08, .18]
##
## 4 5 6 7 8 9
##
##
##
##
##
##
##
##
##
##
##
## .47**
## [.36, .56]
##
## .29** .36**
## [.17, .40] [.24, .46]
##
## .38** .46** .52**
## [.26, .48] [.35, .56] [.42, .61]
##
## .35** .44** .51** .69**
## [.23, .46] [.33, .54] [.41, .60] [.62, .75]
##
## .50** .27** .22** .19** .40**
## [.40, .59] [.15, .39] [.10, .34] [.07, .31] [.29, .51]
##
## .60** .31** .31** .33** .46** .76**
## [.51, .68] [.19, .43] [.19, .42] [.21, .44] [.35, .56] [.70, .81]
##
## .25** .50** .27** .56** .45** .08
## [.13, .37] [.40, .59] [.15, .38] [.46, .64] [.34, .54] [-.05, .21]
##
## .15* .08 .22** .24** .25** .13*
## [.02, .27] [-.05, .21] [.09, .34] [.11, .35] [.13, .37] [.00, .25]
##
## 10 11
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## .18**
## [.06, .30]
##
## .24** .09
## [.12, .36] [-.04, .22]
##
##
## 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.
## Run Mplus Path Models
Table 6 (Model 1): Path Model for Organizational Ally Work
## Mplus VERSION 8.11 (Mac)
## MUTHEN & MUTHEN
## 09/04/2025 11:42 AM
##
## INPUT INSTRUCTIONS
##
## TITLE: Study 2: Mediation Models
## DATA: FILE = "Study2.dat";
## VARIABLE:
## NAMES = Male White Ideology LdrDivAd PDB Aware Regulate Manage OrgAlly DVoice pastexp;
## MISSING = ALL (999);
##
## USEVARIABLES LdrDivAd PDB Aware Manage OrgAlly
## PolID;
##
## DEFINE:
## ! Political Ideology centered at the scale midpoint (= 4)
## PolID = Ideology - 4;
##
## ! Grand-mean center Leader Diversity Advocacy and Pro-Diversity Attitudes
## CENTER LdrDivAd PDB (GRANDMEAN);
##
## ANALYSIS:
## ESTIMATOR = ML;
##
## MODEL:
## Aware ON PDB LdrDivAd;
## Manage ON PDB LdrDivAd;
##
## OrgAlly ON PolID PDB LdrDivAd Aware Manage;
##
##
## ! Covariances among predictors
## PDB WITH LdrDivAd PolID;
## LdrDivAd WITH PolID;
## Aware WITH Manage;
##
##
##
## INPUT READING TERMINATED NORMALLY
##
##
##
## Study 2: Mediation Models
##
## SUMMARY OF ANALYSIS
##
## Number of groups 1
## Number of observations 234
##
## Number of dependent variables 3
## Number of independent variables 3
## Number of continuous latent variables 0
##
## Observed dependent variables
##
## Continuous
## AWARE MANAGE ORGALLY
##
## Observed independent variables
## LDRDIVAD PDB POLID
##
## Variables with special functions
##
## Centering (GRANDMEAN)
## LDRDIVAD PDB
##
##
## Estimator ML
## Information matrix OBSERVED
## Maximum number of iterations 1000
## Convergence criterion 0.500D-04
## Maximum number of steepest descent iterations 20
## Maximum number of iterations for H1 2000
## Convergence criterion for H1 0.100D-03
##
## Input data file(s)
## Study2.dat
##
## Input data format FREE
##
##
## SUMMARY OF DATA
##
## Number of missing data patterns 1
##
##
## COVARIANCE COVERAGE OF DATA
##
## Minimum covariance coverage value 0.100
##
##
## PROPORTION OF DATA PRESENT
##
##
## Covariance Coverage
## AWARE MANAGE ORGALLY LDRDIVAD PDB
## ________ ________ ________ ________ ________
## AWARE 1.000
## MANAGE 1.000 1.000
## ORGALLY 1.000 1.000 1.000
## LDRDIVAD 1.000 1.000 1.000 1.000
## PDB 1.000 1.000 1.000 1.000 1.000
## POLID 1.000 1.000 1.000 1.000 1.000
##
##
## Covariance Coverage
## POLID
## ________
## POLID 1.000
##
##
##
## UNIVARIATE SAMPLE STATISTICS
##
##
## UNIVARIATE HIGHER-ORDER MOMENT DESCRIPTIVE STATISTICS
##
## Variable/ Mean/ Skewness/ Minimum/ % with Percentiles
## Sample Size Variance Kurtosis Maximum Min/Max 20%/60% 40%/80% Median
##
## AWARE 3.833 -0.606 1.000 1.71% 3.000 3.667 4.000
## 234.000 0.861 0.144 5.000 20.94% 4.000 5.000
## MANAGE 3.852 -0.469 1.000 0.43% 3.000 3.600 4.000
## 234.000 0.712 -0.298 5.000 13.68% 4.200 4.600
## ORGALLY 3.115 -0.348 1.000 5.56% 2.111 3.000 3.222
## 234.000 1.093 -0.519 5.000 3.85% 3.444 4.000
## LDRDIVAD 0.000 -0.935 -2.747 4.27% -0.747 0.003 