#read in data
setwd("~/Downloads/foldah")
ANES <- read.csv("ANES_clean_merged2.csv")
ANES_clean <- subset(ANES, !is.na(V240106b))
ANES_clean$Race3 <- with(ANES_clean,
ifelse(White == 1, "White",
ifelse(Black == 1, "Black",
ifelse(Hispanic == 1, "Hispanic",
NA
))))
ANES_clean$Race3 <- factor(ANES_clean$Race3,
levels = c("White", "Black", "Hispanic"))
ANES_cleanest <- subset(ANES_clean, !is.na(Race3))
library(lavaan)## This is lavaan 0.6-19
## lavaan is FREE software! Please report any bugs.library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union#RICLPM IPE + CA, MLR
RICLPM1 <- '
# Create between components (random intercepts)
RIipe =~ 1*in_eff_w1 + 1*in_eff_w2 + 1*in_eff_w3
RIca =~ 1*c_act_w1 + 1*c_act_w2 + 1*c_act_w3
# Create within-person centered variables
wipe1 =~ 1*in_eff_w1
wipe2 =~ 1*in_eff_w2
wipe3 =~ 1*in_eff_w3
wca1 =~ 1*c_act_w1
wca2 =~ 1*c_act_w2
wca3 =~ 1*c_act_w3
# Estimate lagged effects between within-person centered variables
wipe2 + wca2 ~ wipe1 + wca1
wipe3 + wca3 ~ wipe2 + wca2
# Estimate covariance between within-person centered variables at first wave
wipe1 ~~ wca1 # Covariance
# Estimate covariances between residuals of within-person centered variables
# (i.e., innovations)
wipe2 ~~ wca2
wipe3 ~~ wca3
# Estimate variance and covariance of random intercepts
RIipe ~~ RIipe
RIca ~~ RIca
RIipe ~~ RIca
# Estimate (residual) variance of within-person centered variables
wipe1 ~~ wipe1 # Variances
wca1 ~~ wca1
wipe2 ~~ wipe2 # Residual variances
wca2 ~~ wca2
wipe3 ~~ wipe3
wca3 ~~ wca3'
RICLPM1fit <- lavaan(RICLPM1,
data = ANES_clean,
missing = 'FIML',
sampling.weights = 'V240106b',
estimator = "MLR",
meanstructure = T,
int.ov.free = T)
summary(RICLPM1fit, fit.measures = T, standardized = T, rsquare = T)## lavaan 0.6-19 ended normally after 73 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 26
##
## Number of observations 2070
## Number of missing patterns 12
## Sampling weights variable V240106b
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.486 0.313
## Degrees of freedom 1 1
## P-value (Chi-square) 0.486 0.576
## Scaling correction factor 1.553
## Yuan-Bentler correction (Mplus variant)
##
## Model Test Baseline Model:
##
## Test statistic 2871.247 1379.513
## Degrees of freedom 15 15
## P-value 0.000 0.000
## Scaling correction factor 2.081
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.003 1.008
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.006
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -5534.689 -5534.689
## Scaling correction factor 2.265
## for the MLR correction
## Loglikelihood unrestricted model (H1) -5534.446 -5534.446
## Scaling correction factor 2.239
## for the MLR correction
##
## Akaike (AIC) 11121.378 11121.378
## Bayesian (BIC) 11267.895 11267.895
## Sample-size adjusted Bayesian (SABIC) 11185.291 11185.291
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.051 0.036
## P-value H_0: RMSEA <= 0.050 0.944 0.991
## P-value H_0: RMSEA >= 0.080 0.002 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.060
## P-value H_0: Robust RMSEA <= 0.050 0.905
## P-value H_0: Robust RMSEA >= 0.080 0.009
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.003 0.003
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIipe =~
## in_eff_w1 1.000 0.548 0.693
## in_eff_w2 1.000 0.548 0.645
## in_eff_w3 1.000 0.548 0.659
## RIca =~
## c_act_w1 1.000 0.112 0.447
## c_act_w2 1.000 0.112 0.469
## c_act_w3 1.000 0.112 0.627
## wipe1 =~
## in_eff_w1 1.000 0.571 0.721
## wipe2 =~
## in_eff_w2 1.000 0.650 0.764
## wipe3 =~
## in_eff_w3 1.000 0.626 0.752
## wca1 =~
## c_act_w1 1.000 0.224 0.894
## wca2 =~
## c_act_w2 1.000 0.211 0.883
## wca3 =~
## c_act_w3 1.000 0.139 0.779
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wipe2 ~
## wipe1 0.146 0.073 1.987 0.047 0.128 0.128
## wca1 0.403 0.122 3.308 0.001 0.139 0.139
## wca2 ~
## wipe1 0.046 0.015 3.061 0.002 0.126 0.126
## wca1 0.251 0.041 6.056 0.000 0.266 0.266
## wipe3 ~
## wipe2 0.325 0.048 6.769 0.000 0.338 0.338
## wca2 0.358 0.115 3.120 0.002 0.121 0.121
## wca3 ~
## wipe2 0.013 0.010 1.407 0.159 0.063 0.063
## wca2 0.029 0.048 0.603 0.546 0.044 0.044
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wipe1 ~~
## wca1 0.030 0.006 4.804 0.000 0.233 0.233
## .wipe2 ~~
## .wca2 0.018 0.005 3.690 0.000 0.142 0.142
## .wipe3 ~~
## .wca3 0.011 0.004 2.628 0.009 0.134 0.134
## RIipe ~~
## RIca 0.017 0.005 3.795 0.000 0.283 0.283
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .in_eff_w1 3.142 0.024 132.679 0.000 3.142 3.970
## .in_eff_w2 3.259 0.026 124.842 0.000 3.259 3.831
## .in_eff_w3 3.263 0.025 128.357 0.000 3.263 3.920
## .c_act_w1 0.192 0.007 26.905 0.000 0.192 0.768
## .c_act_w2 0.159 0.007 23.009 0.000 0.159 0.665
## .c_act_w3 0.078 0.005 14.840 0.000 0.078 0.437
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIipe 0.301 0.029 10.369 0.000 1.000 1.000
## RIca 0.013 0.002 5.759 0.000 1.000 1.000
## wipe1 0.326 0.028 11.598 0.000 1.000 1.000
## wca1 0.050 0.003 17.213 0.000 1.000 1.000
## .wipe2 0.405 0.032 12.649 0.000 0.956 0.956
## .wca2 0.040 0.003 15.625 0.000 0.898 0.898
## .wipe3 0.335 0.019 17.451 0.000 0.855 0.855
## .wca3 0.019 0.003 6.048 0.000 0.993 0.993
## .in_eff_w1 0.000 0.000 0.000
## .in_eff_w2 0.000 0.000 0.000
## .in_eff_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wipe2 0.044
## wca2 0.102
## wipe3 0.145
## wca3 0.007
## in_eff_w1 1.000
## in_eff_w2 1.000
## in_eff_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000#RICLPM IPE + CA, MLR, Multi-Group by Race
RICLPM2 <- '
# Create between components (random intercepts)
RIipe =~ 1*in_eff_w1 + 1*in_eff_w2 + 1*in_eff_w3
RIca =~ 1*c_act_w1 + 1*c_act_w2 + 1*c_act_w3
# Create within-person centered variables
wipe1 =~ 1*in_eff_w1
wipe2 =~ 1*in_eff_w2
wipe3 =~ 1*in_eff_w3
wca1 =~ 1*c_act_w1
wca2 =~ 1*c_act_w2
wca3 =~ 1*c_act_w3
# Estimate lagged effects between within-person centered variables
wipe2 + wca2 ~ wipe1 + wca1
wipe3 + wca3 ~ wipe2 + wca2
# Estimate covariance between within-person centered variables at first wave
wipe1 ~~ wca1 # Covariance
# Estimate covariances between residuals of within-person centered variables
# (i.e., innovations)
wipe2 ~~ wca2
wipe3 ~~ wca3
# Estimate variance and covariance of random intercepts
RIipe ~~ RIipe
RIca ~~ RIca
RIipe ~~ RIca
# Estimate (residual) variance of within-person centered variables
wipe1 ~~ wipe1 # Variances
wca1 ~~ wca1
wipe2 ~~ wipe2 # Residual variances
wca2 ~~ wca2
wipe3 ~~ wipe3
wca3 ~~ wca3'
RICLPM2fit <- lavaan(RICLPM2,
data = ANES_cleanest,
missing = 'FIML',
sampling.weights = 'V240106b',
estimator = "ML",
group = 'Race3',
meanstructure = T,
int.ov.free = T)
summary(RICLPM2fit, fit.measures = T, standardized = T, rsquare = T)## lavaan 0.6-19 ended normally after 179 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 78
##
## Number of observations per group:
## White 1537
## Black 161
## Hispanic 184
## Number of missing patterns per group:
## White 11
## Black 2
## Hispanic 5
## Sampling weights variable V240106b
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 4.450 2.442
## Degrees of freedom 3 3
## P-value (Chi-square) 0.217 0.486
## Scaling correction factor 1.822
## Yuan-Bentler correction (Mplus variant)
## Test statistic for each group:
## White 0.151 0.151
## Black 0.143 0.143
## Hispanic 2.148 2.148
##
## Model Test Baseline Model:
##
## Test statistic 2645.972 1198.768
## Degrees of freedom 45 45
## P-value 0.000 0.000
## Scaling correction factor 2.207
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.999 1.000
