Load Data
# Study 2
load("Study2.RData")
Descriptives
#TEST ASSUMPTIONS
mardiaSkew(df[, c("AMBDIS", "DSEMGMT", "M1", "M2", "Y1", "Y2")])
## b1d chi df p
## 3.190 127.591 56.000 0.000
mardiaKurtosis(df[, c("AMBDIS", "DSEMGMT", "M1", "M2", "Y1", "Y2")])
## b2d z p
## 48.418 0.330 0.741
describe(df[, c("AMBDIS", "DSEMGMT", "M1", "M2", "Y1", "Y2")])
## vars n mean sd median trimmed mad min max range skew kurtosis
## AMBDIS 1 240 2.26 0.78 2.00 2.19 0.74 1.25 5.0 3.75 0.77 0.32
## DSEMGMT 2 240 3.57 1.00 3.75 3.63 1.11 1.00 5.0 4.00 -0.48 -0.54
## M1 3 240 2.64 1.13 2.75 2.61 1.48 1.00 5.0 4.00 0.09 -1.09
## M2 4 240 3.27 1.04 3.50 3.33 0.74 1.00 5.0 4.00 -0.55 -0.48
## Y1 5 240 2.32 0.84 2.20 2.29 0.89 1.00 4.4 3.40 0.21 -0.73
## Y2 6 240 2.67 1.05 2.67 2.66 1.24 1.00 5.0 4.00 0.08 -0.88
## se
## AMBDIS 0.05
## DSEMGMT 0.06
## M1 0.07
## M2 0.07
## Y1 0.05
## Y2 0.07
Correlation Table
corr_df <- df[c("AMBDIS", "DSEMGMT", "M1", "M2", "Y1", "Y2")]
apa.cor.table(data = corr_df,
filename = "Study2Correlation.doc",
table.number = 3)
##
##
## Table 3
##
## Means, standard deviations, and correlations with confidence intervals
##
##
## Variable M SD 1 2 3 4
## 1. AMBDIS 2.26 0.78
##
## 2. DSEMGMT 3.57 1.00 .05
## [-.08, .18]
##
## 3. M1 2.64 1.13 .36** .15*
## [.25, .47] [.02, .27]
##
## 4. M2 3.27 1.04 .26** .36** .31**
## [.14, .38] [.25, .47] [.19, .42]
##
## 5. Y1 2.31 0.84 .17** -.20** .27** -.06
## [.04, .29] [-.32, -.08] [.15, .39] [-.18, .07]
##
## 6. Y2 2.67 1.05 .29** .45** .34** .39**
## [.17, .40] [.35, .55] [.22, .45] [.28, .50]
##
## 5
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## -.07
## [-.19, .06]
##
##
## 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.
##
Sex, Race, Age, and Education
## # A tibble: 3 × 2
## sex n
## <dbl+lbl> <int>
## 1 1 [Male] 114
## 2 2 [Female] 46
## 3 NA 80
## # A tibble: 3 × 2
## SexOrnt n
## <dbl+lbl> <int>
## 1 11 [Heterosexual or straight] 206
## 2 12 [Gay or lesbian] 11
## 3 13 [Bisexual] 23
## # A tibble: 6 × 2
## Race n
## <dbl+lbl> <int>
## 1 1 [White] 151
## 2 2 [Black or African American] 50
## 3 3 [Hispanic/Latinx] 12
## 4 4 [Native American or Alaska Native] 2
## 5 5 [Asian] 21
## 6 7 [Two or More Races (please specify)] 4
## # A tibble: 7 × 2
## Education n
## <dbl+lbl> <int>
## 1 2 [High school graduate (high school diploma or equivalent including GE… 16
## 2 3 [Some college but no degree] 32
## 3 4 [Associate degree in college (2-year)] 20
## 4 5 [Bachelor's degree in college (4-year)] 124
## 5 6 [Master's degree] 36
## 6 7 [Doctoral degree] 6
## 7 8 [Professional degree (JD, MD)] 6
##
## 1 2
## 0.7125 0.2875
##
## 11 12 13
## 0.85833333 0.04583333 0.09583333
##
## 1 2 3 4 5 7
## 0.629166667 0.208333333 0.050000000 0.008333333 0.087500000 0.016666667
##
## 2 3 4 5 6 7 8
## 0.06666667 0.13333333 0.08333333 0.51666667 0.15000000 0.02500000 0.02500000
## [1] 37.79167
## [1] 9.34454
Tenure
## [1] 7.141667
## [1] 6.037757
Reliabilities (Cronbach’s alphas)
