RI-CLPM - Family Conflict
Ayla Pollmann
2023
Introduction
We will use a random intercept cross-lagged panel model (RI-CLPM) to investigate family relations and their relationship with youth behavioral and emotional problems & brain development, using the prospective, longitudinal Adolescent Brain Cognitive Development study (ABCD, N ≈ 12.000).
Analysis
In this script,
we conducted an RI-CLPM for family conflict.
we conduct two additional RI-CLPMs:
peer support as a resilience factor
gender differences
- Lastly, we constrain the lagged parameters that were significant in the RI-CLPM for family conflict.
All measures will be assessed at baseline/six-month follow-up, one-year follow-up and three/four-year follow-up in the ABCD study.
Adversity
- Family conflict (ABCD Youth Family Environment Scale-Family Conflict Subscale Modified from PhenX (FES))
Brain connectivity
- Average fractional anisotropy within all DTI atlas tract fibers.
Youth problems
- Externalizing and internalizing issues (Youth brief problem monitor)
Resilience
- Peer support (ABCD Other resilience scale)
Code Legend
1,2,3 = corresponding time point (time point 1,….)
b = brain (white matter connectivity)
F = family conflict
m = youth mental problems (behavioral and emotional problems)
Family conflict - Main model
RICLPM_Family<- '
# Create between components (random intercepts)
RIx =~ 1*a1F + 1*a2F + 1*a3F
RIy =~ 1*b1 + 1*b2 + 1*b3
RIz =~ 1*m1 + 1*m2 + 1*m3
# Create within-person centered variables
wx1 =~ 1*a1F #each factor loading set to 1
wx2 =~ 1*a2F
wx3 =~ 1*a3F
wy1 =~ 1*b1
wy2 =~ 1*b2
wy3 =~ 1*b3
wz1 =~ 1*m1
wz2 =~ 1*m2
wz3 =~ 1*m3
# Estimate lagged effects between within-person centered variables
wx2 + wy2 + wz2 ~ wx1 + wy1 + wz1
wx3 + wy3 + wz3 ~ wx2 + wy2 + wz2
# Estimate covariance between within-person centered variables at first wave
wx1 ~~ wy1 # Covariance
wx1 ~~ wz1
wy1 ~~ wz1
# Estimate covariances between residuals of within-person centered variables
# (i.e., innovations)
wx2 ~~ wy2
wx2 ~~ wz2
wy2 ~~ wz2
wx3 ~~ wy3
wx3 ~~ wz3
wy3 ~~ wz3
# Estimate variance and covariance of random intercepts
RIx ~~ RIx
RIy ~~ RIy
RIz ~~ RIz
RIx ~~ RIy
RIx ~~ RIz
RIy ~~ RIz
# Estimate (residual) variance of within-person centered variables
wx1 ~~ wx1 # Variances
wy1 ~~ wy1
wz1 ~~ wz1
wx2 ~~ wx2 # Residual variances
wy2 ~~ wy2
wz2 ~~ wz2
wx3 ~~ wx3
wy3 ~~ wy3
wz3 ~~ wz3
'
RICLPM_Family_fit <- lavaan::lavaan(RICLPM_Family,
data = Data,
missing = "fiml",
meanstructure = TRUE,
int.ov.free = TRUE)
summary(RICLPM_Family_fit, standardized = TRUE)## lavaan 0.6.16 ended normally after 93 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 51