## Tucker-Lewis Index (TLI) 0.992 1.007
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.006
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -4899.561 -4899.561
## Scaling correction factor 2.671
## for the MLR correction
## Loglikelihood unrestricted model (H1) -4897.336 -4897.336
## Scaling correction factor 2.640
## for the MLR correction
##
## Akaike (AIC) 9955.122 9955.122
## Bayesian (BIC) 10387.249 10387.249
## Sample-size adjusted Bayesian (SABIC) 10139.444 10139.444
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.028 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.078 0.048
## P-value H_0: RMSEA <= 0.050 0.707 0.959
## P-value H_0: RMSEA >= 0.080 0.041 0.001
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.084
## P-value H_0: Robust RMSEA <= 0.050 0.765
## P-value H_0: Robust RMSEA >= 0.080 0.064
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.006 0.006
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
##
## Group 1 [White]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIipe =~
## in_eff_w1 1.000 0.567 0.715
## in_eff_w2 1.000 0.567 0.663
## in_eff_w3 1.000 0.567 0.683
## RIca =~
## c_act_w1 1.000 0.115 0.459
## c_act_w2 1.000 0.115 0.481
## c_act_w3 1.000 0.115 0.656
## wipe1 =~
## in_eff_w1 1.000 0.554 0.699
## wipe2 =~
## in_eff_w2 1.000 0.641 0.749
## wipe3 =~
## in_eff_w3 1.000 0.607 0.730
## wca1 =~
## c_act_w1 1.000 0.222 0.888
## wca2 =~
## c_act_w2 1.000 0.209 0.877
## wca3 =~
## c_act_w3 1.000 0.132 0.755
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wipe2 ~
## wipe1 0.185 0.084 2.205 0.027 0.160 0.160
## wca1 0.405 0.134 3.023 0.003 0.140 0.140
## wca2 ~
## wipe1 0.063 0.019 3.414 0.001 0.168 0.168
## wca1 0.277 0.048 5.794 0.000 0.293 0.293
## wipe3 ~
## wipe2 0.332 0.058 5.762 0.000 0.351 0.351
## wca2 0.269 0.140 1.919 0.055 0.093 0.093
## wca3 ~
## wipe2 0.016 0.010 1.578 0.115 0.079 0.079
## wca2 0.035 0.052 0.676 0.499 0.056 0.056
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wipe1 ~~
## wca1 0.026 0.007 3.529 0.000 0.211 0.211
## .wipe2 ~~
## .wca2 0.014 0.006 2.433 0.015 0.119 0.119
## .wipe3 ~~
## .wca3 0.006 0.003 1.695 0.090 0.078 0.078
## RIipe ~~
## RIca 0.024 0.005 4.607 0.000 0.367 0.367
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .in_eff_w1 3.134 0.027 114.768 0.000 3.134 3.951
## .in_eff_w2 3.260 0.030 106.909 0.000 3.260 3.808
## .in_eff_w3 3.253 0.029 112.050 0.000 3.253 3.916
## .c_act_w1 0.187 0.008 22.785 0.000 0.187 0.750
## .c_act_w2 0.158 0.008 19.992 0.000 0.158 0.665
## .c_act_w3 0.077 0.006 14.005 0.000 0.077 0.442
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIipe 0.322 0.033 9.696 0.000 1.000 1.000
## RIca 0.013 0.003 4.966 0.000 1.000 1.000
## wipe1 0.307 0.032 9.723 0.000 1.000 1.000
## wca1 0.049 0.004 13.052 0.000 1.000 1.000
## .wipe2 0.389 0.035 11.178 0.000 0.945 0.945
## .wca2 0.038 0.003 14.260 0.000 0.865 0.865
## .wipe3 0.315 0.021 14.964 0.000 0.856 0.856
## .wca3 0.017 0.002 7.521 0.000 0.989 0.989
## .in_eff_w1 0.000 0.000 0.000
## .in_eff_w2 0.000 0.000 0.000
## .in_eff_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wipe2 0.055
## wca2 0.135
## wipe3 0.144
## wca3 0.011
## in_eff_w1 1.000
## in_eff_w2 1.000
## in_eff_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000
##
##
## Group 2 [Black]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIipe =~
## in_eff_w1 1.000 0.435 0.542
## in_eff_w2 1.000 0.435 0.539
## in_eff_w3 1.000 0.435 0.538
## RIca =~
## c_act_w1 1.000 0.115 0.450
## c_act_w2 1.000 0.115 0.495
## c_act_w3 1.000 0.115 0.672
## wipe1 =~
## in_eff_w1 1.000 0.675 0.841
## wipe2 =~
## in_eff_w2 1.000 0.679 0.842
## wipe3 =~
## in_eff_w3 1.000 0.680 0.843
## wca1 =~
## c_act_w1 1.000 0.228 0.893
## wca2 =~
## c_act_w2 1.000 0.202 0.869
## wca3 =~
## c_act_w3 1.000 0.127 0.741
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wipe2 ~
## wipe1 0.039 0.226 0.173 0.863 0.039 0.039
## wca1 0.387 0.395 0.979 0.327 0.130 0.130
## wca2 ~
## wipe1 0.006 0.029 0.221 0.825 0.021 0.021
## wca1 0.061 0.102 0.600 0.549 0.069 0.069
## wipe3 ~
## wipe2 0.334 0.170 1.968 0.049 0.334 0.334
## wca2 0.788 0.360 2.191 0.028 0.234 0.234
## wca3 ~
## wipe2 -0.024 0.039 -0.609 0.542 -0.128 -0.128
## wca2 -0.256 0.147 -1.741 0.082 -0.407 -0.407
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wipe1 ~~
## wca1 0.022 0.017 1.330 0.183 0.143 0.143
## .wipe2 ~~
## .wca2 -0.009 0.017 -0.513 0.608 -0.066 -0.066
## .wipe3 ~~
## .wca3 0.030 0.015 1.960 0.050 0.413 0.413
## RIipe ~~
## RIca 0.005 0.010 0.481 0.631 0.094 0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .in_eff_w1 3.196 0.083 38.687 0.000 3.196 3.982
## .in_eff_w2 3.425 0.084 40.752 0.000 3.425 4.249
## .in_eff_w3 3.456 0.083 41.653 0.000 3.456 4.280
## .c_act_w1 0.220 0.025 8.740 0.000 0.220 0.859
## .c_act_w2 0.158 0.023 6.835 0.000 0.158 0.679
## .c_act_w3 0.082 0.020 4.013 0.000 0.082 0.479
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIipe 0.189 0.095 1.986 0.047 1.000 1.000
## RIca 0.013 0.006 2.151 0.031 1.000 1.000
## wipe1 0.455 0.097 4.673 0.000 1.000 1.000
## wca1 0.052 0.008 6.816 0.000 1.000 1.000
## .wipe2 0.452 0.120 3.776 0.000 0.980 0.980
## .wca2 0.040 0.011 3.782 0.000 0.994 0.994
## .wipe3 0.390 0.068 5.771 0.000 0.843 0.843
## .wca3 0.013 0.011 1.229 0.219 0.824 0.824
## .in_eff_w1 0.000 0.000 0.000
## .in_eff_w2 0.000 0.000 0.000
## .in_eff_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wipe2 0.020
## wca2 0.006
## wipe3 0.157
## wca3 0.176
## in_eff_w1 1.000
## in_eff_w2 1.000
## in_eff_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000
##
##
## Group 3 [Hispanic]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIipe =~
## in_eff_w1 1.000 0.426 0.572
## in_eff_w2 1.000 0.426 0.507
## in_eff_w3 1.000 0.426 0.536
## RIca =~
## c_act_w1 1.000 0.084 0.354
## c_act_w2 1.000 0.084 0.372
## c_act_w3 1.000 0.084 0.475
## wipe1 =~
## in_eff_w1 1.000 0.610 0.820
## wipe2 =~
## in_eff_w2 1.000 0.724 0.862
## wipe3 =~
## in_eff_w3 1.000 0.671 0.844
## wca1 =~
## c_act_w1 1.000 0.222 0.935
## wca2 =~
## c_act_w2 1.000 0.210 0.928
## wca3 =~
## c_act_w3 1.000 0.156 0.880
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wipe2 ~
## wipe1 0.322 0.187 1.726 0.084 0.272 0.272
## wca1 0.039 0.410 0.096 0.924 0.012 0.012
## wca2 ~
## wipe1 0.029 0.040 0.737 0.461 0.085 0.085
## wca1 0.216 0.118 1.835 0.067 0.229 0.229
## wipe3 ~
## wipe2 0.378 0.125 3.022 0.003 0.408 0.408
## wca2 0.321 0.318 1.011 0.312 0.101 0.101
## wca3 ~
## wipe2 0.056 0.027 2.090 0.037 0.259 0.259
## wca2 -0.057 0.116 -0.487 0.626 -0.076 -0.076
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wipe1 ~~
## wca1 0.037 0.021 1.786 0.074 0.275 0.275
## .wipe2 ~~
## .wca2 0.050 0.013 3.793 0.000 0.356 0.356
## .wipe3 ~~
## .wca3 0.019 0.019 0.965 0.335 0.207 0.207
## RIipe ~~
## RIca -0.007 0.014 -0.468 0.639 -0.184 -0.184
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .in_eff_w1 3.051 0.075 40.876 0.000 3.051 4.101
## .in_eff_w2 3.027 0.084 36.104 0.000 3.027 3.605
## .in_eff_w3 3.089 0.081 38.113 0.000 3.089 3.889
## .c_act_w1 0.172 0.022 7.976 0.000 0.172 0.722
## .c_act_w2 0.147 0.021 7.045 0.000 0.147 0.649
## .c_act_w3 0.074 0.019 3.978 0.000 0.074 0.419
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIipe 0.181 0.111 1.628 0.104 1.000 1.000