0.253
## 234.000 1.192 0.250 1.253 17.95% 0.253 1.003
## PDB 0.000 -0.826 -3.630 0.85% -1.130 0.120 0.370
## 234.000 1.408 0.043 1.370 20.09% 0.370 1.120
## POLID -0.209 0.082 -3.000 8.97% -2.000 0.000 0.000
## 234.000 2.507 -0.479 3.000 5.98% 0.000 1.000
##
##
## THE MODEL ESTIMATION TERMINATED NORMALLY
##
##
##
## MODEL FIT INFORMATION
##
## Number of Free Parameters 25
##
## Loglikelihood
##
## H0 Value -1960.717
## H1 Value -1957.512
##
## Information Criteria
##
## Akaike (AIC) 3971.435
## Bayesian (BIC) 4057.818
## Sample-Size Adjusted BIC 3978.579
## (n* = (n + 2) / 24)
##
## Chi-Square Test of Model Fit
##
## Value 6.412
## Degrees of Freedom 2
## P-Value 0.0405
##
## RMSEA (Root Mean Square Error Of Approximation)
##
## Estimate 0.097
## 90 Percent C.I. 0.017 0.186
## Probability RMSEA <= .05 0.128
##
## CFI/TLI
##
## CFI 0.980
## TLI 0.882
##
## Chi-Square Test of Model Fit for the Baseline Model
##
## Value 235.747
## Degrees of Freedom 12
## P-Value 0.0000
##
## SRMR (Standardized Root Mean Square Residual)
##
## Value 0.033
##
##
##
## MODEL RESULTS
##
## Two-Tailed
## Estimate S.E. Est./S.E. P-Value
##
## AWARE ON
## PDB 0.220 0.053 4.123 0.000
## LDRDIVAD 0.134 0.058 2.307 0.021
##
## MANAGE ON
## PDB 0.250 0.047 5.379 0.000
## LDRDIVAD 0.141 0.051 2.790 0.005
##
## ORGALLY ON
## POLID -0.070 0.037 -1.868 0.062
## PDB -0.050 0.057 -0.877 0.381
## LDRDIVAD 0.403 0.060 6.744 0.000
## AWARE -0.052 0.072 -0.725 0.468
## MANAGE 0.347 0.083 4.196 0.000
##
## PDB WITH
## LDRDIVAD 0.606 0.094 6.483 0.000
## POLID -0.432 0.126 -3.428 0.001
##
## LDRDIVAD WITH
## POLID -0.413 0.116 -3.551 0.000
##
## AWARE WITH
## MANAGE 0.262 0.045 5.798 0.000
##
## Means
## LDRDIVAD 0.000 0.071 0.000 1.000
## PDB 0.000 0.078 0.000 1.000
## POLID -0.209 0.104 -2.023 0.043
##
## Intercepts
## AWARE 3.833 0.056 68.386 0.000
## MANAGE 3.852 0.049 78.931 0.000
## ORGALLY 1.963 0.332 5.916 0.000
##
## Variances
## LDRDIVAD 1.192 0.110 10.817 0.000
## PDB 1.408 0.130 10.817 0.000
## POLID 2.507 0.232 10.817 0.000
##
## Residual Variances
## AWARE 0.735 0.068 10.817 0.000
## MANAGE 0.557 0.052 10.817 0.000
## ORGALLY 0.737 0.068 10.817 0.000
##
##
## QUALITY OF NUMERICAL RESULTS
##
## Condition Number for the Information Matrix 0.866E-03
## (ratio of smallest to largest eigenvalue)
##
##
## Beginning Time: 11:42:56
## Ending Time: 11:42:56
## Elapsed Time: 00:00:00
##
##
##
## MUTHEN & MUTHEN
## 3463 Stoner Ave.
## Los Angeles, CA 90066
##
## Tel: (310) 391-9971
## Fax: (310) 391-8971
## Web: www.StatModel.com
## Support: Support@StatModel.com
##
## Copyright (c) 1998-2024 Muthen & MuthenHypothesis 1b: Mediation Analysis
res <- readModels("Mplus Syntax/Study2_Mediation.out")
# Extract coefficients
a_est <- res$parameters$unstandardized$est[2] # Effect of X on M (a-path)
b_est <- res$parameters$unstandardized$est[8] # Effect of M on Y (b-path)
# Extract standard errors
a_se <- res$parameters$unstandardized$se[2]
b_se <- res$parameters$unstandardized$se[8]
# 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")## Indirect effect estimate: -0.006968## Indirect effect standard error: 0.01093705## Monte Carlo 90% CI: [ -0.02655867 , 0.008882594 ]Hypothesis 3: Mediation Analysis
# Extract coefficients
a_est <- res$parameters$unstandardized$est[4] # Effect of X on M (a-path)
b_est <- res$parameters$unstandardized$est[9] # Effect of M on Y (b-path)
# Extract standard errors
a_se <- res$parameters$unstandardized$se[4]
b_se <- res$parameters$unstandardized$se[9]
# 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")## Indirect effect estimate: 0.048927## Indirect effect standard error: 0.02163475## Monte Carlo 99% CI: [ 0.002980975 , 0.1152867 ]Table 6 (Model 2): Conditional Path Model for Organizational Ally Work