##
## Used Total
## Number of observations 9493 9495
## Number of missing patterns 71
##
## Model Test User Model:
##
## Test statistic 28.428
## Degrees of freedom 3
## P-value (Chi-square) 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIx =~
## a1F 1.000 0.493 0.496
## a2F 1.000 0.493 0.497
## a3F 1.000 0.493 0.495
## RIy =~
## b1 1.000 0.869 0.866
## b2 1.000 0.869 0.856
## b3 1.000 0.869 0.843
## RIz =~
## m1 1.000 0.456 0.459
## m2 1.000 0.456 0.455
## m3 1.000 0.456 0.456
## wx1 =~
## a1F 1.000 0.864 0.868
## wx2 =~
## a2F 1.000 0.860 0.868
## wx3 =~
## a3F 1.000 0.865 0.869
## wy1 =~
## b1 1.000 0.501 0.500
## wy2 =~
## b2 1.000 0.524 0.516
## wy3 =~
## b3 1.000 0.554 0.538
## wz1 =~
## m1 1.000 0.882 0.888
## wz2 =~
## m2 1.000 0.892 0.890
## wz3 =~
## m3 1.000 0.890 0.890
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wx2 ~
## wx1 0.131 0.027 4.909 0.000 0.131 0.131
## wy1 -0.068 0.071 -0.959 0.338 -0.040 -0.040
## wz1 0.177 0.024 7.454 0.000 0.181 0.181
## wy2 ~
## wx1 0.013 0.020 0.675 0.499 0.022 0.022
## wy1 0.312 0.093 3.359 0.001 0.299 0.299
## wz1 0.008 0.023 0.338 0.735 0.013 0.013
## wz2 ~
## wx1 0.063 0.021 3.030 0.002 0.061 0.061
## wy1 0.082 0.071 1.155 0.248 0.046 0.046
## wz1 0.355 0.030 11.886 0.000 0.351 0.351
## wx3 ~
## wx2 0.212 0.028 7.718 0.000 0.211 0.211
## wy2 -0.031 0.049 -0.629 0.529 -0.019 -0.019
## wz2 0.200 0.025 7.929 0.000 0.207 0.207
## wy3 ~
## wx2 -0.015 0.019 -0.775 0.439 -0.023 -0.023
## wy2 0.573 0.041 14.074 0.000 0.541 0.541
## wz2 0.007 0.019 0.362 0.717 0.011 0.011
## wz3 ~
## wx2 0.010 0.024 0.421 0.673 0.010 0.010
## wy2 -0.079 0.049 -1.613 0.107 -0.046 -0.046
## wz2 0.428 0.029 14.606 0.000 0.429 0.429
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wx1 ~~
## wy1 -0.006 0.020 -0.296 0.767 -0.014 -0.014
## wz1 0.181 0.025 7.256 0.000 0.237 0.237
## wy1 ~~
## wz1 0.009 0.024 0.393 0.695 0.021 0.021
## .wx2 ~~
## .wy2 -0.001 0.014 -0.108 0.914 -0.004 -0.004
## .wz2 0.199 0.014 14.217 0.000 0.289 0.289
## .wy2 ~~
## .wz2 0.008 0.013 0.561 0.575 0.018 0.018
## .wx3 ~~
## .wy3 -0.002 0.010 -0.201 0.841 -0.005 -0.005
## .wz3 0.230 0.014 16.317 0.000 0.353 0.353
## .wy3 ~~
## .wz3 -0.008 0.010 -0.807 0.420 -0.021 -0.021
## RIx ~~
## RIy -0.010 0.020 -0.483 0.629 -0.023 -0.023
## RIz 0.113 0.024 4.725 0.000 0.503 0.503
## RIy ~~
## RIz -0.025 0.024 -1.064 0.288 -0.063 -0.063
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .a1F -0.009 0.010 -0.841 0.400 -0.009 -0.009
## .a2F -0.001 0.011 -0.141 0.888 -0.001 -0.001
## .a3F 0.020 0.015 1.317 0.188 0.020 0.020
## .b1 -0.010 0.011 -0.908 0.364 -0.010 -0.010
## .b2 -0.026 0.012 -2.233 0.026 -0.026 -0.026
## .b3 -0.055 0.015 -3.741 0.000 -0.055 -0.054
## .m1 0.000 0.010 0.002 0.999 0.000 0.000
## .m2 0.006 0.011 0.610 0.542 0.006 0.006
## .m3 0.021 0.015 1.392 0.164 0.021 0.021
## RIx 0.000 0.000 0.000
## RIy 0.000 0.000 0.000
## RIz 0.000 0.000 0.000
## wx1 0.000 0.000 0.000
## .wx2 0.000 0.000 0.000
## .wx3 0.000 0.000 0.000
## wy1 0.000 0.000 0.000
## .wy2 