## RIca 0.007 0.005 1.454 0.146 1.000 1.000
## wipe1 0.372 0.110 3.370 0.001 1.000 1.000
## wca1 0.049 0.008 6.137 0.000 1.000 1.000
## .wipe2 0.484 0.101 4.782 0.000 0.924 0.924
## .wca2 0.041 0.008 5.133 0.000 0.930 0.930
## .wipe3 0.357 0.053 6.711 0.000 0.793 0.793
## .wca3 0.023 0.016 1.446 0.148 0.942 0.942
## .in_eff_w1 0.000 0.000 0.000
## .in_eff_w2 0.000 0.000 0.000
## .in_eff_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wipe2 0.076
## wca2 0.070
## wipe3 0.207
## wca3 0.058
## in_eff_w1 1.000
## in_eff_w2 1.000
## in_eff_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000#RICLPM EPE + CA, MLR
RICLPM3 <- '
# Create between components (random intercepts)
RIepe =~ 1*ex_eff_w1 + 1*ex_eff_w2 + 1*ex_eff_w3
RIca =~ 1*c_act_w1 + 1*c_act_w2 + 1*c_act_w3
# Create within-person centered variables
wepe1 =~ 1*ex_eff_w1
wepe2 =~ 1*ex_eff_w2
wepe3 =~ 1*ex_eff_w3
wca1 =~ 1*c_act_w1
wca2 =~ 1*c_act_w2
wca3 =~ 1*c_act_w3
# Estimate lagged effects between within-person centered variables
wepe2 + wca2 ~ wepe1 + wca1
wepe3 + wca3 ~ wepe2 + wca2
# Estimate covariance between within-person centered variables at first wave
wepe1 ~~ wca1 # Covariance
# Estimate covariances between residuals of within-person centered variables
# (i.e., innovations)
wepe2 ~~ wca2
wepe3 ~~ wca3
# Estimate variance and covariance of random intercepts
RIepe ~~ RIepe
RIca ~~ RIca
RIepe ~~ RIca
# Estimate (residual) variance of within-person centered variables
wepe1 ~~ wepe1 # Variances
wca1 ~~ wca1
wepe2 ~~ wepe2 # Residual variances
wca2 ~~ wca2
wepe3 ~~ wepe3
wca3 ~~ wca3'
RICLPM3fit <- lavaan(RICLPM3,
data = ANES_clean,
missing = 'FIML',
sampling.weights = 'V240106b',
estimator = "MLR",
meanstructure = T,
int.ov.free = T)
summary(RICLPM3fit, fit.measures = T, standardized = T, rsquare = T)## lavaan 0.6-19 ended normally after 70 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 26
##
## Number of observations 2070
## Number of missing patterns 10
## Sampling weights variable V240106b
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 3.828 2.383
## Degrees of freedom 1 1
## P-value (Chi-square) 0.050 0.123
## Scaling correction factor 1.607
## Yuan-Bentler correction (Mplus variant)
##
## Model Test Baseline Model:
##
## Test statistic 1574.648 726.545
## Degrees of freedom 15 15
## P-value 0.000 0.000
## Scaling correction factor 2.167
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.998 0.998
## Tucker-Lewis Index (TLI) 0.973 0.971
##
## Robust Comparative Fit Index (CFI) 0.999
## Robust Tucker-Lewis Index (TLI) 0.980
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -7305.490 -7305.490
## Scaling correction factor 2.243
## for the MLR correction
## Loglikelihood unrestricted model (H1) -7303.576 -7303.576
## Scaling correction factor 2.220
## for the MLR correction
##
## Akaike (AIC) 14662.981 14662.981
## Bayesian (BIC) 14809.499 14809.499
## Sample-size adjusted Bayesian (SABIC) 14726.895 14726.895
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.037 0.026
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.079 0.060
## P-value H_0: RMSEA <= 0.050 0.625 0.855
## P-value H_0: RMSEA >= 0.080 0.046 0.003
##
## Robust RMSEA 0.032
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.091
## P-value H_0: Robust RMSEA <= 0.050 0.594
## P-value H_0: Robust RMSEA >= 0.080 0.102
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.008 0.008
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIepe =~
## ex_eff_w1 1.000 0.543 0.545
## ex_eff_w2 1.000 0.543 0.535
## ex_eff_w3 1.000 0.543 0.571
## RIca =~
## c_act_w1 1.000 0.113 0.451
## c_act_w2 1.000 0.113 0.474
## c_act_w3 1.000 0.113 0.635
## wepe1 =~
## ex_eff_w1 1.000 0.835 0.838
## wepe2 =~
## ex_eff_w2 1.000 0.858 0.845
## wepe3 =~
## ex_eff_w3 1.000 0.781 0.821
## wca1 =~
## c_act_w1 1.000 0.223 0.892
## wca2 =~
## c_act_w2 1.000 0.210 0.881
## wca3 =~
## c_act_w3 1.000 0.137 0.772
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wepe2 ~
## wepe1 0.053 0.049 1.089 0.276 0.052 0.052
## wca1 0.087 0.158 0.554 0.579 0.023 0.023
## wca2 ~
## wepe1 -0.016 0.010 -1.584 0.113 -0.063 -0.063
## wca1 0.280 0.042 6.602 0.000 0.297 0.297
## wepe3 ~
## wepe2 0.164 0.046 3.588 0.000 0.181 0.181
## wca2 -0.244 0.170 -1.430 0.153 -0.066 -0.066
## wca3 ~
## wepe2 0.007 0.008 0.980 0.327 0.047 0.047
## wca2 0.027 0.049 0.563 0.573 0.042 0.042
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wepe1 ~~
## wca1 0.013 0.008 1.572 0.116 0.068 0.068
## .wepe2 ~~
## .wca2 0.013 0.007 1.835 0.067 0.076 0.076
## .wepe3 ~~
## .wca3 -0.011 0.005 -2.086 0.037 -0.103 -0.103
## RIepe ~~
## RIca 0.015 0.006 2.508 0.012 0.244 0.244
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ex_eff_w1 2.563 0.030 86.501 0.000 2.563 2.572
## .ex_eff_w2 2.363 0.030 79.307 0.000 2.363 2.328
## .ex_eff_w3 2.208 0.028 79.045 0.000 2.208 2.322
## .c_act_w1 0.192 0.007 26.917 0.000 0.192 0.766
## .c_act_w2 0.159 0.007 23.008 0.000 0.159 0.665
## .c_act_w3 0.078 0.005 14.844 0.000 0.078 0.438
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIepe 0.295 0.033 8.908 0.000 1.000 1.000
## RIca 0.013 0.002 6.064 0.000 1.000 1.000
## wepe1 0.698 0.040 17.350 0.000 1.000 1.000
## wca1 0.050 0.003 17.343 0.000 1.000 1.000
## .wepe2 0.733 0.045 16.121 0.000 0.997 0.997
## .wca2 0.040 0.003 15.284 0.000 0.910 0.910
## .wepe3 0.588 0.036 16.375 0.000 0.965 0.965
## .wca3 0.019 0.003 6.057 0.000 0.996 0.996
## .ex_eff_w1 0.000 0.000 0.000
## .ex_eff_w2 0.000 0.000 0.000
## .ex_eff_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wepe2 0.003
## wca2 0.090
## wepe3 0.035
## wca3 0.004
## ex_eff_w1 1.000
## ex_eff_w2 1.000
## ex_eff_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000#RICLPM EPE + CA, MLR, Multi-Group by Race
RICLPM4 <- '
# Create between components (random intercepts)
RIepe =~ 1*ex_eff_w1 + 1*ex_eff_w2 + 1*ex_eff_w3
RIca =~ 1*c_act_w1 + 1*c_act_w2 + 1*c_act_w3
# Create within-person centered variables
wepe1 =~ 1*ex_eff_w1
wepe2 =~ 1*ex_eff_w2
wepe3 =~ 1*ex_eff_w3
wca1 =~ 1*c_act_w1
wca2 =~ 1*c_act_w2
wca3 =~ 1*c_act_w3
# Estimate lagged effects between within-person centered variables
wepe2 + wca2 ~ wepe1 + wca1
wepe3 + wca3 ~ wepe2 + wca2
# Estimate covariance between within-person centered variables at first wave
wepe1 ~~ wca1 # Covariance
# Estimate covariances between residuals of within-person centered variables
# (i.e., innovations)
wepe2 ~~ wca2
wepe3 ~~ wca3
# Estimate variance and covariance of random intercepts
RIepe ~~ RIepe
RIca ~~ RIca
RIepe ~~ RIca
# Estimate (residual) variance of within-person centered variables
wepe1 ~~ wepe1 # Variances
wca1 ~~ wca1
wepe2 ~~ wepe2 # Residual variances
wca2 ~~ wca2
wepe3 ~~ wepe3
wca3 ~~ wca3'
RICLPM4fit <- lavaan(RICLPM4,
data = ANES_cleanest,
missing = 'FIML',
sampling.weights = 'V240106b',
group = 'Race3',
estimator = "MLR",
meanstructure = T,
int.ov.free = T)
summary(RICLPM4fit, fit.measures = T, standardized = T, rsquare = T)## lavaan 0.6-19 ended normally after 183 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 78
##
## Number of observations per group:
## White 1537
## Black 161
## Hispanic 184
## Number of missing patterns per group:
## White 10
## Black 2
## Hispanic 4
## Sampling weights variable V240106b
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 6.621 4.304
## Degrees of freedom 3 3
## P-value (Chi-square) 0.085 0.230
## Scaling correction factor 1.538
## Yuan-Bentler correction (Mplus variant)
## Test statistic for each group:
## White 0.013 0.013
## Black 0.920 0.920
## Hispanic 3.371 3.371
##
## Model Test Baseline Model:
##
## Test statistic 1547.887 652.166
## Degrees of freedom 45 45
## P-value 0.000 0.000
## Scaling correction factor 2.373
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.998 0.998
## Tucker-Lewis Index (TLI) 0.964 0.968
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 0.996