## Mplus VERSION 8.11 (Mac)
## MUTHEN & MUTHEN
## 09/04/2025 11:42 AM
##
## INPUT INSTRUCTIONS
##
## TITLE: Study 2: Moderated Mediation Models
## DATA: FILE = "Study2.dat";
## VARIABLE:
## NAMES = Male White Ideology LdrDivAd PDB Aware Regulate Manage OrgAlly DVoice pastexp;
## MISSING = ALL (999);
##
## USEVARIABLES LdrDivAd PDB Aware Manage OrgAlly
## PolID LDA_PDB
##
## DEFINE:
## ! Political Ideology centered at the scale midpoint (= 4)
## PolID = Ideology - 4;
##
## ! Grand-mean center Leader Diversity Advocacy and Pro-Diversity Attitudes
## CENTER LdrDivAd PDB (GRANDMEAN);
##
## ! Create interaction term
## LDA_PDB = LdrDivAd * PDB;
##
## ANALYSIS:
## ESTIMATOR = ML;
##
## MODEL:
## Aware ON PDB
## LdrDivAd
## LDA_PDB;
##
## Manage ON PDB (c2)
## LdrDivAd (c1)
## LDA_PDB (c3);
##
## OrgAlly ON PolID
## PDB
## LdrDivAd
## Aware
## Manage (mg);
##
## ! Covariances among predictors
## PDB WITH LdrDivAd PolID;
## LdrDivAd WITH PolID;
## Aware WITH Manage;
##
## MODEL CONSTRAINT:
##
## LOOP(PDB, -1.96, 1.96, .98); ! Two Standard Deviations Below/Above Mean
## PLOT(LdrDivAd_mg);
## LdrDivAd_mg = (c1 + c3*PDB)*mg;
##
## PLOT: TYPE = PLOT2;
##
##
##
## INPUT READING TERMINATED NORMALLY
##
##
##
## Study 2: Moderated Mediation Models
##
## SUMMARY OF ANALYSIS
##
## Number of groups 1
## Number of observations 234
##
## Number of dependent variables 3
## Number of independent variables 4
## Number of continuous latent variables 0
##
## Observed dependent variables
##
## Continuous
## AWARE MANAGE ORGALLY
##
## Observed independent variables
## LDRDIVAD PDB POLID LDA_PDB
##
## Variables with special functions
##
## Centering (GRANDMEAN)
## LDRDIVAD PDB
##
##
## Estimator ML
## Information matrix OBSERVED
## Maximum number of iterations 1000
## Convergence criterion 0.500D-04
## Maximum number of steepest descent iterations 20
## Maximum number of iterations for H1 2000
## Convergence criterion for H1 0.100D-03
##
## Input data file(s)
## Study2.dat
##
## Input data format FREE
##
##
## SUMMARY OF DATA
##
## Number of missing data patterns 1
##
##
## COVARIANCE COVERAGE OF DATA
##
## Minimum covariance coverage value 0.100
##
##
## PROPORTION OF DATA PRESENT
##
##
## Covariance Coverage
## AWARE MANAGE ORGALLY LDRDIVAD PDB
## ________ ________ ________ ________ ________
## AWARE 1.000
## MANAGE 1.000 1.000
## ORGALLY 1.000 1.000 1.000
## LDRDIVAD 1.000 1.000 1.000 1.000
## PDB 1.000 1.000 1.000 1.000 1.000
## POLID 1.000 1.000 1.000 1.000 1.000
## LDA_PDB 1.000 1.000 1.000 1.000 1.000
##
##
## Covariance Coverage
## POLID LDA_PDB
## ________ ________
## POLID 1.000
## LDA_PDB 1.000 1.000
##
##
##
## UNIVARIATE SAMPLE STATISTICS
##
##
## UNIVARIATE HIGHER-ORDER MOMENT DESCRIPTIVE STATISTICS
##
## Variable/ Mean/ Skewness/ Minimum/ % with Percentiles
## Sample Size Variance Kurtosis Maximum Min/Max 20%/60% 40%/80% Median
##
## AWARE 3.833 -0.606 1.000 1.71% 3.000 3.667 4.000
## 234.000 0.861 0.144 5.000 20.94% 4.000 5.000
## MANAGE 3.852 -0.469 1.000 0.43% 3.000 3.600 4.000
## 234.000 0.712 -0.298 5.000 13.68% 4.200 4.600
## ORGALLY 3.115 -0.348 1.000 5.56% 2.111 3.000 3.222
## 234.000 1.093 -0.519 5.000 3.85% 3.444 4.000
## LDRDIVAD 0.000 -0.935 -2.747 4.27% -0.747 0.003 0.253
## 234.000 1.192 0.250 1.253 17.95% 0.253 1.003
## PDB 0.000 -0.826 -3.630 0.85% -1.130 0.120 0.370
## 234.000 1.408 0.043 1.370 20.09% 0.370 1.120
## POLID -0.209 0.082 -3.000 8.97% -2.000 0.000 0.000
## 234.000 2.507 -0.479 3.000 5.98% 0.000 1.000
## LDA_PDB 0.606 2.052 -3.922 0.43% -0.215 0.004 0.218
## 234.000 2.114 7.321 8.600 0.43% 0.437 1.374
##
##
## THE MODEL ESTIMATION TERMINATED NORMALLY
##
##
##
## MODEL FIT INFORMATION
##
## Number of Free Parameters 27
##
## Loglikelihood
##
## H0 Value -1955.708
## H1 Value -1931.227
##
## Information Criteria
##
## Akaike (AIC) 3965.415
## Bayesian (BIC) 4058.709
## Sample-Size Adjusted BIC 3973.131
## (n* = (n + 2) / 24)
##
## Chi-Square Test of Model Fit
##
## Value 48.961
## Degrees of Freedom 6
## P-Value 0.0000
##
## RMSEA (Root Mean Square Error Of Approximation)
##
## Estimate 0.175
## 90 Percent C.I. 0.131 0.222
## Probability RMSEA <= .05 0.000
##
## CFI/TLI
##
## CFI 0.814
## TLI 0.536
##
## Chi-Square Test of Model Fit for the Baseline Model
##
## Value 246.278
## Degrees of Freedom 15
## P-Value 0.0000
##
## SRMR (Standardized Root Mean Square Residual)
##
## Value 0.110
##
##
##
## MODEL RESULTS
##
## Two-Tailed
## Estimate S.E. Est./S.E. P-Value
##
## AWARE ON
## PDB 0.224 0.053 4.230 0.000
## LDRDIVAD 0.176 0.061 2.862 0.004
## LDA_PDB 0.082 0.042 1.955 0.051
##
## MANAGE ON
## PDB 0.256 0.046 5.607 0.000
## LDRDIVAD 0.198 0.053 3.748 0.000
## LDA_PDB 0.112 0.036 3.099 0.002
##
## ORGALLY ON
## POLID -0.070 0.037 -1.868 0.062
## PDB -0.050 0.057 -0.877 0.381
## LDRDIVAD 0.403 0.060 6.744 0.000
## AWARE -0.052 0.072 -0.725 0.468
## MANAGE 0.347 0.083 4.196 0.000
##
## PDB WITH