0.000 0.000 0.000
## .wy3 0.000 0.000 0.000
## wz1 0.000 0.000 0.000
## .wz2 0.000 0.000 0.000
## .wz3 0.000 0.000 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIx 0.243 0.025 9.663 0.000 1.000 1.000
## RIy 0.754 0.033 22.529 0.000 1.000 1.000
## RIz 0.208 0.035 5.900 0.000 1.000 1.000
## wx1 0.747 0.027 27.914 0.000 1.000 1.000
## wy1 0.251 0.031 8.018 0.000 1.000 1.000
## wz1 0.778 0.037 21.031 0.000 1.000 1.000
## .wx2 0.694 0.020 34.990 0.000 0.937 0.937
## .wy2 0.249 0.019 13.325 0.000 0.910 0.910
## .wz2 0.685 0.018 37.454 0.000 0.860 0.860
## .wx3 0.661 0.019 34.435 0.000 0.883 0.883
## .wy3 0.216 0.009 24.469 0.000 0.706 0.706
## .wz3 0.644 0.019 34.341 0.000 0.813 0.813
## .a1F 0.000 0.000 0.000
## .a2F 0.000 0.000 0.000
## .a3F 0.000 0.000 0.000
## .b1 0.000 0.000 0.000
## .b2 0.000 0.000 0.000
## .b3 0.000 0.000 0.000
## .m1 0.000 0.000 0.000
## .m2 0.000 0.000 0.000
## .m3 0.000 0.000 0.000fitMeasures(RICLPM_Family_fit, fit.measures = c("chisq","df","pvalue","rmsea","srmr","cfi"))## chisq df pvalue rmsea srmr cfi
## 28.428 3.000 0.000 0.030 0.010 0.998Multigroup analysis
Family conflict & Peer resilience
RICLPM_Family_fit_Peers <- lavaan::lavaan(RICLPM_Family,
data = Data,
missing = "fiml",
meanstructure = TRUE,
int.ov.free = TRUE,
group = "Resilience_Peers"
)
summary(RICLPM_Family_fit_Peers, standardized = TRUE)## lavaan 0.6.16 ended normally after 190 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 102
##
## Number of observations per group:
## 1 4407
## 0 5070
## Number of missing patterns per group:
## 1 58
## 0 54
##
## Model Test User Model:
##
## Test statistic 30.420
## Degrees of freedom 6
## P-value (Chi-square) 0.000
## Test statistic for each group:
## 1 19.736
## 0 10.685
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [1]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIx =~
## a1F 1.000 0.462 0.464
## a2F 1.000 0.462 0.462
## a3F 1.000 0.462 0.470
## RIy =~
## b1 1.000 0.880 0.887
## b2 1.000 0.880 0.886
## b3 1.000 0.880 0.874
## RIz =~
## m1 1.000 0.421 0.425
## m2 1.000 0.421 0.416
## m3 1.000 0.421 0.426
## wx1 =~
## a1F 1.000 0.883 0.886
## wx2 =~
## a2F 1.000 0.888 0.887
## wx3 =~
## a3F 1.000 0.868 0.883
## wy1 =~
## b1 1.000 0.459 0.462
## wy2 =~
## b2 1.000 0.461 0.464
## wy3 =~
## b3 1.000 0.490 0.486
## wz1 =~
## m1 1.000 0.898 0.905
## wz2 =~
## m2 1.000 0.922 0.910
## wz3 =~
## m3 1.000 0.896 0.905
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wx2 ~