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -6480.929 -6480.929
## Scaling correction factor 2.674
## for the MLR correction
## Loglikelihood unrestricted model (H1) -6477.619 -6477.619
## Scaling correction factor 2.632
## for the MLR correction
##
## Akaike (AIC) 13117.858 13117.858
## Bayesian (BIC) 13549.985 13549.985
## Sample-size adjusted Bayesian (SABIC) 13302.180 13302.180
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.044 0.026
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.090 0.067
## P-value H_0: RMSEA <= 0.050 0.513 0.794
## P-value H_0: RMSEA >= 0.080 0.108 0.011
##
## Robust RMSEA 0.014
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.099
## P-value H_0: Robust RMSEA <= 0.050 0.645
## P-value H_0: Robust RMSEA >= 0.080 0.130
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.006 0.006
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
##
## Group 1 [White]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIepe =~
## ex_eff_w1 1.000 0.546 0.559
## ex_eff_w2 1.000 0.546 0.529
## ex_eff_w3 1.000 0.546 0.591
## RIca =~
## c_act_w1 1.000 0.115 0.462
## c_act_w2 1.000 0.115 0.484
## c_act_w3 1.000 0.115 0.660
## wepe1 =~
## ex_eff_w1 1.000 0.810 0.829
## wepe2 =~
## ex_eff_w2 1.000 0.874 0.848
## wepe3 =~
## ex_eff_w3 1.000 0.745 0.807
## wca1 =~
## c_act_w1 1.000 0.221 0.887
## wca2 =~
## c_act_w2 1.000 0.209 0.875
## wca3 =~
## c_act_w3 1.000 0.131 0.751
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wepe2 ~
## wepe1 0.150 0.054 2.761 0.006 0.139 0.139
## wca1 0.452 0.168 2.691 0.007 0.114 0.114
## wca2 ~
## wepe1 0.004 0.011 0.398 0.691 0.017 0.017
## wca1 0.307 0.052 5.932 0.000 0.326 0.326
## wepe3 ~
## wepe2 0.162 0.045 3.577 0.000 0.190 0.190
## wca2 -0.069 0.182 -0.379 0.705 -0.019 -0.019
## wca3 ~
## wepe2 0.011 0.008 1.349 0.177 0.076 0.076
## wca2 0.035 0.053 0.656 0.512 0.055 0.055
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wepe1 ~~
## wca1 0.018 0.007 2.401 0.016 0.098 0.098
## .wepe2 ~~
## .wca2 0.018 0.008 2.302 0.021 0.104 0.104
## .wepe3 ~~
## .wca3 -0.006 0.005 -1.132 0.258 -0.062 -0.062
## RIepe ~~
## RIca 0.009 0.006 1.597 0.110 0.145 0.145
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ex_eff_w1 2.553 0.032 79.440 0.000 2.553 2.614
## .ex_eff_w2 2.312 0.034 67.886 0.000 2.312 2.243
## .ex_eff_w3 2.188 0.030 73.002 0.000 2.188 2.369
## .c_act_w1 0.187 0.008 22.798 0.000 0.187 0.751
## .c_act_w2 0.158 0.008 19.990 0.000 0.158 0.665
## .c_act_w3 0.077 0.006 14.004 0.000 0.077 0.442
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIepe 0.298 0.035 8.390 0.000 1.000 1.000
## RIca 0.013 0.003 5.156 0.000 1.000 1.000
## wepe1 0.657 0.040 16.436 0.000 1.000 1.000
## wca1 0.049 0.004 13.140 0.000 1.000 1.000
## .wepe2 0.738 0.043 17.272 0.000 0.965 0.965
## .wca2 0.039 0.003 13.774 0.000 0.893 0.893
## .wepe3 0.536 0.035 15.297 0.000 0.965 0.965
## .wca3 0.017 0.002 7.459 0.000 0.990 0.990
## .ex_eff_w1 0.000 0.000 0.000
## .ex_eff_w2 0.000 0.000 0.000
## .ex_eff_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wepe2 0.035
## wca2 0.107
## wepe3 0.035
## wca3 0.010
## ex_eff_w1 1.000
## ex_eff_w2 1.000
## ex_eff_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000
##
##
## Group 2 [Black]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIepe =~
## ex_eff_w1 1.000 0.650 0.639
## ex_eff_w2 1.000 0.650 0.642
## ex_eff_w3 1.000 0.650 0.604
## RIca =~
## c_act_w1 1.000 0.102 0.397
## c_act_w2 1.000 0.102 0.439
## c_act_w3 1.000 0.102 0.600
## wepe1 =~
## ex_eff_w1 1.000 0.784 0.770
## wepe2 =~
## ex_eff_w2 1.000 0.777 0.767
## wepe3 =~
## ex_eff_w3 1.000 0.858 0.797
## wca1 =~
## c_act_w1 1.000 0.235 0.918
## wca2 =~
## c_act_w2 1.000 0.209 0.899
## wca3 =~
## c_act_w3 1.000 0.136 0.800
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wepe2 ~
## wepe1 -0.185 0.170 -1.090 0.276 -0.187 -0.187
## wca1 -0.688 0.429 -1.604 0.109 -0.208 -0.208
## wca2 ~
## wepe1 0.016 0.041 0.388 0.698 0.060 0.060
## wca1 0.099 0.109 0.913 0.361 0.112 0.112
## wepe3 ~
## wepe2 0.067 0.193 0.347 0.729 0.061 0.061
## wca2 -0.067 0.648 -0.104 0.917 -0.016 -0.016
## wca3 ~
## wepe2 -0.036 0.028 -1.280 0.201 -0.203 -0.203
## wca2 -0.176 0.123 -1.427 0.154 -0.270 -0.270
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wepe1 ~~
## wca1 0.055 0.022 2.468 0.014 0.298 0.298
## .wepe2 ~~
## .wca2 0.005 0.022 0.243 0.808 0.036 0.036
## .wepe3 ~~
## .wca3 -0.026 0.027 -0.978 0.328 -0.241 -0.241
## RIepe ~~
## RIca 0.023 0.015 1.485 0.138 0.342 0.342
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ex_eff_w1 2.548 0.104 24.514 0.000 2.548 2.501
## .ex_eff_w2 2.602 0.105 24.876 0.000 2.602 2.569
## .ex_eff_w3 2.247 0.112 20.045 0.000 2.247 2.087
## .c_act_w1 0.220 0.025 8.740 0.000 0.220 0.857
## .c_act_w2 0.158 0.023 6.835 0.000 0.158 0.679
## .c_act_w3 0.082 0.020 4.013 0.000 0.082 0.483
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIepe 0.423 0.098 4.310 0.000 1.000 1.000
## RIca 0.010 0.006 1.690 0.091 1.000 1.000
## wepe1 0.614 0.127 4.832 0.000 1.000 1.000
## wca1 0.055 0.008 6.545 0.000 1.000 1.000
## .wepe2 0.542 0.171 3.163 0.002 0.899 0.899
## .wca2 0.043 0.010 4.164 0.000 0.980 0.980
## .wepe3 0.733 0.140 5.238 0.000 0.996 0.996
## .wca3 0.016 0.011 1.429 0.153 0.887 0.887
## .ex_eff_w1 0.000 0.000 0.000
## .ex_eff_w2 0.000 0.000 0.000
## .ex_eff_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wepe2 0.101
## wca2 0.020
## wepe3 0.004
## wca3 0.113
## ex_eff_w1 1.000
## ex_eff_w2 1.000
## ex_eff_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000
##
##
## Group 3 [Hispanic]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIepe =~
## ex_eff_w1 1.000 0.260 0.240
## ex_eff_w2 1.000 0.260 0.274
## ex_eff_w3 1.000 0.260 0.297
## RIca =~
## c_act_w1 1.000 0.094 0.391
## c_act_w2 1.000 0.094 0.414
## c_act_w3 1.000 0.094 0.530
## wepe1 =~
## ex_eff_w1 1.000 1.050 0.971
## wepe2 =~
## ex_eff_w2 1.000 0.912 0.962
## wepe3 =~
## ex_eff_w3 1.000 0.834 0.955
## wca1 =~
## c_act_w1 1.000 0.221 0.920
## wca2 =~
## c_act_w2 1.000 0.206 0.910
## wca3 =~
## c_act_w3 1.000 0.150 0.848
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wepe2 ~
## wepe1 0.087 0.128 0.685 0.493 0.101 0.101
## wca1 -0.892 0.592 -1.505 0.132 -0.216 -0.216
## wca2 ~
## wepe1 -0.065 0.025 -2.636 0.008 -0.334 -0.334
## wca1 0.198 0.103 1.911 0.056 0.212 0.212
## wepe3 ~
## wepe2 0.281 0.147 1.918 0.055 0.308 0.308
## wca2 -0.983 0.568 -1.732 0.083 -0.243 -0.243
## wca3 ~
## wepe2 0.012 0.026 0.451 0.652 0.072 0.072
## wca2 -0.023 0.110 -0.209 0.835 -0.032 -0.032
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wepe1 ~~
## wca1 -0.015 0.043 -0.339 0.735 -0.063 -0.063
## .wepe2 ~~
## .wca2 0.003 0.024 0.123 0.902 0.017 0.017
## .wepe3 ~~
## .wca3 -0.009 0.015 -0.574 0.566 -0.078 -0.078
## RIepe ~~
## RIca 0.022 0.029 0.767 0.443 0.904 0.904
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ex_eff_w1 2.576 0.113 22.700 0.000 2.576 2.380
## .ex_eff_w2 2.389 0.093 25.713 0.000 2.389 2.518
## .ex_eff_w3 2.125 0.078 27.219 0.000 2.125 2.432
## .c_act_w1 0.171 0.022 7.975 0.000 0.171 0.715
## .c_act_w2 0.147 0.021 7.045 0.000 0.147 0.649
## .c_act_w3 0.074 0.019 3.978 0.000 0.074 0.420
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIepe 0.068 0.150 0.449 0.653 1.000 1.000
## RIca 0.009 0.005 1.908 0.056 1.000 1.000
## wepe1 1.103 0.225 4.907 0.000 1.000 1.000
## wca1 0.049 0.008 5.806 0.000 1.000 1.000
## .wepe2 0.783 0.133 5.898 0.000 0.941 0.941
## .wca2 0.035 0.007 5.113 0.000 0.835 0.835
## .wepe3 0.581 0.084 6.938 0.000 0.836 0.836
## .wca3 0.022 0.015 1.461 0.144 0.993 0.993
## .ex_eff_w1 0.000 0.000 0.000
## .ex_eff_w2 0.000 0.000 0.000
## .ex_eff_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wepe2 0.059
## wca2 0.165
## wepe3 0.164
## wca3 0.007
## ex_eff_w1 1.000
## ex_eff_w2 1.000
## ex_eff_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000#RICLPM CR + CA, MLR
RICLPM5 <- '