## Scale Raw_Alpha
## 1 amdisr 0.86
## 2 hinapr 0.89
## 3 chaapr 0.90
## 4 scwthr 0.84
## 5 dvr 0.94
## 6 dmser 0.91
Indirect Effect: Ambient Discrimination → Threat Appraisal → Social
Withdrawal
# Study 2
estimates <- parameterEstimates(fit_Study2, ci = TRUE, boot.ci.type = "bca.simple")
a_path <- estimates[estimates$label == "a1", "est"]
a_path_se <- estimates[estimates$label == "a1", "se"]
b_path <- estimates[estimates$label == "b11", "est"]
b_path_se <- estimates[estimates$label == "b11", "se"]
# Compute Monte Carlo confidence interval
mc_ci <- medci(mu.x = a_path, mu.y = b_path, se.x = a_path_se, se.y = b_path_se,
rho = 0, alpha = .05, sims = 10000, method = "parametric")
cat("indirect effect (Study 2):", a_path * b_path, "\n")
## indirect effect (Study 2): 0.1126643
cat("Monte Carlo 95% CI (Study 2): [", mc_ci$`95% CI`[1], ",", mc_ci$`95% CI`[2], "]\n")
## Monte Carlo 95% CI (Study 2): [ 0.05051393 , 0.1875219 ]
Indirect Effect: Ambient Discrimination → Challenge Appraisal →
Diversity Voice
# Study 2
estimates <- parameterEstimates(fit_Study2, ci = TRUE, boot.ci.type = "bca.simple")
a_path <- estimates[estimates$label == "a2", "est"]
a_path_se <- estimates[estimates$label == "a2", "se"]
b_path <- estimates[estimates$label == "b22", "est"]
b_path_se <- estimates[estimates$label == "b22", "se"]
# Compute Monte Carlo confidence interval
mc_ci <- medci(mu.x = a_path, mu.y = b_path, se.x = a_path_se, se.y = b_path_se,
rho = 0, alpha = .05, sims = 10000, method = "parametric")
cat("indirect effect (Study 2):", a_path * b_path, "\n")
## indirect effect (Study 2): 0.1054376
cat("Monte Carlo 95% CI (Study 2): [", mc_ci$`95% CI`[1], ",", mc_ci$`95% CI`[2], "]\n")
## Monte Carlo 95% CI (Study 2): [ 0.04762055 , 0.1775846 ]
Moderated Mediation Model
model <- '
M1 ~ a1*X + a1w*XW + d1*W
M2 ~ a2*X + a2w*XW + d2*W
Y1 ~ X + W + b11*M1 + b21*M2
Y2 ~ X + W + b12*M1 + b22*M2
# Low/High Ambient Discrimination
LowAmbdis := -.78
HighAmbdis := .78
# Low/High Diversity Management Efficacy
LowEfficacy := -1
HighEfficacy := 1
# Simple Slopes for Low/High Diversity Management Self-Efficacy
SS_LowEfficacy_challenge := a2 + a2w*LowEfficacy
SS_HighEfficacy_challenge := a2 + a2w*HighEfficacy
# Compute predicted values for plotting at Low/High values of X and W (M2 intercept = 3.261)
LowEfficacy_LowAmbdis := (a2 + a2w*LowEfficacy)*LowAmbdis + (3.261 + d2*LowEfficacy)
LowEfficacy_HighAmbdis := (a2 + a2w*LowEfficacy)*HighAmbdis + (3.261 + d2*LowEfficacy)
HighEfficacy_LowAmbdis := (a2 + a2w*HighEfficacy)*LowAmbdis + (3.261 + d2*HighEfficacy)
HighEfficacy_HighAmbdis := (a2 + a2w*HighEfficacy)*HighAmbdis + (3.261 + d2*HighEfficacy)
'
results <- sem(model,
data = df,
estimator = "MLR",
se = "robust",
missing = "fiml")
summary(results, standardized = TRUE, rsquare = TRUE)
## lavaan 0.7-3 ended normally after 6 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 23
##
## Number of observations 240
## Number of missing patterns 1
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 10.214 10.975