## wx1 0.165 0.037 4.447 0.000 0.164 0.164
## wy1 -0.090 0.112 -0.809 0.418 -0.047 -0.047
## wz1 0.203 0.034 6.035 0.000 0.205 0.205
## wy2 ~
## wx1 0.030 0.031 0.970 0.332 0.058 0.058
## wy1 0.091 0.154 0.591 0.554 0.090 0.090
## wz1 0.037 0.037 0.992 0.321 0.072 0.072
## wz2 ~
## wx1 0.093 0.030 3.091 0.002 0.089 0.089
## wy1 0.202 0.118 1.719 0.086 0.100 0.100
## wz1 0.370 0.044 8.464 0.000 0.360 0.360
## wx3 ~
## wx2 0.197 0.040 4.971 0.000 0.202 0.202
## wy2 -0.057 0.075 -0.764 0.445 -0.030 -0.030
## wz2 0.237 0.035 6.667 0.000 0.251 0.251
## wy3 ~
## wx2 -0.007 0.028 -0.241 0.810 -0.012 -0.012
## wy2 0.470 0.061 7.684 0.000 0.443 0.443
## wz2 0.019 0.028 0.695 0.487 0.037 0.037
## wz3 ~
## wx2 0.007 0.034 0.198 0.843 0.007 0.007
## wy2 -0.103 0.075 -1.387 0.165 -0.053 -0.053
## wz2 0.439 0.041 10.802 0.000 0.452 0.452
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wx1 ~~
## wy1 0.016 0.026 0.613 0.540 0.039 0.039
## wz1 0.238 0.039 6.063 0.000 0.301 0.301
## wy1 ~~
## wz1 0.035 0.031 1.135 0.257 0.086 0.086
## .wx2 ~~
## .wy2 0.006 0.022 0.290 0.772 0.017 0.017
## .wz2 0.224 0.020 11.200 0.000 0.316 0.316
## .wy2 ~~
## .wz2 0.030 0.023 1.313 0.189 0.080 0.080
## .wx3 ~~
## .wy3 0.018 0.013 1.339 0.180 0.051 0.051
## .wz3 0.230 0.021 11.047 0.000 0.357 0.357
## .wy3 ~~
## .wz3 -0.016 0.013 -1.214 0.225 -0.045 -0.045
## RIx ~~
## RIy -0.029 0.026 -1.116 0.264 -0.072 -0.072
## RIz 0.074 0.038 1.968 0.049 0.380 0.380
## RIy ~~
## RIz -0.057 0.031 -1.872 0.061 -0.154 -0.154
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .a1F -0.029 0.015 -1.913 0.056 -0.029 -0.029
## .a2F 0.003 0.016 0.212 0.832 0.003 0.003
## .a3F -0.009 0.022 -0.411 0.681 -0.009 -0.009
## .b1 0.017 0.016 1.108 0.268 0.017 0.018
## .b2 0.020 0.017 1.219 0.223 0.020 0.021
## .b3 -0.015 0.021 -0.714 0.475 -0.015 -0.015
## .m1 -0.017 0.015 -1.140 0.254 -0.017 -0.017
## .m2 0.005 0.016 0.291 0.771 0.005 0.005
## .m3 0.005 0.022 0.249 0.803 0.005 0.005
## RIx 0.000 0.000 0.000
## RIy 0.000 0.000 0.000
## RIz 0.000 0.000 0.000
## wx1 0.000 0.000 0.000
## .wx2 0.000 0.000 0.000
## .wx3 0.000 0.000 0.000
## wy1 0.000 0.000 0.000
## .wy2 0.000 0.000 0.000
## .wy3 0.000 0.000 0.000
## wz1 0.000 0.000 0.000
## .wz2 0.000 0.000 0.000
## .wz3 0.000 0.000 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIx 0.214 0.039 5.463 0.000 1.000 1.000
## RIy 0.775 0.038 20.636 0.000 1.000 1.000
## RIz 0.178 0.054 3.306 0.001 1.000 1.000
## wx1 0.779 0.041 18.786 0.000 1.000 1.000
## wy1 0.210 0.034 6.236 0.000 1.000 1.000
## wz1 0.806 0.057 14.232 0.000 1.000 1.000
## .wx2 0.718 0.028 25.763 0.000 0.911 0.911
## .wy2 0.208 0.033 6.230 0.000 0.979 0.979
## .wz2 0.702 0.027 25.782 0.000 0.826 0.826
## .wx3 0.647 0.028 22.892 0.000 0.859 0.859
## .wy3 0.192 0.013 15.271 0.000 0.799 0.799
## .wz3 0.640 0.028 23.158 0.000 0.797 0.797
## .a1F 0.000 0.000 0.000
## .a2F 0.000 0.000 0.000
## .a3F 0.000 0.000 0.000
## .b1 0.000 0.000 0.000
## .b2 0.000 0.000 0.000
## .b3 0.000 0.000 0.000
## .m1 0.000 0.000 0.000
## .m2 0.000 0.000 0.000
## .m3 0.000 0.000 0.000
##
##
## Group 2 [0]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIx =~
## a1F 1.000 0.513 0.517
## a2F 1.000 0.513 0.523
## a3F 