# Create between components (random intercepts)
RIcr =~ 1*c_ref_w1 + 1*c_ref_w2 + 1*c_ref_w3
RIca =~ 1*c_act_w1 + 1*c_act_w2 + 1*c_act_w3
# Create within-person centered variables
wcr1 =~ 1*c_ref_w1
wcr2 =~ 1*c_ref_w2
wcr3 =~ 1*c_ref_w3
wca1 =~ 1*c_act_w1
wca2 =~ 1*c_act_w2
wca3 =~ 1*c_act_w3
# Estimate lagged effects between within-person centered variables
wcr2 + wca2 ~ wcr1 + wca1
wcr3 + wca3 ~ wcr2 + wca2
# Estimate covariance between within-person centered variables at first wave
wcr1 ~~ wca1 # Covariance
# Estimate covariances between residuals of within-person centered variables
# (i.e., innovations)
wcr2 ~~ wca2
wcr3 ~~ wca3
# Estimate variance and covariance of random intercepts
RIcr ~~ RIcr
RIca ~~ RIca
RIcr ~~ RIca
# Estimate (residual) variance of within-person centered variables
wcr1 ~~ wcr1 # Variances
wca1 ~~ wca1
wcr2 ~~ wcr2 # Residual variances
wca2 ~~ wca2
wcr3 ~~ wcr3
wca3 ~~ wca3'
RICLPM5fit <- lavaan(RICLPM5,
data = ANES_clean,
missing = 'FIML',
sampling.weights = 'V240106b',
estimator = "MLR",
meanstructure = T,
int.ov.free = T)
summary(RICLPM5fit, fit.measures = T, standardized = T, rsquare = T)## lavaan 0.6-19 ended normally after 76 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 26
##
## Number of observations 2070
## Number of missing patterns 10
## Sampling weights variable V240106b
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 1.978 1.013
## Degrees of freedom 1 1
## P-value (Chi-square) 0.160 0.314
## Scaling correction factor 1.954
## Yuan-Bentler correction (Mplus variant)
##
## Model Test Baseline Model:
##
## Test statistic 3830.775 1602.897
## Degrees of freedom 15 15
## P-value 0.000 0.000
## Scaling correction factor 2.390
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 0.996 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -7490.719 -7490.719
## Scaling correction factor 2.304
## for the MLR correction
## Loglikelihood unrestricted model (H1) -7489.729 -7489.729
## Scaling correction factor 2.291
## for the MLR correction
##
## Akaike (AIC) 15033.437 15033.437
## Bayesian (BIC) 15179.955 15179.955
## Sample-size adjusted Bayesian (SABIC) 15097.351 15097.351
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.022 0.002
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.067 0.044
## P-value H_0: RMSEA <= 0.050 0.808 0.977
## P-value H_0: RMSEA >= 0.080 0.013 0.000
##
## Robust RMSEA 0.006
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.081
## P-value H_0: Robust RMSEA <= 0.050 0.736
## P-value H_0: Robust RMSEA >= 0.080 0.054
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.006 0.006
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr =~
## c_ref_w1 1.000 0.969 0.790
## c_ref_w2 1.000 0.969 0.779
## c_ref_w3 1.000 0.969 0.802
## RIca =~
## c_act_w1 1.000 0.113 0.452
## c_act_w2 1.000 0.113 0.473
## c_act_w3 1.000 0.113 0.632
## wcr1 =~
## c_ref_w1 1.000 0.751 0.613
## wcr2 =~
## c_ref_w2 1.000 0.781 0.628
## wcr3 =~
## c_ref_w3 1.000 0.722 0.598
## wca1 =~
## c_act_w1 1.000 0.223 0.892
## wca2 =~
## c_act_w2 1.000 0.210 0.881
## wca3 =~
## c_act_w3 1.000 0.138 0.775
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr2 ~
## wcr1 0.121 0.071 1.704 0.088 0.116 0.116
## wca1 0.211 0.150 1.411 0.158 0.060 0.060
## wca2 ~
## wcr1 0.049 0.016 3.088 0.002 0.175 0.175
## wca1 0.260 0.041 6.290 0.000 0.276 0.276
## wcr3 ~
## wcr2 0.174 0.064 2.725 0.006 0.188 0.188
## wca2 0.593 0.211 2.815 0.005 0.173 0.173
## wca3 ~
## wcr2 0.008 0.009 0.891 0.373 0.047 0.047
## wca2 0.025 0.048 0.522 0.602 0.038 0.038
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr1 ~~
## wca1 0.014 0.008 1.733 0.083 0.086 0.086
## .wcr2 ~~
## .wca2 0.034 0.008 4.182 0.000 0.225 0.225
## .wcr3 ~~
## .wca3 0.009 0.005 1.693 0.090 0.093 0.093
## RIcr ~~
## RIca 0.030 0.007 4.281 0.000 0.277 0.277
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .c_ref_w1 3.023 0.037 82.590 0.000 3.023 2.465
## .c_ref_w2 3.234 0.036 89.365 0.000 3.234 2.599
## .c_ref_w3 3.113 0.036 86.139 0.000 3.113 2.576
## .c_act_w1 0.192 0.007 26.911 0.000 0.192 0.769
## .c_act_w2 0.159 0.007 23.008 0.000 0.159 0.665
## .c_act_w3 0.078 0.005 14.840 0.000 0.078 0.437
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr 0.939 0.053 17.826 0.000 1.000 1.000
## RIca 0.013 0.002 6.115 0.000 1.000 1.000
## wcr1 0.565 0.043 13.166 0.000 1.000 1.000
## wca1 0.050 0.003 17.431 0.000 1.000 1.000
## .wcr2 0.598 0.046 12.986 0.000 0.982 0.982
## .wca2 0.039 0.003 15.441 0.000 0.885 0.885
## .wcr3 0.479 0.035 13.642 0.000 0.919 0.919
## .wca3 0.019 0.003 6.168 0.000 0.995 0.995
## .c_ref_w1 0.000 0.000 0.000
## .c_ref_w2 0.000 0.000 0.000
## .c_ref_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wcr2 0.018
## wca2 0.115
## wcr3 0.081
## wca3 0.005
## c_ref_w1 1.000
## c_ref_w2 1.000
## c_ref_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000#RICLPM CR + CA, MLR, Multi-Group by Race
RICLPM6 <- '
# Create between components (random intercepts)
RIcr =~ 1*c_ref_w1 + 1*c_ref_w2 + 1*c_ref_w3
RIca =~ 1*c_act_w1 + 1*c_act_w2 + 1*c_act_w3
# Create within-person centered variables
wcr1 =~ 1*c_ref_w1
wcr2 =~ 1*c_ref_w2
wcr3 =~ 1*c_ref_w3
wca1 =~ 1*c_act_w1
wca2 =~ 1*c_act_w2
wca3 =~ 1*c_act_w3
# Estimate lagged effects between within-person centered variables
wcr2 + wca2 ~ wcr1 + wca1
wcr3 + wca3 ~ wcr2 + wca2
# Estimate covariance between within-person centered variables at first wave
wcr1 ~~ wca1 # Covariance
# Estimate covariances between residuals of within-person centered variables
# (i.e., innovations)
wcr2 ~~ wca2
wcr3 ~~ wca3
# Estimate variance and covariance of random intercepts
RIcr ~~ RIcr
RIca ~~ RIca
RIcr ~~ RIca
# Estimate (residual) variance of within-person centered variables
wcr1 ~~ wcr1 # Variances
wca1 ~~ wca1
wcr2 ~~ wcr2 # Residual variances
wca2 ~~ wca2
wcr3 ~~ wcr3
wca3 ~~ wca3'
RICLPM6fit <- lavaan(RICLPM6,
data = ANES_cleanest,
missing = 'FIML',
sampling.weights = 'V240106b',
estimator = "MLR",
group = 'Race3',
meanstructure = T,
int.ov.free = T)
summary(RICLPM6fit, fit.measures = T, standardized = T, rsquare = T)## lavaan 0.6-19 ended normally after 204 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 78
##
## Number of observations per group:
## White 1537
## Black 161
## Hispanic 184
## Number of missing patterns per group:
## White 10
## Black 4
## Hispanic 3
## Sampling weights variable V240106b
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 3.888 1.416
## Degrees of freedom 3 3
## P-value (Chi-square) 0.274 0.702
## Scaling correction factor 2.746
## Yuan-Bentler correction (Mplus variant)
## Test statistic for each group:
## White 0.041 0.041
## Black 1.033 1.033
## Hispanic 0.342 0.342
##
## Model Test Baseline Model:
##
## Test statistic 3382.209 1318.479
## Degrees of freedom 45 45
## P-value 0.000 0.000
## Scaling correction factor 2.565
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 0.996 1.019
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.016
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -6584.676 -6584.676
## Scaling correction factor 2.803
## for the MLR correction
## Loglikelihood unrestricted model (H1) -6582.732 -6582.732
## Scaling correction factor 2.801
## for the MLR correction
##
## Akaike (AIC) 13325.353 13325.353
## Bayesian (BIC) 13757.480 13757.480
## Sample-size adjusted Bayesian (SABIC) 13509.674 13509.674
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.022 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.074 0.023