## Degrees of freedom 3 3
## P-value (Chi-square) 0.017 0.012
## Scaling correction factor 0.931
## Yuan-Bentler correction (Mplus variant)
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M1 ~
## X (a1) 0.523 0.092 5.712 0.000 0.523 0.361
## XW (a1w) -0.031 0.080 -0.390 0.697 -0.031 -0.021
## W (d1) 0.148 0.067 2.219 0.026 0.148 0.131
## M2 ~
## X (a2) 0.298 0.075 3.991 0.000 0.298 0.224
## XW (a2w) 0.178 0.087 2.048 0.041 0.178 0.130
## W (d2) 0.372 0.067 5.591 0.000 0.372 0.358
## Y1 ~
## X 0.103 0.075 1.374 0.169 0.103 0.095
## W -0.184 0.052 -3.561 0.000 -0.184 -0.218
## M1 (b11) 0.224 0.053 4.215 0.000 0.224 0.300
## M2 (b21) -0.076 0.055 -1.388 0.165 -0.076 -0.093
## Y2 ~
## X 0.223 0.077 2.905 0.004 0.223 0.167
## W 0.375 0.066 5.712 0.000 0.375 0.360
## M1 (b12) 0.160 0.059 2.713 0.007 0.160 0.174
## M2 (b22) 0.168 0.065 2.587 0.010 0.168 0.168
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .Y1 ~~
## .Y2 -0.054 0.047 -1.166 0.244 -0.054 -0.083
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1 2.641 0.067 39.275 0.000 2.641 2.346
## .M2 3.261 0.060 54.733 0.000 3.261 3.149
## .Y1 1.972 0.217 9.092 0.000 1.972 2.342
## .Y2 1.697 0.248 6.843 0.000 1.697 1.635
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1 1.077 0.085 12.702 0.000 1.077 0.849
## .M2 0.847 0.076 11.102 0.000 0.847 0.790
## .Y1 0.598 0.050 12.069 0.000 0.598 0.843
## .Y2 0.723 0.061 11.856 0.000 0.723 0.671
##
## R-Square:
## Estimate
## M1 0.151
## M2 0.210
## Y1 0.157
## Y2 0.329
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## LowAmbdis -0.780 -0.780 -0.780
## HighAmbdis 0.780 0.780 0.780
## LowEfficacy -1.000 -1.000 -1.000
## HighEfficacy 1.000 1.000 1.000
## SS_LwEffccy_ch 0.120 0.124 0.972 0.331 0.120 0.094
## SS_HghEffccy_c 0.476 0.105 4.549 0.000 0.476 0.354
## LwEffccy_LwAmb 2.795 0.129 21.652 0.000 2.795 2.829
## LwEffccy_HghAm 2.983 0.104 28.617 0.000 2.983 2.977
## HghEffccy_LwAm 3.262 0.122 26.754 0.000 3.262 3.343
## HghEffccy_HghA 4.005 0.086 46.708 0.000 4.005 3.895
# CONDITIONAL INDIRECT EFFECTS
estimates <- parameterEstimates(results)
# A-path
a1 <- estimates[estimates$label == "a2", "est"]
a3 <- estimates[estimates$label == "a2w", "est"]
a1_se <- estimates[estimates$label == "a2", "se"]
a3_se <- estimates[estimates$label == "a2w", "se"]
# Conditional a-paths
a_low <- estimates[estimates$label == "SS_LowEfficacy_challenge", "est"]
a_high <- estimates[estimates$label == "SS_HighEfficacy_challenge", "est"]
# SE for conditional a-paths
a_low_se <- estimates[estimates$label == "SS_LowEfficacy_challenge", "se"]
a_high_se <- estimates[estimates$label == "SS_HighEfficacy_challenge", "se"]
# B-path
b1 <- estimates[estimates$label == "b11", "est"]
b1_se <- estimates[estimates$label == "b11", "se"]
# Compute Monte Carlo CI for Low Diversity Management Self-Efficacy
mc_ci_low <- medci(mu.x = a_low, mu.y = b1,
se.x = a_low_se, se.y = b1_se,
rho = 0, alpha = .05, sims = 10000)
# Compute Monte Carlo CI for High Diversity Management Self-Efficacy
mc_ci_high <- medci(mu.x = a_high, mu.y = b1,