1.000 0.513 0.510
## RIy =~
## b1 1.000 0.841 0.832
## b2 1.000 0.841 0.817
## b3 1.000 0.841 0.802
## RIz =~
## m1 1.000 0.479 0.483
## m2 1.000 0.479 0.483
## m3 1.000 0.479 0.476
## wx1 =~
## a1F 1.000 0.849 0.856
## wx2 =~
## a2F 1.000 0.837 0.852
## wx3 =~
## a3F 1.000 0.865 0.860
## wy1 =~
## b1 1.000 0.562 0.555
## wy2 =~
## b2 1.000 0.593 0.576
## wy3 =~
## b3 1.000 0.626 0.597
## wz1 =~
## m1 1.000 0.869 0.876
## wz2 =~
## m2 1.000 0.868 0.875
## wz3 =~
## m3 1.000 0.885 0.879
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wx2 ~
## wx1 0.102 0.038 2.684 0.007 0.104 0.104
## wy1 -0.032 0.090 -0.355 0.722 -0.021 -0.021
## wz1 0.151 0.034 4.477 0.000 0.156 0.156
## wy2 ~
## wx1 0.011 0.026 0.409 0.682 0.015 0.015
## wy1 0.492 0.108 4.539 0.000 0.466 0.466
## wz1 -0.012 0.028 -0.434 0.664 -0.018 -0.018
## wz2 ~
## wx1 0.031 0.030 1.049 0.294 0.030 0.030
## wy1 -0.013 0.087 -0.146 0.884 -0.008 -0.008
## wz1 0.336 0.042 8.006 0.000 0.336 0.336
## wx3 ~
## wx2 0.229 0.038 5.998 0.000 0.221 0.221
## wy2 0.003 0.066 0.047 0.963 0.002 0.002
## wz2 0.167 0.036 4.650 0.000 0.168 0.168
## wy3 ~
## wx2 -0.016 0.026 -0.621 0.535 -0.022 -0.022
## wy2 0.655 0.056 11.665 0.000 0.620 0.620
## wz2 -0.003 0.027 -0.123 0.902 -0.005 -0.005
## wz3 ~
## wx2 0.010 0.033 0.292 0.770 0.009 0.009
## wy2 -0.065 0.065 -0.994 0.320 -0.043 -0.043
## wz2 0.419 0.042 10.012 0.000 0.411 0.411
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wx1 ~~
## wy1 -0.018 0.032 -0.558 0.577 -0.038 -0.038
## wz1 0.131 0.032 4.090 0.000 0.177 0.177
## wy1 ~~
## wz1 -0.016 0.038 -0.413 0.679 -0.033 -0.033
## .wx2 ~~
## .wy2 -0.006 0.017 -0.337 0.736 -0.013 -0.013
## .wz2 0.175 0.020 8.840 0.000 0.262 0.262
## .wy2 ~~
## .wz2 -0.008 0.016 -0.484 0.628 -0.018 -0.018
## .wx3 ~~
## .wy3 -0.020 0.014 -1.378 0.168 -0.049 -0.049
## .wz3 0.230 0.019 11.950 0.000 0.349 0.349
## .wy3 ~~
## .wz3 0.001 0.014 0.045 0.964 0.002 0.002
## RIx ~~
## RIy 0.002 0.032 0.057 0.955 0.004 0.004
## RIz 0.144 0.031 4.688 0.000 0.586 0.586
## RIy ~~
## RIz 0.007 0.038 0.197 0.844 0.018 0.018
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .a1F 0.008 0.014 0.556 0.578 0.008 0.008
## .a2F -0.008 0.014 -0.555 0.579 -0.008 -0.008
## .a3F 0.043 0.021 2.090 0.037 0.043 0.043
## .b1 -0.032 0.015 -2.139 0.032 -0.032 -0.032
## .b2 -0.063 0.016 -3.942 0.000 -0.063 -0.062
## .b3 -0.087 0.021 -4.186 0.000 -0.087 -0.083
## .m1 0.014 0.014 0.975 0.329 0.014 0.014
## .m2 0.008 0.014 0.522 0.602 0.008 0.008
## .m3 0.032 0.020 1.575 0.115 0.032 0.032
## RIx 0.000 0.000 0.000
## RIy 0.000 0.000 0.000
## RIz 0.000 0.000 0.000
## wx1 0.000 0.000 0.000
## .wx2 0.000 0.000 0.000
## .wx3 0.000 0.000 0.000
## wy1 0.000 0.000 0.000
## .wy2 0.000 0.000 0.000
## .wy3 0.000 0.000 0.000
## wz1 0.000 0.000 0.000
## .wz2 0.000 0.000 0.000
## .wz3 0.000 0.000 