## LDRDIVAD 0.606 0.094 6.483 0.000
## POLID -0.432 0.126 -3.428 0.001
##
## LDRDIVAD WITH
## POLID -0.413 0.116 -3.551 0.000
##
## AWARE WITH
## MANAGE 0.246 0.044 5.625 0.000
##
## Means
## LDRDIVAD 0.000 0.071 0.000 1.000
## PDB 0.000 0.078 0.000 1.000
## POLID -0.209 0.104 -2.023 0.043
##
## Intercepts
## AWARE 3.783 0.061 61.916 0.000
## MANAGE 3.784 0.053 71.988 0.000
## ORGALLY 1.963 0.332 5.916 0.000
##
## Variances
## LDRDIVAD 1.192 0.110 10.817 0.000
## PDB 1.408 0.130 10.817 0.000
## POLID 2.507 0.232 10.817 0.000
##
## Residual Variances
## AWARE 0.723 0.067 10.817 0.000
## MANAGE 0.535 0.049 10.817 0.000
## ORGALLY 0.737 0.068 10.817 0.000
##
##
## QUALITY OF NUMERICAL RESULTS
##
## Condition Number for the Information Matrix 0.991E-04
## (ratio of smallest to largest eigenvalue)
##
##
## PLOT INFORMATION
##
## The following plots are available:
##
## Loop plots
##
## Beginning Time: 11:42:56
## Ending Time: 11:42:56
## Elapsed Time: 00:00:00
##
##
##
## MUTHEN & MUTHEN
## 3463 Stoner Ave.
## Los Angeles, CA 90066
##
## Tel: (310) 391-9971
## Fax: (310) 391-8971
## Web: www.StatModel.com
## Support: Support@StatModel.com
##
## Copyright (c) 1998-2024 Muthen & MuthenHypothesis 5a: Moderated Mediation (Bias-Awareness Efficacy and Organizational Ally Work)
res <- readModels("Mplus Syntax/Study2_Moderated Mediation.out")
# Extract coefficients
a_int <- res$parameters$unstandardized$est[3] # Effect of XW on M (a-path)
b_est <- res$parameters$unstandardized$est[10] # Effect of M on Y (b-path)
# Extract standard errors
a_int_se <- res$parameters$unstandardized$se[3]
b_se <- res$parameters$unstandardized$se[10]
# 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: -0.004264## Standard error: 0.00698367## Monte Carlo 90% CI: [ -0.01696925 , 0.005518282 ]Hypothesis 5b: Moderated Mediation (Intergroup-Management Efficacy and Organizational Ally Work)
# Extract coefficients
a_int <- res$parameters$unstandardized$est[6] # Effect of XW on M (a-path)
b_est <- res$parameters$unstandardized$est[11] # Effect of M on Y (b-path)
# Extract standard errors
a_int_se <- res$parameters$unstandardized$se[6]
b_se <- res$parameters$unstandardized$se[11]
# 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: 0.038864## Standard error: 0.0158554## Monte Carlo 99% CI: [ 0.005639582 , 0.08740678 ]##
## --- Conditional Indirect Effects ---## At LOW PDB (-1 SD):## Indirect effect estimate: 0.02246## Standard error (LOW PDB): 0.0249## Monte Carlo 90% CI: [ -0.016 , 0.065 ]## At HIGH PDB (+1 SD):## Indirect effect estimate: 0.115## Standard error (HIGH PDB): 0.0367## Monte Carlo 99% CI: [ 0.036 , 0.225 ]View Johnson-Neyman Plots for Conditional Indirect Effects
Figure 4: Conditional Indirect Effect on Organizational Ally Work via Intergroup-Management Self-Efficacy
Supplementary Analyses #1: Past Positive Interracial Contact
# View output files
med_out <- readLines("Mplus Syntax/Study2_IntergroupContact.out")
cat(paste(med_out, collapse = "\n"))## Mplus VERSION 8.11 (Mac)
## MUTHEN & MUTHEN
## 09/04/2025 1:35 PM
##
## INPUT INSTRUCTIONS
##
## TITLE: Study 2: Mediation Models
## DATA: FILE = "Study2.dat";
## VARIABLE:
## NAMES = Male White Ideology LdrDivAd PDB Aware Regulate Manage OrgAlly DVoice pastexp;
## MISSING = ALL (999);
##
## USEVARIABLES LdrDivAd PDB Aware Manage OrgAlly
## pastexp PolID;
##
## DEFINE:
## ! Political Ideology centered at the scale midpoint (= 4)
## PolID = Ideology - 4;
##
## ! Grand-mean center Leader Diversity Advocacy and Pro-Diversity Attitudes
## CENTER LdrDivAd PDB (GRANDMEAN);
##
## ANALYSIS:
## ESTIMATOR = ML;
##
## MODEL:
## Aware ON pastexp PDB LdrDivAd;
## Manage ON pastexp PDB LdrDivAd;
##
## OrgAlly ON pastexp PolID PDB LdrDivAd Aware Manage;
##
##
## ! Covariances among predictors
## PDB WITH LdrDivAd PolID pastexp;
## LdrDivAd WITH PolID pastexp;
## PolID WITH pastexp;
## Aware WITH Manage;
##
##
##
## INPUT READING TERMINATED NORMALLY
##
##
##
## Study 2: Mediation Models
##
## SUMMARY OF ANALYSIS
##
## Number of groups 1
## Number of observations 234
##
## Number of dependent variables 3
## Number of independent variables 4
## Number of continuous latent variables 0
##
## Observed dependent variables
##
## Continuous
## AWARE MANAGE ORGALLY
##
## Observed independent variables
## LDRDIVAD PDB PASTEXP POLID
##
## Variables with special functions
##
## Centering (GRANDMEAN)
## LDRDIVAD PDB
##
##
## Estimator ML
## Information matrix OBSERVED
## Maximum number of iterations 1000
## Convergence criterion 0.500D-04
## Maximum number of steepest descent iterations 20
## Maximum number of iterations for H1 2000
## Convergence criterion for H1 0.100D-03
##
## Input data file(s)
## Study2.dat
##
## Input data format FREE
##
##
## SUMMARY OF DATA
##
## Number of missing data patterns 1
##
##
## COVARIANCE COVERAGE OF DATA
##
## Minimum covariance coverage value 0.100
##
##
## PROPORTION OF