se.x = a_high_se, se.y = b1_se,
rho = 0, alpha = .05, sims = 10000)
# Conditional ab
cat("Indirect Effect for Low Diversity Management Self-Efficacy:", a_low * b1, "\n")
## Indirect Effect for Low Diversity Management Self-Efficacy: 0.02696978
cat("Monte Carlo 95% CI (Low Diversity Management Self-Efficacy): [", round(mc_ci_low$`95% CI`, 3), "]\n\n")
## Monte Carlo 95% CI (Low Diversity Management Self-Efficacy): [ -0.027 0.089 ]
cat("Indirect Effect for High Diversity Management Self-Efficacy:", a_high * b1, "\n")
## Indirect Effect for High Diversity Management Self-Efficacy: 0.1067388
cat("Monte Carlo 95% CI (High Diversity Management Self-Efficacy): [", round(mc_ci_high$`95% CI`, 3), "]\n")
## Monte Carlo 95% CI (High Diversity Management Self-Efficacy): [ 0.046 0.183 ]
# Figure: Study 2 Moderating Effect of Challenge Appraisal
# Extract parameter estimates
estimates <- parameterEstimates(results)
int_M2 <- estimates$est[estimates$lhs == "M2" &
estimates$op == "~1"]
# Define moderator levels (efficacy) and predictor levels (X)
LowEfficacy <- 0 - sd(df$W, na.rm = TRUE)
HighEfficacy <- 0 + sd(df$W, na.rm = TRUE)
X_LOW <- -sd(df$X)
X_HIGH <- sd(df$X)
#Challenge appraisal
# Coefficients
a2 <- estimates$est[estimates$label == "a2"] # X → M2
a2w <- estimates$est[estimates$label == "a2w"] # XW → M2
d2 <- estimates$est[estimates$label == "d2"] # W → M2
# Low efficacy
LOWEFF_LOWX <- int_M2 + a2*X_LOW + a2w*(X_LOW * LowEfficacy) + d2*LowEfficacy
LOWEFF_HIGHX <- int_M2 + a2*X_HIGH + a2w*(X_HIGH * LowEfficacy) + d2*LowEfficacy
# High efficacy
HIGHEFF_LOWX <- int_M2 + a2*X_LOW + a2w*(X_LOW * HighEfficacy) + d2*HighEfficacy
HIGHEFF_HIGHX <- int_M2 + a2*X_HIGH + a2w*(X_HIGH * HighEfficacy) + d2*HighEfficacy
# Data frame for plotting the interaction
plot_data <- data.frame(
Efficacy = rep(c("Low efficacy", "High efficacy"), each = 2),
X_Level = rep(c("Low", "High"), times = 2),
Predicted_M2 = c(
LOWEFF_LOWX, LOWEFF_HIGHX,
HIGHEFF_LOWX, HIGHEFF_HIGHX
)
)
plot_data$X_Level <- factor(plot_data$X_Level, levels = c("Low", "High"))
plot_data$Efficacy <- factor(plot_data$Efficacy, levels = c("Low efficacy", "High efficacy"))
# Plot interaction
ggplot(plot_data, aes(x = X_Level, y = Predicted_M2,
group = Efficacy, color = Efficacy)) +
geom_line(linewidth = 1.2) +
geom_point(size = 3) +
scale_color_manual(
values = c(
"Low efficacy" = "grey50",
"High efficacy" = "black"
)
) +
labs(
x = "Ambient Racial Discrimination",
y = "Challenge Appraisal",
color = "Intergroup Management Self-Efficacy"
) +
theme_classic(base_size = 14) +
theme(
legend.position = "right",
axis.line = element_line(color = "black", linewidth = 0.6),
axis.ticks = element_line(color = "black"),
axis.title = element_text(size = 12),
axis.text = element_text(size = 12),
legend.title = element_text(size = 12),
legend.text = element_text(size = 12),
) + scale_y_continuous(
breaks = 1:5
) +
coord_cartesian(ylim = c(1, 5))

Exploratory Second-Stage Moderation