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIx 0.264 0.033 8.038 0.000 1.000 1.000
## RIy 0.707 0.064 11.069 0.000 1.000 1.000
## RIz 0.230 0.047 4.911 0.000 1.000 1.000
## wx1 0.721 0.035 20.612 0.000 1.000 1.000
## wy1 0.315 0.062 5.105 0.000 1.000 1.000
## wz1 0.756 0.049 15.432 0.000 1.000 1.000
## .wx2 0.671 0.028 23.885 0.000 0.958 0.958
## .wy2 0.275 0.021 13.384 0.000 0.782 0.782
## .wz2 0.665 0.026 25.997 0.000 0.882 0.882
## .wx3 0.674 0.026 25.694 0.000 0.900 0.900
## .wy3 0.240 0.013 18.606 0.000 0.614 0.614
## .wz3 0.647 0.026 25.304 0.000 0.826 0.826
## .a1F 0.000 0.000 0.000
## .a2F 0.000 0.000 0.000
## .a3F 0.000 0.000 0.000
## .b1 0.000 0.000 0.000
## .b2 0.000 0.000 0.000
## .b3 0.000 0.000 0.000
## .m1 0.000 0.000 0.000
## .m2 0.000 0.000 0.000
## .m3 0.000 0.000 0.000fitMeasures(RICLPM_Family_fit_Peers, fit.measures = c("chisq","df","pvalue","rmsea","srmr","cfi"))## chisq df pvalue rmsea srmr cfi
## 30.420 6.000 0.000 0.029 0.010 0.999Family conflict & Gender
RICLPM_Family_fit_Sex <- lavaan::lavaan(RICLPM_Family,
data = Data,
missing = "fiml",
meanstructure = TRUE,
int.ov.free = TRUE,
group = "Sex"
)
summary(RICLPM_Family_fit_Sex, standardized = TRUE)## lavaan 0.6.16 ended normally after 160 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 102
##
## Number of observations per group: Used Total
## 1 4953 4953
## 2 4522 4524
## Number of missing patterns per group:
## 1 65
## 2 51
##
## Model Test User Model:
##
## Test statistic 27.736
## Degrees of freedom 6
## P-value (Chi-square) 0.000
## Test statistic for each group:
## 1 20.624
## 2 7.112
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [1]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIx =~
## a1F 1.000 0.495 0.496
## a2F 1.000 0.495 0.508
## a3F 1.000 0.495 0.518
## RIy =~
## b1 1.000 0.879 0.874
## b2 1.000 0.879 0.859
## b3 1.000 0.879 0.832
## RIz =~
## m1 1.000 0.520 0.513
## m2 1.000 0.520 0.538
## m3 1.000 0.520 0.580
## wx1 =~
## a1F 1.000 0.867 0.868
## wx2 =~
## a2F 1.000 0.840 0.861
## wx3 =~
## a3F 1.000 0.818 0.856
## wy1 =~
## b1 1.000 0.488 0.486
## wy2 =~
## b2 1.000 0.523 0.512
## wy3 =~
## b3 1.000 0.587 0.555
## wz1 =~
## m1 1.000 0.869 0.858
## wz2 =~
## m2 1.000 0.815 0.843
## wz3 =~
## m3 1.000 0.730 0.815
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wx2 ~
## wx1 0.129 0.036 3.548 0.000 0.133 0.133
## wy1 -0.036 0.106 -0.337 0.736 -0.021 -0.021
## wz1 0.171 0.031 5.512 0.000 0.177 0.177
## wy2 ~
## wx1 0.055 0.029 1.920 0.055 0.092 0.092
## wy1 0.291 0.158 1.841 0.066 0.271 0.271
## wz1 0.009 0.031 0.294 0.769 0.015 0.015
## wz2 ~
## wx1 0.079 0.027 2.920 0.004 0.084 0.084
## wy1 0.104 0.100 1.045 0.296 0.062 0.062
## wz1 0.288 0.037 7.769 0.000 0.308 0.308
## wx3 ~
## wx2 0.217 0.038 5.734 0.000 0.223 0.223
## wy2 0.085 0.065 1.298 0.194 0.054 0.054
## wz2 0.182 0.036 5.044 0.000 0.182 0.182
## wy3 ~
## wx2 0.011 0.026 0.445 0.656 0.016 0.016
## wy2 0.634 0.056 11.414 0.000 0.565 0.565
## wz2 -0.018 0.027 -0.658 0.510 -0.025 -0.025
## wz3 ~
## wx2 0.044 0.031 1.416 0.157 0.050 0.050
## wy2 -0.075 0.061 -1.232 0.218 -0.054 -0.054
## wz2 0.315 0.042 7.553 0.000 0.351 0.351
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wx1 ~~