## P-value H_0: RMSEA <= 0.050 0.759 0.999
## P-value H_0: RMSEA >= 0.080 0.030 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.082
## P-value H_0: Robust RMSEA <= 0.050 0.833
## P-value H_0: Robust RMSEA >= 0.080 0.056
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.006 0.006
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
##
## Group 1 [White]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr =~
## c_ref_w1 1.000 0.976 0.797
## c_ref_w2 1.000 0.976 0.784
## c_ref_w3 1.000 0.976 0.811
## RIca =~
## c_act_w1 1.000 0.117 0.467
## c_act_w2 1.000 0.117 0.490
## c_act_w3 1.000 0.117 0.668
## wcr1 =~
## c_ref_w1 1.000 0.740 0.604
## wcr2 =~
## c_ref_w2 1.000 0.772 0.620
## wcr3 =~
## c_ref_w3 1.000 0.703 0.585
## wca1 =~
## c_act_w1 1.000 0.221 0.884
## wca2 =~
## c_act_w2 1.000 0.208 0.872
## wca3 =~
## c_act_w3 1.000 0.130 0.744
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr2 ~
## wcr1 0.159 0.082 1.937 0.053 0.153 0.153
## wca1 0.399 0.168 2.379 0.017 0.114 0.114
## wca2 ~
## wcr1 0.050 0.019 2.703 0.007 0.180 0.180
## wca1 0.288 0.049 5.836 0.000 0.306 0.306
## wcr3 ~
## wcr2 0.178 0.071 2.503 0.012 0.196 0.196
## wca2 0.753 0.253 2.980 0.003 0.222 0.222
## wca3 ~
## wcr2 0.002 0.010 0.204 0.838 0.012 0.012
## wca2 0.032 0.055 0.572 0.567 0.051 0.051
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr1 ~~
## wca1 0.015 0.009 1.593 0.111 0.092 0.092
## .wcr2 ~~
## .wca2 0.036 0.009 4.129 0.000 0.248 0.248
## .wcr3 ~~
## .wca3 0.004 0.004 0.895 0.371 0.045 0.045
## RIcr ~~
## RIca 0.035 0.008 4.492 0.000 0.312 0.312
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .c_ref_w1 2.900 0.041 69.868 0.000 2.900 2.367
## .c_ref_w2 3.078 0.040 76.285 0.000 3.078 2.474
## .c_ref_w3 3.001 0.040 75.248 0.000 3.001 2.495
## .c_act_w1 0.187 0.008 22.790 0.000 0.187 0.750
## .c_act_w2 0.158 0.008 19.987 0.000 0.158 0.665
## .c_act_w3 0.077 0.006 14.006 0.000 0.077 0.443
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr 0.952 0.060 15.788 0.000 1.000 1.000
## RIca 0.014 0.003 5.298 0.000 1.000 1.000
## wcr1 0.548 0.047 11.548 0.000 1.000 1.000
## wca1 0.049 0.004 13.314 0.000 1.000 1.000
## .wcr2 0.572 0.050 11.528 0.000 0.960 0.960
## .wca2 0.037 0.003 13.424 0.000 0.864 0.864
## .wcr3 0.438 0.036 12.195 0.000 0.887 0.887
## .wca3 0.017 0.002 7.401 0.000 0.997 0.997
## .c_ref_w1 0.000 0.000 0.000
## .c_ref_w2 0.000 0.000 0.000
## .c_ref_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wcr2 0.040
## wca2 0.136
## wcr3 0.113
## wca3 0.003
## c_ref_w1 1.000
## c_ref_w2 1.000
## c_ref_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000
##
##
## Group 2 [Black]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr =~
## c_ref_w1 1.000 0.790 0.723
## c_ref_w2 1.000 0.790 0.755
## c_ref_w3 1.000 0.790 0.679
## RIca =~
## c_act_w1 1.000 0.113 0.442
## c_act_w2 1.000 0.113 0.488
## c_act_w3 1.000 0.113 0.669
## wcr1 =~
## c_ref_w1 1.000 0.755 0.691
## wcr2 =~
## c_ref_w2 1.000 0.685 0.656
## wcr3 =~
## c_ref_w3 1.000 0.854 0.734
## wca1 =~
## c_act_w1 1.000 0.230 0.897
## wca2 =~
## c_act_w2 1.000 0.203 0.873
## wca3 =~
## c_act_w3 1.000 0.126 0.743
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr2 ~
## wcr1 -0.335 0.192 -1.748 0.081 -0.369 -0.369
## wca1 -0.337 0.466 -0.723 0.470 -0.113 -0.113
## wca2 ~
## wcr1 0.051 0.032 1.555 0.120 0.188 0.188
## wca1 0.069 0.088 0.783 0.434 0.078 0.078
## wcr3 ~
## wcr2 -0.117 0.269 -0.436 0.663 -0.094 -0.094
## wca2 0.809 0.746 1.084 0.278 0.192 0.192
## wca3 ~
## wcr2 0.044 0.037 1.174 0.240 0.238 0.238
## wca2 -0.272 0.144 -1.895 0.058 -0.438 -0.438
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr1 ~~
## wca1 0.007 0.026 0.272 0.786 0.040 0.040
## .wcr2 ~~
## .wca2 0.035 0.025 1.389 0.165 0.280 0.280
## .wcr3 ~~
## .wca3 0.038 0.028 1.371 0.170 0.404 0.404
## RIcr ~~
## RIca -0.007 0.013 -0.573 0.567 -0.082 -0.082
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .c_ref_w1 3.821 0.118 32.484 0.000 3.821 3.499
## .c_ref_w2 4.093 0.123 33.371 0.000 4.093 3.914
## .c_ref_w3 3.795 0.135 28.190 0.000 3.795 3.262
## .c_act_w1 0.220 0.025 8.740 0.000 0.220 0.855
## .c_act_w2 0.158 0.023 6.835 0.000 0.158 0.679
## .c_act_w3 0.082 0.020 4.013 0.000 0.082 0.484
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr 0.623 0.193 3.231 0.001 1.000 1.000
## RIca 0.013 0.006 2.128 0.033 1.000 1.000
## wcr1 0.569 0.118 4.819 0.000 1.000 1.000
## wca1 0.053 0.008 6.673 0.000 1.000 1.000
## .wcr2 0.398 0.185 2.155 0.031 0.848 0.848
## .wca2 0.039 0.010 3.815 0.000 0.957 0.957
## .wcr3 0.701 0.135 5.200 0.000 0.961 0.961
## .wca3 0.012 0.010 1.283 0.200 0.787 0.787
## .c_ref_w1 0.000 0.000 0.000
## .c_ref_w2 0.000 0.000 0.000
## .c_ref_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wcr2 0.152
## wca2 0.043
## wcr3 0.039
## wca3 0.213
## c_ref_w1 1.000
## c_ref_w2 1.000
## c_ref_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000
##
##
## Group 3 [Hispanic]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr =~
## c_ref_w1 1.000 0.767 0.734
## c_ref_w2 1.000 0.767 0.722
## c_ref_w3 1.000 0.767 0.731
## RIca =~
## c_act_w1 1.000 0.082 0.349
## c_act_w2 1.000 0.082 0.362
## c_act_w3 1.000 0.082 0.459
## wcr1 =~
## c_ref_w1 1.000 0.709 0.679
## wcr2 =~
## c_ref_w2 1.000 0.734 0.691
## wcr3 =~
## c_ref_w3 1.000 0.715 0.682
## wca1 =~
## c_act_w1 1.000 0.220 0.937
## wca2 =~
## c_act_w2 1.000 0.211 0.932
## wca3 =~
## c_act_w3 1.000 0.159 0.889
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr2 ~
## wcr1 -0.054 0.194 -0.276 0.782 -0.052 -0.052
## wca1 -0.500 0.648 -0.773 0.440 -0.150 -0.150
## wca2 ~
## wcr1 0.008 0.064 0.124 0.901 0.027 0.027
## wca1 0.241 0.114 2.117 0.034 0.252 0.252
## wcr3 ~
## wcr2 0.277 0.168 1.653 0.098 0.285 0.285
## wca2 -0.056 0.662 -0.085 0.932 -0.017 -0.017
## wca3 ~
## wcr2 -0.001 0.020 -0.066 0.948 -0.006 -0.006
## wca2 0.030 0.110 0.275 0.783 0.040 0.040
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr1 ~~
## wca1 -0.022 0.032 -0.698 0.485 -0.144 -0.144
## .wcr2 ~~
## .wca2 0.040 0.033 1.238 0.216 0.272 0.272
## .wcr3 ~~
## .wca3 0.013 0.011 1.233 0.217 0.122 0.122
## RIcr ~~
## RIca 0.037 0.028 1.319 0.187 0.594 0.594
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .c_ref_w1 2.940 0.098 30.156 0.000 2.940 2.815
## .c_ref_w2 3.292 0.096 34.435 0.000 3.292 3.101
## .c_ref_w3 3.105 0.102 30.359 0.000 3.105 2.961
## .c_act_w1 0.172 0.022 7.976 0.000 0.172 0.730
## .c_act_w2 0.147 0.021 7.045 0.000 0.147 0.649
## .c_act_w3 0.074 0.019 3.978 0.000 0.074 0.415
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr 0.588 0.111 5.316 0.000 1.000 1.000
## RIca 0.007 0.004 1.562 0.118 1.000 1.000
## wcr1 0.503 0.092 5.453 0.000 1.000 1.000
## wca1 0.048 0.008 6.138 0.000 1.000 1.000
## .wcr2 0.526 0.137 3.831 0.000 0.977 0.977
## .wca2 0.042 0.007 5.581 0.000 0.938 0.938
## .wcr3 0.471 0.116 4.060 0.000 0.921 0.921
## .wca3 0.025 0.016 1.609 0.108 0.998 0.998
## .c_ref_w1 0.000 0.000 0.000
## .c_ref_w2 0.000 0.000 0.000
## .c_ref_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wcr2 0.023
## wca2 0.062
## wcr3 0.079
## wca3 0.002
## c_ref_w1 1.000
## c_ref_w2 1.000
## c_ref_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000#Mean split
ANES_clean$in_eff_ms_w2 <- ifelse(ANES_clean$in_eff_w2 > mean(ANES_clean$in_eff_w2, na.rm = TRUE), 1, 0)
ANES_clean$ex_eff_ms_w2 <- ifelse(ANES_clean$ex_eff_w2 > mean(ANES_clean$ex_eff_w2, na.rm = TRUE), 1, 0)