df$M1_c <- df$M1 - mean(df$M1, na.rm = TRUE)
mean(df$M1_c, na.rm = TRUE)
## [1] -1.757853e-17
df$M2_c <- df$M2 - mean(df$M2, na.rm = TRUE)
mean(df$M2_c, na.rm = TRUE)
## [1] 1.808738e-16
df$XW1 <- df$M1_c * df$W
df$XW2 <- df$M2_c * df$W
SUPPLEMENTARY - SECOND STAGE MODERATION
model <- '
M1 ~ a1*X + W
M2 ~ a2*X + W
Y1 ~ d1*W + b1*M1 + M2 + b1w*XW1 + X
Y2 ~ d2*W + M1 + b2*M2 + b2w*XW2 + X
M1 ~~ M2
Y1 ~~ Y2
# Low/High Diversity Management Efficacy
LowEfficacy := -1
HighEfficacy := 1
# Simple Slopes for Low/High Diversity Management Self-Efficacy
SS_LowEfficacy_threat := b1 + b1w*LowEfficacy
SS_HighEfficacy_threat := b1 + b1w*HighEfficacy
'
results <- sem(model,
data = df,
estimator = "MLR",
se = "robust",
missing = "fiml")
summary(results, standardized = TRUE, fit.measures = TRUE, rsquare = TRUE)
## lavaan 0.7-3 ended normally after 22 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 24
##
## Number of observations 240
## Number of missing patterns 1
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 8.381 5.699
## Degrees of freedom 6 6
## P-value (Chi-square) 0.212 0.458
## Scaling correction factor 1.471
## Yuan-Bentler correction (Mplus variant)
##
## Model Test Baseline Model:
##
## Test statistic 251.231 206.813
## Degrees of freedom 22 22
## P-value 0.000 0.000
## Scaling correction factor 1.215
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.990 1.000
## Tucker-Lewis Index (TLI) 0.962 1.006
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.010
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1245.220 -1245.220
## Scaling correction factor 1.014
## for the MLR correction
## Loglikelihood unrestricted model (H1) -1241.030 -1241.030
## Scaling correction factor 1.106
## for the MLR correction
##
## Akaike (AIC) 2538.441 2538.441
## Bayesian (BIC) 2621.976 2621.976
## Sample-size adjusted Bayesian (SABIC) 2545.902 2545.902
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.041 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.099 0.071
## P-value H_0: RMSEA <= 0.050 0.530 0.822
## P-value H_0: RMSEA >= 0.080 0.159 0.023
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.099
## P-value H_0: Robust RMSEA <= 0.050 0.689
## P-value H_0: Robust RMSEA >= 0.080 0.121
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.026 0.026
##
## Goodness of Fit Index:
##
## Goodness of Fit Index (GFI) 0.998
## 90 Percent confidence interval - lower 0.985
## 90 Percent confidence interval - upper 1.000
##
## Robust GFI 1.000
## 90 Percent confidence interval - lower 0.986
## 90 Percent confidence interval - upper 1.000
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M1 ~
## X (a1) 0.518 0.090 5.779 0.000 0.518 0.358
## W 0.149 0.067 2.230 0.026 0.149 0.132
## M2 ~
## X (a2) 0.329 0.073 4.525 0.000 0.329 0.247
## W 0.366 0.072 5.115 0.000 0.366 0.352
## Y1 ~
## W (d1) -0.210 0.053 -3.972 0.000 -0.210 -0.249
## M1 (b1) 0.228 0.051 4.451 0.000 0.228 0.306
## M2 -0.059 0.054 -1.081 0.280 -0.059 -0.073
## XW1 (b1w) -0.089 0.039 -2.266 0.023 -0.089 -0.123
## X 0.101 0.074 1.364 0.172 0.101 0.094
## Y2 ~
## W (d2) 0.372 0.067 5.586 0.000 0.372 0.355
## M1 0.161 0.059 2.726 0.006 0.161 0.174
## M2 (b2) 0.168 0.065 2.570 0.010 0.168 0.167
## XW2 (b2w) -0.020 0.050 -0.403 0.687 -0.020 -0.022
## X 0.227 0.078 2.928 0.003 0.227 0.169
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1 ~~