## wy1 0.033 0.028 1.163 0.245 0.078 0.078
## wz1 0.179 0.030 6.024 0.000 0.237 0.237
## wy1 ~~
## wz1 0.022 0.029 0.763 0.446 0.053 0.053
## .wx2 ~~
## .wy2 -0.001 0.019 -0.040 0.968 -0.002 -0.002
## .wz2 0.151 0.018 8.253 0.000 0.243 0.243
## .wy2 ~~
## .wz2 -0.003 0.018 -0.181 0.856 -0.009 -0.009
## .wx3 ~~
## .wy3 -0.002 0.013 -0.115 0.909 -0.004 -0.004
## .wz3 0.170 0.017 9.905 0.000 0.325 0.325
## .wy3 ~~
## .wz3 -0.008 0.012 -0.697 0.486 -0.026 -0.026
## RIx ~~
## RIy -0.042 0.028 -1.513 0.130 -0.096 -0.096
## RIz 0.109 0.028 3.886 0.000 0.425 0.425
## RIy ~~
## RIz -0.033 0.028 -1.175 0.240 -0.072 -0.072
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .a1F 0.047 0.014 3.323 0.001 0.047 0.047
## .a2F 0.024 0.014 1.701 0.089 0.024 0.025
## .a3F -0.019 0.020 -0.970 0.332 -0.019 -0.020
## .b1 -0.021 0.015 -1.406 0.160 -0.021 -0.021
## .b2 -0.035 0.016 -2.168 0.030 -0.035 -0.034
## .b3 -0.095 0.021 -4.536 0.000 -0.095 -0.090
## .m1 0.086 0.015 5.881 0.000 0.086 0.085
## .m2 -0.046 0.014 -3.283 0.001 -0.046 -0.048
## .m3 -0.183 0.018 -10.022 0.000 -0.183 -0.205
## RIx 0.000 0.000 0.000
## RIy 0.000 0.000 0.000
## RIz 0.000 0.000 0.000
## wx1 0.000 0.000 0.000
## .wx2 0.000 0.000 0.000
## .wx3 0.000 0.000 0.000
## wy1 0.000 0.000 0.000
## .wy2 0.000 0.000 0.000
## .wy3 0.000 0.000 0.000
## wz1 0.000 0.000 0.000
## .wz2 0.000 0.000 0.000
## .wz3 0.000 0.000 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIx 0.245 0.033 7.326 0.000 1.000 1.000
## RIy 0.773 0.053 14.638 0.000 1.000 1.000
## RIz 0.270 0.038 7.022 0.000 1.000 1.000
## wx1 0.752 0.036 21.051 0.000 1.000 1.000
## wy1 0.238 0.050 4.767 0.000 1.000 1.000
## wz1 0.755 0.041 18.485 0.000 1.000 1.000
## .wx2 0.663 0.027 24.397 0.000 0.940 0.940
## .wy2 0.250 0.030 8.381 0.000 0.913 0.913
## .wz2 0.584 0.024 24.499 0.000 0.879 0.879
## .wx3 0.595 0.025 24.015 0.000 0.889 0.889
## .wy3 0.235 0.012 19.158 0.000 0.681 0.681
## .wz3 0.460 0.022 20.584 0.000 0.862 0.862
## .a1F 0.000 0.000 0.000
## .a2F 0.000 0.000 0.000
## .a3F 0.000 0.000 0.000
## .b1 0.000 0.000 0.000
## .b2 0.000 0.000 0.000
## .b3 0.000 0.000 0.000
## .m1 0.000 0.000 0.000
## .m2 0.000 0.000 0.000
## .m3 0.000 0.000 0.000
##
##
## Group 2 [2]:
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIx =~