DATA PRESENT
##
##
## Covariance Coverage
## AWARE MANAGE ORGALLY LDRDIVAD PDB
## ________ ________ ________ ________ ________
## AWARE 1.000
## MANAGE 1.000 1.000
## ORGALLY 1.000 1.000 1.000
## LDRDIVAD 1.000 1.000 1.000 1.000
## PDB 1.000 1.000 1.000 1.000 1.000
## PASTEXP 1.000 1.000 1.000 1.000 1.000
## POLID 1.000 1.000 1.000 1.000 1.000
##
##
## Covariance Coverage
## PASTEXP POLID
## ________ ________
## PASTEXP 1.000
## POLID 1.000 1.000
##
##
##
## UNIVARIATE SAMPLE STATISTICS
##
##
## UNIVARIATE HIGHER-ORDER MOMENT DESCRIPTIVE STATISTICS
##
## Variable/ Mean/ Skewness/ Minimum/ % with Percentiles
## Sample Size Variance Kurtosis Maximum Min/Max 20%/60% 40%/80% Median
##
## AWARE 3.833 -0.606 1.000 1.71% 3.000 3.667 4.000
## 234.000 0.861 0.144 5.000 20.94% 4.000 5.000
## MANAGE 3.852 -0.469 1.000 0.43% 3.000 3.600 4.000
## 234.000 0.712 -0.298 5.000 13.68% 4.200 4.600
## ORGALLY 3.115 -0.348 1.000 5.56% 2.111 3.000 3.222
## 234.000 1.093 -0.519 5.000 3.85% 3.444 4.000
## LDRDIVAD 0.000 -0.935 -2.747 4.27% -0.747 0.003 0.253
## 234.000 1.192 0.250 1.253 17.95% 0.253 1.003
## PDB 0.000 -0.826 -3.630 0.85% -1.130 0.120 0.370
## 234.000 1.408 0.043 1.370 20.09% 0.370 1.120
## PASTEXP 4.162 -0.834 1.000 0.43% 3.500 4.000 4.000
## 234.000 0.572 0.727 5.000 30.34% 4.500 5.000
## POLID -0.209 0.082 -3.000 8.97% -2.000 0.000 0.000
## 234.000 2.507 -0.479 3.000 5.98% 0.000 1.000
##
##
## THE MODEL ESTIMATION TERMINATED NORMALLY
##
##
##
## MODEL FIT INFORMATION
##
## Number of Free Parameters 33
##
## Loglikelihood
##
## H0 Value -2177.858
## H1 Value -2172.783
##
## Information Criteria
##
## Akaike (AIC) 4421.716
## Bayesian (BIC) 4535.742
## Sample-Size Adjusted BIC 4431.147
## (n* = (n + 2) / 24)
##
## Chi-Square Test of Model Fit
##
## Value 10.151
## Degrees of Freedom 2
## P-Value 0.0062
##
## RMSEA (Root Mean Square Error Of Approximation)
##
## Estimate 0.132
## 90 Percent C.I. 0.060 0.217
## Probability RMSEA <= .05 0.033
##
## CFI/TLI
##
## CFI 0.968
## TLI 0.757
##
## Chi-Square Test of Model Fit for the Baseline Model
##
## Value 266.467
## Degrees of Freedom 15
## P-Value 0.0000
##
## SRMR (Standardized Root Mean Square Residual)
##
## Value 0.035
##
##
##
## MODEL RESULTS
##
## Two-Tailed
## Estimate S.E. Est./S.E. P-Value
##
## AWARE ON
## PASTEXP 0.146 0.085 1.710 0.087
## PDB 0.175 0.059 2.939 0.003
## LDRDIVAD 0.132 0.058 2.285 0.022
##
## MANAGE ON
## PASTEXP 0.333 0.071 4.674 0.000
## PDB 0.146 0.050 2.928 0.003
## LDRDIVAD 0.136 0.048 2.816 0.005
##
## ORGALLY ON
## PASTEXP -0.223 0.090 -2.480 0.013
## POLID -0.053 0.038 -1.408 0.159
## PDB 0.007 0.061 0.122 0.903
## LDRDIVAD 0.402 0.059 6.807 0.000
## AWARE -0.051 0.071 -0.716 0.474
## MANAGE 0.409 0.085 4.787 0.000
##
## PDB WITH
## LDRDIVAD 0.606 0.094 6.483 0.000
## POLID -0.432 0.126 -3.428 0.001
## PASTEXP 0.450 0.066 6.857 0.000
##
## LDRDIVAD WITH
## POLID -0.413 0.116 -3.551 0.000
## PASTEXP 0.207 0.056 3.723 0.000
##
## POLID WITH
## PASTEXP -0.009 0.078 -0.112 0.911
##
## AWARE WITH
## MANAGE 0.241 0.043 5.642 0.000
##
## Means
## LDRDIVAD 0.000 0.071 0.000 1.000
## PDB 0.000 0.078 0.000 1.000
## PASTEXP 4.162 0.049 84.195 0.000
## POLID -0.209 0.104 -2.023 0.043
##
## Intercepts
## AWARE 3.226 0.359 8.994 0.000
## MANAGE 2.464 0.301 8.196 0.000
## ORGALLY 2.656 0.430 6.170 0.000
##
## Variances
## LDRDIVAD 1.192 0.110 10.817 0.000
## PDB 1.408 0.130 10.817 0.000
## PASTEXP 0.572 0.053 10.817 0.000
## POLID 2.507 0.232 10.817 0.000
##
## Residual Variances
## AWARE 0.726 0.067 10.817 0.000
## MANAGE 0.510 0.047 10.816 0.000
## ORGALLY 0.718 0.066 10.817 0.000
##
##
## QUALITY OF NUMERICAL RESULTS
##
## Condition Number for the Information Matrix 0.556E-03
## (ratio of smallest to largest eigenvalue)
##
##
## Beginning Time: 13:35:53
## Ending Time: 13:35:54
## Elapsed Time: 00:00:01
##
##
##
## MUTHEN & MUTHEN
## 3463 Stoner Ave.
## Los Angeles, CA 90066
##
## Tel: (310) 391-9971
## Fax: (310) 391-8971
## Web: www.StatModel.com
## Support: Support@StatModel.com
##
## Copyright (c) 1998-2024 Muthen & Muthen### Mediation via Intergroup-Management Self-Efficacy, Controlling for Past Positive Interracial Contact
res <- readModels("Mplus Syntax/Study2_IntergroupContact.out")
# Extract coefficients
a_est <- res$parameters$unstandardized$est[6] # Effect of X on M (a-path)
b_est <- res$parameters$unstandardized$est[12] # Effect of M on Y (b-path)
# Extract standard errors
a_se <- res$parameters$unstandardized$se[6]
b_se <- res$parameters$unstandardized$se[12]
# 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")## Indirect effect estimate: 0.055624## Indirect effect standard error: 0.0231451## Monte Carlo 99% CI: [ 0.004697249 , 0.1252399 ]Supplementary Analyses #2: Diversity Voice
# View output files
med_out <- readLines("Mplus Syntax/Study2_Mediation_DVoice.out")
cat(paste(med_out, collapse = "\n"))## Mplus VERSION 8.11 (Mac)