ANES_grouped_clean <- subset(ANES_clean, !is.na(ex_eff_ms_w2))
ANES_grouped2_clean <- subset(ANES_clean, !is.na(in_eff_ms_w2))#RICLPM IPE Mod, MLR
RICLPMmod <- '
# Create between components (random intercepts)
RIcr =~ 1*c_ref_w1 + 1*c_ref_w2 + 1*c_ref_w3
RIca =~ 1*c_act_w1 + 1*c_act_w2 + 1*c_act_w3
# Create within-person centered variables
wcr1 =~ 1*c_ref_w1
wcr2 =~ 1*c_ref_w2
wcr3 =~ 1*c_ref_w3
wca1 =~ 1*c_act_w1
wca2 =~ 1*c_act_w2
wca3 =~ 1*c_act_w3
# Estimate lagged effects between within-person centered variables
wcr2 ~ wcr1 + wca1
wcr3 ~ wca2
wcr3 ~ wcr2
wca2 ~ wca1
wca3 ~ wca2
wca2 ~ wcr1
wca3 ~ wcr2
# Estimate covariance between within-person centered variables at first wave
wcr1 ~~ wca1 # Covariance
# Estimate covariances between residuals of within-person centered variables
# (i.e., innovations)
wcr2 ~~ wca2
wcr3 ~~ wca3
# Estimate variance and covariance of random intercepts
RIcr ~~ RIcr
RIca ~~ RIca
RIcr ~~ RIca
# Estimate (residual) variance of within-person centered variables
wcr1 ~~ wcr1 # Variances
wca1 ~~ wca1
wcr2 ~~ wcr2 # Residual variances
wca2 ~~ wca2
wcr3 ~~ wcr3
wca3 ~~ wca3'
RICLPMmodfit <- lavaan(RICLPMmod,
data = ANES_grouped2_clean,
missing = 'FIML',
sampling.weights = 'V240106b',
estimator = "MLR",
meanstructure = T,
group = "in_eff_ms_w2",
int.ov.free = T)
summary(RICLPMmodfit, fit.measures = T, standardized = T, rsquare = T)## lavaan 0.6-19 ended normally after 128 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 52
##
## Number of observations per group:
## 0 862
## 1 1199
## Number of missing patterns per group:
## 0 8
## 1 7
## Sampling weights variable V240106b
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 5.950 3.160
## Degrees of freedom 2 2
## P-value (Chi-square) 0.051 0.206
## Scaling correction factor 1.883
## Yuan-Bentler correction (Mplus variant)
## Test statistic for each group:
## 0 0.163 0.163
## 1 2.997 2.997
##
## Model Test Baseline Model:
##
## Test statistic 3704.261 1590.263
## Degrees of freedom 30 30
## P-value 0.000 0.000
## Scaling correction factor 2.329
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.999 0.999
## Tucker-Lewis Index (TLI) 0.984 0.989
##
## Robust Comparative Fit Index (CFI) 0.999
## Robust Tucker-Lewis Index (TLI) 0.992
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -7319.465 -7319.465
## Scaling correction factor 2.411
## for the MLR correction
## Loglikelihood unrestricted model (H1) -7316.490 -7316.490
## Scaling correction factor 2.392
## for the MLR correction
##
## Akaike (AIC) 14742.930 14742.930
## Bayesian (BIC) 15035.739 15035.739
## Sample-size adjusted Bayesian (SABIC) 14870.531 14870.531
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.044 0.024
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.086 0.058
## P-value H_0: RMSEA <= 0.050 0.520 0.883
## P-value H_0: RMSEA >= 0.080 0.086 0.002
##
## Robust RMSEA 0.031
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.098
## P-value H_0: Robust RMSEA <= 0.050 0.578
## P-value H_0: Robust RMSEA >= 0.080 0.138
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.010 0.010
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr =~
## c_ref_w1 1.000 0.851 0.769
## c_ref_w2 1.000 0.851 0.748
## c_ref_w3 1.000 0.851 0.753
## RIca =~
## c_act_w1 1.000 0.098 0.429
## c_act_w2 1.000 0.098 0.517
## c_act_w3 1.000 0.098 0.615
## wcr1 =~
## c_ref_w1 1.000 0.708 0.640
## wcr2 =~
## c_ref_w2 1.000 0.755 0.664
## wcr3 =~
## c_ref_w3 1.000 0.743 0.658
## wca1 =~
## c_act_w1 1.000 0.207 0.903
## wca2 =~
## c_act_w2 1.000 0.163 0.856
## wca3 =~
## c_act_w3 1.000 0.126 0.789
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr2 ~
## wcr1 0.098 0.114 0.855 0.392 0.092 0.092
## wca1 0.013 0.234 0.056 0.955 0.004 0.004
## wcr3 ~
## wca2 0.077 0.414 0.185 0.853 0.017 0.017
## wcr2 0.142 0.094 1.505 0.132 0.144 0.144
## wca2 ~
## wca1 0.174 0.054 3.252 0.001 0.221 0.221
## wca3 ~
## wca2 -0.111 0.081 -1.376 0.169 -0.144 -0.144
## wca2 ~
## wcr1 0.014 0.022 0.613 0.540 0.059 0.059
## wca3 ~
## wcr2 0.012 0.014 0.826 0.409 0.070 0.070
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr1 ~~
## wca1 0.006 0.011 0.509 0.611 0.038 0.038
## .wcr2 ~~
## .wca2 0.015 0.010 1.445 0.149 0.124 0.124
## .wcr3 ~~
## .wca3 0.015 0.009 1.694 0.090 0.168 0.168
## RIcr ~~
## RIca 0.031 0.010 3.114 0.002 0.366 0.366
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .c_ref_w1 2.911 0.051 57.358 0.000 2.911 2.631
## .c_ref_w2 3.096 0.051 61.182 0.000 3.096 2.722
## .c_ref_w3 3.039 0.053 57.782 0.000 3.039 2.691
## .c_act_w1 0.151 0.010 15.530 0.000 0.151 0.662
## .c_act_w2 0.108 0.008 12.805 0.000 0.108 0.571
## .c_act_w3 0.058 0.008 7.421 0.000 0.058 0.366
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr 0.723 0.072 10.039 0.000 1.000 1.000
## RIca 0.010 0.002 3.913 0.000 1.000 1.000
## wcr1 0.501 0.058 8.589 0.000 1.000 1.000
## wca1 0.043 0.003 13.134 0.000 1.000 1.000
## .wcr2 0.565 0.067 8.420 0.000 0.992 0.992
## .wca2 0.025 0.003 7.955 0.000 0.946 0.946
## .wcr3 0.540 0.057 9.407 0.000 0.978 0.978
## .wca3 0.015 0.005 3.024 0.002 0.977 0.977
## .c_ref_w1 0.000 0.000 0.000
## .c_ref_w2 0.000 0.000 0.000
## .c_ref_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wcr2 0.008
## wca2 0.054
## wcr3 0.022
## wca3 0.023
## c_ref_w1 1.000
## c_ref_w2 1.000
## c_ref_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000
##
##
## Group 2 [1]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr =~
## c_ref_w1 1.000 1.058 0.805
## c_ref_w2 1.000 1.058 0.799
## c_ref_w3 1.000 1.058 0.830
## RIca =~
## c_act_w1 1.000 0.121 0.459
## c_act_w2 1.000 0.121 0.450
## c_act_w3 1.000 0.121 0.625
## wcr1 =~
## c_ref_w1 1.000 0.781 0.594
## wcr2 =~
## c_ref_w2 1.000 0.796 0.601
## wcr3 =~
## c_ref_w3 1.000 0.712 0.558
## wca1 =~
## c_act_w1 1.000 0.233 0.888
## wca2 =~
## c_act_w2 1.000 0.240 0.893
## wca3 =~
## c_act_w3 1.000 0.151 0.781
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr2 ~
## wcr1 0.122 0.091 1.334 0.182 0.119 0.119
## wca1 0.209 0.198 1.054 0.292 0.061 0.061
## wcr3 ~
## wca2 0.788 0.251 3.136 0.002 0.266 0.266
## wcr2 0.210 0.089 2.367 0.018 0.234 0.234
## wca2 ~
## wca1 0.288 0.055 5.248 0.000 0.280 0.280
## wca3 ~
## wca2 0.076 0.060 1.278 0.201 0.121 0.121
## wca2 ~
## wcr1 0.067 0.022 3.028 0.002 0.218 0.218
## wca3 ~
## wcr2 0.005 0.012 0.369 0.712 0.024 0.024
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr1 ~~
## wca1 0.014 0.012 1.212 0.226 0.077 0.077
## .wcr2 ~~
## .wca2 0.046 0.013 3.637 0.000 0.264 0.264
## .wcr3 ~~
## .wca3 0.004 0.006 0.626 0.531 0.037 0.037
## RIcr ~~
## RIca 0.026 0.010 2.680 0.007 0.203 0.203
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .c_ref_w1 3.143 0.052 60.378 0.000 3.143 2.389
## .c_ref_w2 3.373 0.051 65.816 0.000 3.373 2.548
## .c_ref_w3 3.192 0.050 63.867 0.000 3.192 2.502
## .c_act_w1 0.232 0.010 22.937 0.000 0.232 0.883
## .c_act_w2 0.208 0.010 19.882 0.000 0.208 0.775
## .c_act_w3 0.097 0.007 13.752 0.000 0.097 0.502
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr 1.120 0.073 15.310 0.000 1.000 1.000
## RIca 0.015 0.003 4.719 0.000 1.000 1.000
## wcr1 0.611 0.058 10.560 0.000 1.000 1.000
## wca1 0.055 0.004 12.348 0.000 1.000 1.000
## .wcr2 0.621 0.064 9.644 0.000 0.981 0.981
## .wca2 0.050 0.004 12.898 0.000 0.865 0.865
## .wcr3 0.425 0.041 10.340 0.000 0.838 0.838
## .wca3 0.022 0.003 7.218 0.000 0.983 0.983
## .c_ref_w1 0.000 0.000 0.000
## .c_ref_w2 0.000 0.000 0.000
## .c_ref_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wcr2 0.019
## wca2 0.135
## wcr3 0.162
## wca3 0.017
## c_ref_w1 1.000
## c_ref_w2 1.000
## c_ref_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000#RICLPM EPE Mod, MLR
RICLPMmod9 <- '