## .M2 0.191 0.063 3.010 0.003 0.191 0.198
## .Y1 ~~
## .Y2 -0.056 0.046 -1.220 0.222 -0.056 -0.086
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1 2.640 0.067 39.398 0.000 2.640 2.345
## .M2 3.268 0.060 54.443 0.000 3.268 3.156
## .Y1 1.921 0.209 9.188 0.000 1.921 2.290
## .Y2 1.702 0.251 6.768 0.000 1.702 1.631
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .M1 1.077 0.084 12.790 0.000 1.077 0.850
## .M2 0.865 0.082 10.526 0.000 0.865 0.806
## .Y1 0.588 0.049 12.050 0.000 0.588 0.835
## .Y2 0.722 0.061 11.841 0.000 0.722 0.664
##
## R-Square:
## Estimate
## M1 0.150
## M2 0.194
## Y1 0.165
## Y2 0.336
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## LowEfficacy -1.000 -1.000 -1.000
## HighEfficacy 1.000 1.000 1.000
## SS_LwEffccy_th 0.317 0.062 5.150 0.000 0.317 0.428
## SS_HghEffccy_t 0.139 0.067 2.056 0.040 0.139 0.183
# CONDITIONAL INDIRECT EFFECTS
estimates <- parameterEstimates(results)
# B-path
b1 <- estimates[estimates$label == "b1", "est"]
b3 <- estimates[estimates$label == "b1w", "est"]
b1_se <- estimates[estimates$label == "b1", "se"]
b3_se <- estimates[estimates$label == "b1w", "se"]
# Conditional b-paths
b_low <- estimates[estimates$label == "SS_LowEfficacy_threat", "est"]
b_high <- estimates[estimates$label == "SS_HighEfficacy_threat", "est"]
# SE for conditional a-paths
b_low_se <- estimates[estimates$label == "SS_LowEfficacy_threat", "se"]
b_high_se <- estimates[estimates$label == "SS_HighEfficacy_threat", "se"]
# A-path
a1 <- estimates[estimates$label == "a1", "est"]
a1_se <- estimates[estimates$label == "a1", "se"]
# Compute Monte Carlo CI for Low Diversity Management Self-Efficacy
mc_ci_low <- medci(mu.x = a1, mu.y = b_low,
se.x = a1_se, se.y = b_low_se,
rho = 0, alpha = .05, sims = 10000)
# Compute Monte Carlo CI for High Diversity Management Self-Efficacy
mc_ci_high <- medci(mu.x = a1, mu.y = b_high,
se.x = a1_se, se.y = b_high_se,
rho = 0, alpha = .05, sims = 10000)
# Conditional ab
cat("Indirect Effect for Low Diversity Management Self-Efficacy:", a1 * b_low, "\n")
## Indirect Effect for Low Diversity Management Self-Efficacy: 0.1641423
cat("Monte Carlo 95% CI (Low Diversity Management Self-Efficacy): [", round(mc_ci_low$`95% CI`, 3), "]\n\n")
## Monte Carlo 95% CI (Low Diversity Management Self-Efficacy): [ 0.088 0.256 ]
cat("Indirect Effect for High Diversity Management Self-Efficacy:", a1 * b_high, "\n")
## Indirect Effect for High Diversity Management Self-Efficacy: 0.0717987
cat("Monte Carlo 95% CI (High Diversity Management Self-Efficacy): [", round(mc_ci_high$`95% CI`, 3), "]\n")
## Monte Carlo 95% CI (High Diversity Management Self-Efficacy): [ 0.003 0.151 ]