## MUTHEN & MUTHEN
## 09/04/2025 1:12 PM
##
## INPUT INSTRUCTIONS
##
## TITLE: Study 2: Supplemental Mediation Analyses
## DATA: FILE = "Study2.dat";
## VARIABLE:
## NAMES = Male White Ideology LdrDivAd PDB Aware Regulate Manage OrgAlly DVoice pastexp;
## MISSING = ALL (999);
##
## USEVARIABLES LdrDivAd PDB Aware Manage DVoice
## PolID;
##
## DEFINE:
## ! Political Ideology centered at the scale midpoint (= 4)
## PolID = Ideology - 4;
##
## ! Grand-mean center Leader Diversity Advocacy and Pro-Diversity Attitudes
## CENTER LdrDivAd PDB (GRANDMEAN);
##
## ANALYSIS:
## ESTIMATOR = ML;
##
## MODEL:
## Aware ON PDB LdrDivAd;
## Manage ON PDB LdrDivAd;
##
## DVoice ON PolID PDB LdrDivAd Aware Manage;
##
##
## ! Covariances among predictors
## PDB WITH LdrDivAd PolID;
## LdrDivAd WITH PolID;
## Aware WITH Manage;
##
##
##
## INPUT READING TERMINATED NORMALLY
##
##
##
## Study 2: Supplemental Mediation Analyses
##
## SUMMARY OF ANALYSIS
##
## Number of groups 1
## Number of observations 234
##
## Number of dependent variables 3
## Number of independent variables 3
## Number of continuous latent variables 0
##
## Observed dependent variables
##
## Continuous
## AWARE MANAGE DVOICE
##
## Observed independent variables
## LDRDIVAD PDB POLID
##
## Variables with special functions
##
## Centering (GRANDMEAN)
## LDRDIVAD PDB
##
##
## Estimator ML
## Information matrix OBSERVED
## Maximum number of iterations 1000
## Convergence criterion 0.500D-04
## Maximum number of steepest descent iterations 20
## Maximum number of iterations for H1 2000
## Convergence criterion for H1 0.100D-03
##
## Input data file(s)
## Study2.dat
##
## Input data format FREE
##
##
## SUMMARY OF DATA
##
## Number of missing data patterns 1
##
##
## COVARIANCE COVERAGE OF DATA
##
## Minimum covariance coverage value 0.100
##
##
## PROPORTION OF DATA PRESENT
##
##
## Covariance Coverage
## AWARE MANAGE DVOICE LDRDIVAD PDB
## ________ ________ ________ ________ ________
## AWARE 1.000
## MANAGE 1.000 1.000
## DVOICE 1.000 1.000 1.000
## LDRDIVAD 1.000 1.000 1.000 1.000
## PDB 1.000 1.000 1.000 1.000 1.000
## POLID 1.000 1.000 1.000 1.000 1.000
##
##
## Covariance Coverage
## POLID
## ________
## POLID 1.000
##
##
##
## UNIVARIATE SAMPLE STATISTICS
##
##
## UNIVARIATE HIGHER-ORDER MOMENT DESCRIPTIVE STATISTICS
##
## Variable/ Mean/ Skewness/ Minimum/ % with Percentiles
## Sample Size Variance Kurtosis Maximum Min/Max 20%/60% 40%/80% Median
##
## AWARE 3.833 -0.606 1.000 1.71% 3.000 3.667 4.000
## 234.000 0.861 0.144 5.000 20.94% 4.000 5.000
## MANAGE 3.852 -0.469 1.000 0.43% 3.000 3.600 4.000
## 234.000 0.712 -0.298 5.000 13.68% 4.200 4.600
## DVOICE 4.824 -0.584 1.000 2.99% 4.000 4.333 4.833
## 234.000 2.004 0.298 7.000 7.26% 5.167 6.000
## LDRDIVAD 0.000 -0.935 -2.747 4.27% -0.747 0.003 0.253
## 234.000 1.192 0.250 1.253 17.95% 0.253 1.003
## PDB 0.000 -0.826 -3.630 0.85% -1.130 0.120 0.370
## 234.000 1.408 0.043 1.370 20.09% 0.370 1.120
## POLID -0.209 0.082 -3.000 8.97% -2.000 0.000 0.000
## 234.000 2.507 -0.479 3.000 5.98% 0.000 1.000
##
##
## THE MODEL ESTIMATION TERMINATED NORMALLY
##
##
##
## MODEL FIT INFORMATION
##
## Number of Free Parameters 25
##
## Loglikelihood
##
## H0 Value -2010.111
## H1 Value -2006.906
##
## Information Criteria
##
## Akaike (AIC) 4070.223
## Bayesian (BIC) 4156.606
## Sample-Size Adjusted BIC 4077.367
## (n* = (n + 2) / 24)
##
## Chi-Square Test of Model Fit
##
## Value 6.412
## Degrees of Freedom 2
## P-Value 0.0405
##
## RMSEA (Root Mean Square Error Of Approximation)
##
## Estimate 0.097
## 90 Percent C.I. 0.017 0.186
## Probability RMSEA <= .05 0.128
##
## CFI/TLI
##
## CFI 0.983
## TLI 0.901
##
## Chi-Square Test of Model Fit for the Baseline Model
##
## Value 278.884
## Degrees of Freedom 12
## P-Value 0.0000
##
## SRMR (Standardized Root Mean Square Residual)
##
## Value 0.034
##
##
##
## MODEL RESULTS
##
## Two-Tailed
## Estimate S.E. Est./S.E. P-Value
##
## AWARE ON
## PDB 0.220 0.053 4.123 0.000
## LDRDIVAD 0.134 0.058 2.307 0.021
##
## MANAGE ON
## PDB 0.250 0.047 5.379 0.000
## LDRDIVAD 0.141 0.051 2.790 0.005
##
## DVOICE ON
## POLID 0.036 0.046 0.776 0.438
## PDB -0.080 0.071 -1.123 0.262
## LDRDIVAD 0.685 0.074 9.283 0.000
## AWARE 0.056 0.089 0.629 0.529
## MANAGE 0.499 0.102 4.879 0.000
##
## PDB WITH
## LDRDIVAD 0.606 0.094 6.483 0.000
## POLID -0.432 0.126 -3.428 0.001
##
## LDRDIVAD WITH
## POLID -0.413 0.116 -3.551 0.000
##
## AWARE WITH
## MANAGE 0.262 0.045 5.798 0.000
##
## Means
## LDRDIVAD 0.000 0.071 0.000 1.000
## PDB 0.000 0.078 0.000 1.000
## POLID -0.209 0.104 -2.023 0.043
##
## Intercepts
## AWARE 3.833 0.056 68.386 0.000
## MANAGE 3.852 0.049 78.931 0.000
## DVOICE 2.697 0.410 6.579 0.000
##
## Variances
## LDRDIVAD 1.192 0.110 10.817 0.000
## PDB 1.408 0.130 10.817 0.000
## POLID 2.507 0.232 10.817 0.000
##
## Residual Variances
## AWARE 0.735 0.068 10.817 0.000
## MANAGE 0.557 0.052 10.817 0.000
## DVOICE 1.124 0.104 10.817 0.000
##
##
## QUALITY OF NUMERICAL RESULTS
##
## Condition Number for the Information Matrix 0.149E-02
## (ratio of smallest to largest eigenvalue)
##
##
## Beginning Time: 13:12:33
## Ending Time: 13:12:33
## Elapsed Time: 00:00:00
##
##
##
## MUTHEN & MUTHEN
## 3463 Stoner Ave.
## Los Angeles, CA 90066
##
## Tel: (310) 391-9971
## Fax: (310) 391-8971
## Web: www.StatModel.com
## Support: Support@StatModel.com
##
## Copyright (c) 1998-2024 Muthen & MuthenMediation Analysis (via Bias-Awareness Self-Efficacy)
res <- readModels("Mplus Syntax/Study2_Mediation_DVoice.out")