# Create between components (random intercepts)
RIcr =~ 1*c_ref_w1 + 1*c_ref_w2 + 1*c_ref_w3
RIca =~ 1*c_act_w1 + 1*c_act_w2 + 1*c_act_w3
# Create within-person centered variables
wcr1 =~ 1*c_ref_w1
wcr2 =~ 1*c_ref_w2
wcr3 =~ 1*c_ref_w3
wca1 =~ 1*c_act_w1
wca2 =~ 1*c_act_w2
wca3 =~ 1*c_act_w3
# Estimate lagged effects between within-person centered variables
wcr2 ~ wcr1 + wca1
wcr3 ~ wcr2 + wca2
wca2 ~ wca1
wca3 ~ wca2
wca2 ~ wcr1
wca3 ~ wcr2
# Estimate covariance between within-person centered variables at first wave
wcr1 ~~ wca1 # Covariance
# Estimate covariances between residuals of within-person centered variables
# (i.e., innovations)
wcr2 ~~ wca2
wcr3 ~~ wca3
# Estimate variance and covariance of random intercepts
RIcr ~~ RIcr
RIca ~~ RIca
RIcr ~~ RIca
# Estimate (residual) variance of within-person centered variables
wcr1 ~~ wcr1 # Variances
wca1 ~~ wca1
wcr2 ~~ wcr2 # Residual variances
wca2 ~~ wca2
wcr3 ~~ wcr3
wca3 ~~ wca3
'
RICLPMmodfit9 <- lavaan(RICLPMmod9,
data = ANES_grouped_clean,
missing = 'FIML',
estimator = "MLR",
sampling.weights = 'V240106b',
meanstructure = T,
group = "ex_eff_ms_w2",
int.ov.free = T)
summary(RICLPMmodfit9, fit.measures = T, standardized = T, rsquare = T)## lavaan 0.6-19 ended normally after 129 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 52
##
## Number of observations per group:
## 0 1105
## 1 957
## Number of missing patterns per group:
## 0 8
## 1 7
## Sampling weights variable V240106b
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 3.044 1.645
## Degrees of freedom 2 2
## P-value (Chi-square) 0.218 0.439
## Scaling correction factor 1.850
## Yuan-Bentler correction (Mplus variant)
## Test statistic for each group:
## 0 0.846 0.846
## 1 0.799 0.799
##
## Model Test Baseline Model:
##
## Test statistic 3659.303 1581.180
## Degrees of freedom 30 30
## P-value 0.000 0.000
## Scaling correction factor 2.314
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 0.996 1.003
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.003
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -7366.202 -7366.202
## Scaling correction factor 2.223
## for the MLR correction
## Loglikelihood unrestricted model (H1) -7364.680 -7364.680
## Scaling correction factor 2.209
## for the MLR correction
##
## Akaike (AIC) 14836.403 14836.403
## Bayesian (BIC) 15129.238 15129.238
## Sample-size adjusted Bayesian (SABIC) 14964.029 14964.029
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.022 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.070 0.045
## P-value H_0: RMSEA <= 0.050 0.785 0.974
## P-value H_0: RMSEA >= 0.080 0.018 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.079
## P-value H_0: Robust RMSEA <= 0.050 0.776
## P-value H_0: Robust RMSEA >= 0.080 0.048
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.008 0.008
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr =~
## c_ref_w1 1.000 0.964 0.795
## c_ref_w2 1.000 0.964 0.769
## c_ref_w3 1.000 0.964 0.802
## RIca =~
## c_act_w1 1.000 0.084 0.346
## c_act_w2 1.000 0.084 0.382
## c_act_w3 1.000 0.084 0.561
## wcr1 =~
## c_ref_w1 1.000 0.734 0.606
## wcr2 =~
## c_ref_w2 1.000 0.802 0.640
## wcr3 =~
## c_ref_w3 1.000 0.719 0.598
## wca1 =~
## c_act_w1 1.000 0.226 0.938
## wca2 =~
## c_act_w2 1.000 0.202 0.924
## wca3 =~
## c_act_w3 1.000 0.123 0.828
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr2 ~
## wcr1 0.111 0.100 1.103 0.270 0.101 0.101
## wca1 0.171 0.200 0.855 0.392 0.048 0.048
## wcr3 ~
## wcr2 0.164 0.078 2.099 0.036 0.183 0.183
## wca2 0.521 0.297 1.753 0.080 0.146 0.146
## wca2 ~
## wca1 0.272 0.055 4.949 0.000 0.305 0.305
## wca3 ~
## wca2 0.052 0.057 0.900 0.368 0.085 0.085
## wca2 ~
## wcr1 0.027 0.022 1.222 0.222 0.096 0.096
## wca3 ~
## wcr2 -0.003 0.010 -0.277 0.782 -0.018 -0.018
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr1 ~~
## wca1 0.011 0.011 0.984 0.325 0.068 0.068
## .wcr2 ~~
## .wca2 0.025 0.011 2.286 0.022 0.161 0.161
## .wcr3 ~~
## .wca3 0.003 0.005 0.605 0.546 0.036 0.036
## RIcr ~~
## RIca 0.019 0.008 2.365 0.018 0.236 0.236
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .c_ref_w1 2.835 0.050 56.795 0.000 2.835 2.340
## .c_ref_w2 3.036 0.050 60.681 0.000 3.036 2.422
## .c_ref_w3 2.896 0.049 58.990 0.000 2.896 2.409
## .c_act_w1 0.184 0.010 18.674 0.000 0.184 0.764
## .c_act_w2 0.139 0.009 15.632 0.000 0.139 0.638
## .c_act_w3 0.058 0.006 10.114 0.000 0.058 0.392
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr 0.928 0.071 13.096 0.000 1.000 1.000
## RIca 0.007 0.002 3.461 0.001 1.000 1.000
## wcr1 0.539 0.051 10.505 0.000 1.000 1.000
## wca1 0.051 0.004 11.531 0.000 1.000 1.000
## .wcr2 0.634 0.064 9.882 0.000 0.987 0.987
## .wca2 0.036 0.003 12.129 0.000 0.893 0.893
## .wcr3 0.483 0.045 10.712 0.000 0.935 0.935
## .wca3 0.015 0.003 5.996 0.000 0.993 0.993
## .c_ref_w1 0.000 0.000 0.000
## .c_ref_w2 0.000 0.000 0.000
## .c_ref_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wcr2 0.013
## wca2 0.107
## wcr3 0.065
## wca3 0.007
## c_ref_w1 1.000
## c_ref_w2 1.000
## c_ref_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000
##
##
## Group 2 [1]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr =~
## c_ref_w1 1.000 0.916 0.763
## c_ref_w2 1.000 0.916 0.769
## c_ref_w3 1.000 0.916 0.785
## RIca =~
## c_act_w1 1.000 0.138 0.532
## c_act_w2 1.000 0.138 0.534
## c_act_w3 1.000 0.138 0.671
## wcr1 =~
## c_ref_w1 1.000 0.775 0.646
## wcr2 =~
## c_ref_w2 1.000 0.762 0.639
## wcr3 =~
## c_ref_w3 1.000 0.722 0.619
## wca1 =~
## c_act_w1 1.000 0.220 0.846
## wca2 =~
## c_act_w2 1.000 0.219 0.846
## wca3 =~
## c_act_w3 1.000 0.153 0.741
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr2 ~
## wcr1 0.140 0.098 1.424 0.154 0.142 0.142
## wca1 0.269 0.226 1.191 0.234 0.078 0.078
## wcr3 ~
## wcr2 0.191 0.103 1.853 0.064 0.201 0.201
## wca2 0.583 0.283 2.057 0.040 0.177 0.177
## wca2 ~
## wca1 0.240 0.062 3.836 0.000 0.240 0.240
## wca3 ~
## wca2 -0.021 0.076 -0.270 0.787 -0.030 -0.030
## wca2 ~
## wcr1 0.066 0.021 3.142 0.002 0.236 0.236
## wca3 ~
## wcr2 0.022 0.017 1.298 0.194 0.110 0.110
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wcr1 ~~
## wca1 0.018 0.012 1.488 0.137 0.108 0.108
## .wcr2 ~~
## .wca2 0.043 0.012 3.581 0.000 0.280 0.280
## .wcr3 ~~
## .wca3 0.013 0.009 1.468 0.142 0.129 0.129
## RIcr ~~
## RIca 0.035 0.011 3.146 0.002 0.279 0.279
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .c_ref_w1 3.258 0.052 62.355 0.000 3.258 2.715
## .c_ref_w2 3.476 0.051 68.025 0.000 3.476 2.918
## .c_ref_w3 3.376 0.051 66.310 0.000 3.376 2.895
## .c_act_w1 0.203 0.010 19.474 0.000 0.203 0.783
## .c_act_w2 0.183 0.011 17.000 0.000 0.183 0.708
## .c_act_w3 0.102 0.009 11.104 0.000 0.102 0.493
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIcr 0.839 0.079 10.626 0.000 1.000 1.000
## RIca 0.019 0.004 5.294 0.000 1.000 1.000
## wcr1 0.601 0.071 8.458 0.000 1.000 1.000
## wca1 0.048 0.003 14.712 0.000 1.000 1.000
## .wcr2 0.564 0.067 8.428 0.000 0.971 0.971
## .wca2 0.042 0.004 10.318 0.000 0.874 0.874
## .wcr3 0.472 0.051 9.321 0.000 0.906 0.906
## .wca3 0.023 0.006 4.008 0.000 0.989 0.989
## .c_ref_w1 0.000 0.000 0.000
## .c_ref_w2 0.000 0.000 0.000
## .c_ref_w3 0.000 0.000 0.000
## .c_act_w1 0.000 0.000 0.000
## .c_act_w2 0.000 0.000 0.000
## .c_act_w3 0.000 0.000 0.000
##
## R-Square:
## Estimate
## wcr2 0.029
## wca2 0.126
## wcr3 0.094
## wca3 0.011
## c_ref_w1 1.000
## c_ref_w2 1.000
## c_ref_w3 1.000
## c_act_w1 1.000
## c_act_w2 1.000
## c_act_w3 1.000