# Extract coefficients
a_est <- res$parameters$unstandardized$est[2] # Effect of X on M (a-path)
b_est <- res$parameters$unstandardized$est[8] # Effect of M on Y (b-path)
# Extract standard errors
a_se <- res$parameters$unstandardized$se[2]
b_se <- res$parameters$unstandardized$se[8]
# 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")## Indirect effect estimate: 0.007504## Indirect effect standard error: 0.01339497## Monte Carlo 90% CI: [ -0.01225498 , 0.03131819 ]Mediation Analysis (via Self-Regulation Self-Efficacy)
# Extract coefficients
a_est <- res$parameters$unstandardized$est[4] # Effect of X on M (a-path)
b_est <- res$parameters$unstandardized$est[9] # Effect of M on Y (b-path)
# Extract standard errors
a_se <- res$parameters$unstandardized$se[4]
b_se <- res$parameters$unstandardized$se[9]
# 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")## Indirect effect estimate: 0.070359## Indirect effect standard error: 0.02969098## Monte Carlo 99% CI: [ 0.004509416 , 0.1594321 ]Moderated Mediation (Bias-Awareness Efficacy and Diversity Voice)
# View output files
modmed_out <- readLines("Mplus Syntax/Study2_Moderated Mediation_DVoice.out")
cat(paste(modmed_out, collapse = "\n"))## Mplus VERSION 8.11 (Mac)
## MUTHEN & MUTHEN
## 09/04/2025 1:12 PM
##
## INPUT INSTRUCTIONS
##
## TITLE: Study 2: Moderated Mediation Models
## DATA: FILE = "Study2.dat";
## VARIABLE:
## NAMES = Male White Ideology LdrDivAd PDB Aware Regulate Manage OrgAlly DVoice pastexp;
## MISSING = ALL (999);
##
## USEVARIABLES LdrDivAd PDB Aware Manage DVoice
## PolID LDA_PDB
##
## DEFINE:
## ! Political Ideology centered at the scale midpoint (= 4)
## PolID = Ideology - 4;
##
## ! Grand-mean center Leader Diversity Advocacy and Pro-Diversity Attitudes
## CENTER LdrDivAd PDB (GRANDMEAN);
##
## ! Create interaction term
## LDA_PDB = LdrDivAd * PDB;
##
## ANALYSIS:
## ESTIMATOR = ML;
##
## MODEL:
## Aware ON PDB
## LdrDivAd
## LDA_PDB;
##
## Manage ON PDB (c2)
## LdrDivAd (c1)
## LDA_PDB (c3);
##
## DVoice ON PolID
## PDB
## LdrDivAd
## Aware
## Manage (mg);
##
## ! Covariances among predictors
## PDB WITH LdrDivAd PolID;
## LdrDivAd WITH PolID;
## Aware WITH Manage;
##
## MODEL CONSTRAINT:
##
## LOOP(PDB, -2.38, 2.38, 1.19); ! Two Standard Deviations Below/Above Mean
## PLOT(LdrDivAd_mg);
## LdrDivAd_mg = (c1 + c3*PDB)*mg;
##
## PLOT: TYPE = PLOT2;
##
##
##
## INPUT READING TERMINATED NORMALLY
##
##
##
## Study 2: Moderated Mediation Models
##
## SUMMARY OF ANALYSIS
##
## Number of groups 1
## Number of observations 234
##
## Number of dependent variables 3
## Number of independent variables 4
## Number of continuous latent variables 0
##
## Observed dependent variables
##
## Continuous
## AWARE MANAGE DVOICE
##
## Observed independent variables
## LDRDIVAD PDB POLID LDA_PDB
##
## Variables with special functions
##
## Centering (GRANDMEAN)
## LDRDIVAD PDB
##
##
## Estimator ML
## Information matrix OBSERVED
## Maximum number of iterations 1000
## Convergence criterion 0.500D-04
## Maximum number of steepest descent iterations 20
## Maximum number of iterations for H1 2000
## Convergence criterion for H1 0.100D-03
##
## Input data file(s)
## Study2.dat
##
## Input data format FREE
##
##
## SUMMARY OF DATA
##
## Number of missing data patterns 1
##
##
## COVARIANCE COVERAGE OF DATA
##
## Minimum covariance coverage value 0.100
##
##
## PROPORTION OF DATA PRESENT
##
##
## Covariance Coverage
## AWARE MANAGE DVOICE LDRDIVAD PDB
## ________ ________ ________ ________ ________
## AWARE 1.000
## MANAGE 1.000 1.000
## DVOICE 1.000 1.000 1.000
## LDRDIVAD 1.000 1.000 1.000 1.000
## PDB 1.000 1.000 1.000 1.000 1.000
## POLID 1.000 1.000 1.000 1.000 1.000
## LDA_PDB 1.000 1.000 1.000 1.000 1.000
##
##
## Covariance Coverage
## POLID LDA_PDB
## ________ ________
## POLID 1.000
## LDA_PDB 1.000 1.000
##
##
##
## UNIVARIATE SAMPLE STATISTICS
##
##
## UNIVARIATE HIGHER-ORDER MOMENT DESCRIPTIVE STATISTICS
##
## Variable/ Mean/ Skewness/ Minimum/ % with Percentiles
## Sample Size Variance Kurtosis Maximum Min/Max 20%/60% 40%/80% Median
##
## AWARE 3.833 -0.606 1.000 1.71% 3.000 3.667 4.000
## 234.000 0.861 0.144 5.000 20.94% 4.000 5.000
## MANAGE 3.852 -0.469 1.000 0.43% 3.000 3.600 4.000
## 234.000 0.712 -0.298 5.000 13.68% 4.200 4.600
## DVOICE 4.824 -0.584 1.000 2.99% 4.000 4.333 4.833
## 234.000 2.004 0.298 7.000 7.26% 5.167 6.000
## LDRDIVAD 0.000 -0.935 -2.747 4.27% -0.747 0.003 0.253
## 234.000 1.192 0.250 1.253 17.95% 0.253 1.003
## PDB 0.000 -0.826 -3.630 0.85% -1.130 0.120 0.370
## 234.000 1.408 0.043 1.370 20.09% 0.370 1.120
## POLID -0.209 0.082 -3.000 8.97% -2.000 0.000 0.000
## 234.000 2.507 -0.479 3.000 5.98% 0.000 1.000
## LDA_PDB 0.606 2.052 -3.922 0.43% -0.215 0.004 0.218
## 234.000 2.114 7.321 8.600 0.43% 0.437 1.374
##
##
## THE MODEL ESTIMATION TERMINATED NORMALLY
##
##
##
## MODEL FIT INFORMATION
##
## Number of Free Parameters 27
##
## Loglikelihood
##
## H0 Value -2005.102
## H1 Value -1980.298
##
## Information Criteria
##
## Akaike (AIC) 4064.203
## Bayesian (BIC) 4157.497
## Sample-Size Adjusted BIC 4071.919
## (n* = (n + 2) / 24)
##
## Chi-Square Test of Model Fit
##
## Value 49.607
## Degrees of Freedom 6
## P-Value 0.0000
##
## RMSEA (Root Mean Square Error Of Approximation)
##
## Estimate 0.176
## 90 Percent C.I. 0.133 0.223
## Probability RMSEA <= .05 0.000
##
## CFI/TLI
##
## CFI 0.841
## TLI 0.604
##
## Chi-Square Test of Model Fit for the Baseline Model
##
## Value 290.060
## Degrees of Freedom 15
## P-Value 0.0000
##
## SRMR (Standardized Root Mean Square Residual)
##
## Value 0.115
##
##
##
## MODEL RESULTS
##
## Two-Tailed
## Estimate S.E. Est./S.E. P-Value
##
## AWARE ON
## PDB 0.224 0.053 4.230 0.000
## LDRDIVAD 0.176 0.061 2.862 0.004
## LDA_PDB 0.082 0.042 1.955 0.051
##
## MANAGE ON
## PDB 0.256 0.046 5.607 0.000
## LDRDIVAD 0.198 0.053 3.748 0.000
## LDA_PDB 0.112 0.036 3.099 0.002
##
## DVOICE ON
## POLID 0.036 0.046 0.776 0.437
## PDB -0.080 0.071 -1.123 0.262
## LDRDIVAD 0.685 0.074 9.283 0.000
## AWARE 0.056 0.089 0.629 0.529
## MANAGE 0.499 0.102 4.879 0.000
##
## PDB WITH
## LDRDIVAD 0.606 0.094 6.483 0.000
## POLID -0.432 0.126 -3.428 0.001
##
## LDRDIVAD WITH
## POLID -0.413 0.116 -3.551 0.000
##
## AWARE WITH
## MANAGE 0.246 0.044 5.625 0.000
##
## Means
## LDRDIVAD 0.000 0.071 0.000 1.000
## PDB 0.000 0.078 0.000 1.000
## POLID -0.209 0.104 -2.023 0.043
##
## Intercepts
## AWARE 3.783 0.061 61.916 0.000
## MANAGE 3.784 0.053 71.988 0.000
## DVOICE 2.697 0.410 6.579 0.000
##
## Variances
## LDRDIVAD 1.192 0.110 10.817 0.000
## PDB 1.408 0.130 10.817 0.000
## POLID 2.507 0.232 10.817 0.000
##
## Residual Variances
## AWARE 0.723 0.067 10.817 0.000
## MANAGE 0.535 0.049 10.817 0.000
## DVOICE 1.124 0.104 10.817 0.000
##
##
## QUALITY OF NUMERICAL RESULTS
##
## Condition Number for the Information Matrix 0.148E-03
## (ratio of smallest to largest eigenvalue)
##
##
## PLOT INFORMATION
##
## The following plots are available:
##
## Loop plots
##
## Beginning Time: 13:12:34
## Ending Time: 13:12:34
## Elapsed Time: 00:00:00
##
##
##
## MUTHEN & MUTHEN
## 3463 Stoner Ave.
## Los Angeles, CA 90066
##
## Tel: (310) 391-9971
## Fax: (310) 391-8971
## Web: www.StatModel.com
## Support: Support@StatModel.com
##
## Copyright (c) 1998-2024 Muthen & Muthenres <- readModels("Mplus Syntax/Study2_Moderated Mediation_DVoice.out")
# Extract coefficients
a_int <- res$parameters$unstandardized$est[3] # Effect of XW on M (a-path)
b_est <- res$parameters$unstandardized$est[10] # Effect of M on Y (b-path)
# Extract standard errors
a_int_se <- res$parameters$unstandardized$se[3]
b_se <- res$parameters$unstandardized$se[10]
# 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: 0.004592## Standard error: 0.008530261## Monte Carlo 90% CI: [ -0.007623664 , 0.01998587 ]Moderated Mediation (Intergroup-Management Efficacy and Diversity Voice)
# Extract coefficients
a_int <- res$parameters$unstandardized$est[6] # Effect of XW on M (a-path)
b_est <- res$parameters$unstandardized$est[11] # Effect of M on Y (b-path)
# Extract standard errors
a_int_se <- res$parameters$unstandardized$se[6]
b_se <- res$parameters$unstandardized$se[11]
# 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: 0.055888## Standard error: 0.02160316## Monte Carlo 99% CI: [ 0.008736466 , 0.120739 ]# Conditional Indirect Effect for High and Low Pro-Diversity Attitudes
# Set moderator values (e.g., ±1 SD)
PDB_low <- -1.19 # 1 SD below mean
PDB_high <- 1.19 # 1 SD above mean
# Extract coefficient and standard error for leader diversity advocacy
a_main <- res$parameters$unstandardized$est[5] # Effect of X on M (a-path)
a_main_se <- res$parameters$unstandardized$se[5]
# Compute conditional a-paths
a_low <- a_main + a_int * PDB_low
a_high <- a_main + a_int * PDB_high
# Compute SEs of conditional a-paths
a_low_se <- sqrt(a_main_se^2 + (PDB_low^2 * a_int_se^2))
a_high_se <- sqrt(a_main_se^2 + (PDB_high^2 * a_int_se^2))
# Compute Monte Carlo CI for indirect effect at low PDB
mc_ci_low <- medci(mu.x = a_low, mu.y = b_est,
se.x = a_low_se, se.y = b_se,
rho = 0, alpha = 0.10, sims = 10000, method = "parametric")
# Compute Monte Carlo CI for indirect effect at high PDB
mc_ci_high <- medci(mu.x = a_high, mu.y = b_est,
se.x = a_high_se, se.y = b_se,
rho = 0, alpha = 0.01, sims = 10000, method = "parametric")##
## --- Conditional Indirect Effects ---## At LOW PDB (-1 SD):## Indirect effect estimate: 0.0323## Standard error (LOW PDB): 0.03533## Monte Carlo 90% CI: [ -0.023 , 0.092 ]## At HIGH PDB (+1 SD):## Indirect effect estimate: 0.165## Standard error (HIGH PDB): 0.04844## Monte Carlo 99% CI: [ 0.06 , 0.309 ]