## a1F 1.000 0.481 0.488
## a2F 1.000 0.481 0.477
## a3F 1.000 0.481 0.465
## RIy =~
## b1 1.000 0.856 0.855
## b2 1.000 0.856 0.852
## b3 1.000 0.856 0.856
## RIz =~
## m1 1.000 0.484 0.503
## m2 1.000 0.484 0.468
## m3 1.000 0.484 0.459
## wx1 =~
## a1F 1.000 0.861 0.873
## wx2 =~
## a2F 1.000 0.886 0.879
## wx3 =~
## a3F 1.000 0.916 0.885
## wy1 =~
## b1 1.000 0.518 0.518
## wy2 =~
## b2 1.000 0.526 0.523
## wy3 =~
## b3 1.000 0.518 0.517
## wz1 =~
## m1 1.000 0.831 0.864
## wz2 =~
## m2 1.000 0.913 0.884
## wz3 =~
## m3 1.000 0.937 0.888
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wx2 ~
## wx1 0.146 0.041 3.577 0.000 0.142 0.142
## wy1 -0.103 0.097 -1.062 0.288 -0.060 -0.060
## wz1 0.174 0.038 4.623 0.000 0.163 0.163
## wy2 ~
## wx1 -0.031 0.028 -1.120 0.263 -0.051 -0.051
## wy1 0.324 0.114 2.832 0.005 0.320 0.320
## wz1 0.005 0.033 0.139 0.889 0.007 0.007
## wz2 ~
## wx1 0.050 0.031 1.627 0.104 0.047 0.047
## wy1 0.035 0.092 0.387 0.699 0.020 0.020
## wz1 0.368 0.044 8.301 0.000 0.335 0.335
## wx3 ~
## wx2 0.224 0.041 5.515 0.000 0.217 0.217
## wy2 -0.158 0.075 -2.106 0.035 -0.091 -0.091
## wz2 0.204 0.036 5.609 0.000 0.203 0.203
## wy3 ~
## wx2 -0.045 0.027 -1.639 0.101 -0.077 -0.077
## wy2 0.519 0.060 8.686 0.000 0.527 0.527
## wz2 0.020 0.027 0.740 0.459 0.036 0.036
## wz3 ~
## wx2 -0.000 0.035 -0.002 0.998 -0.000 -0.000
## wy2 -0.086 0.074 -1.161 0.246 -0.048 -0.048
## wz2 0.427 0.040 10.682 0.000 0.417 0.417
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## wx1 ~~
## wy1 -0.048 0.030 -1.626 0.104 -0.108 -0.108
## wz1 0.151 0.036 4.206 0.000 0.211 0.211
## wy1 ~~
## wz1 -0.006 0.032 -0.198 0.843 -0.015 -0.015
## .wx2 ~~
## .wy2 -0.001 0.019 -0.047 0.962 -0.002 -0.002
## .wz2 0.243 0.020 11.946 0.000 0.331 0.331
## .wy2 ~~
## .wz2 0.017 0.018 0.946 0.344 0.041 0.041
## .wx3 ~~
## .wy3 -0.009 0.015 -0.595 0.552 -0.023 -0.023
## .wz3 0.273 0.022 12.417 0.000 0.375 0.375
## .wy3 ~~
## .wz3 -0.024 0.014 -1.656 0.098 -0.064 -0.064
## RIx ~~
## RIy 0.027 0.030 0.913 0.361 0.067 0.067
## RIz 0.140 0.035 4.038 0.000 0.601 0.601
## RIy ~~
## RIz -0.011 0.032 -0.329 0.742 -0.026 -0.026
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .a1F -0.070 0.015 -4.779 0.000 -0.070 -0.071
## .a2F -0.030 0.016 -1.936 0.053 -0.030 -0.030
## .a3F 0.061 0.023 2.681 0.007 0.061 0.059
## .b1 0.003 0.016 0.174 0.862 0.003 0.003
## .b2 -0.014 0.017 -0.855 0.392 -0.014 -0.014
## .b3 -0.013 0.021 -0.623 0.533 -0.013 -0.013
## .m1 -0.097 0.015 -6.654 0.000 -0.097 -0.101
## .m2 0.062 0.016 3.912 0.000 0.062 0.060
## .m3 0.243 0.023 10.690 0.000 0.243 0.231
## RIx 0.000 0.000 0.000
## RIy 0.000 0.000 0.000
## RIz 0.000 0.000 0.000
## wx1 0.000 0.000 0.000
## .wx2 0.000 0.000 0.000
## .wx3 0.000 0.000 0.000
## wy1 0.000 0.000 0.000
## .wy2 0.000 0.000 0.000
## .wy3 0.000 0.000 0.000
## wz1 0.000 0.000 0.000
## .wz2 0.000 0.000 0.000
## .wz3 0.000 0.000 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## RIx 0.231 0.039 5.893 0.000 1.000 1.000
## RIy 0.732 0.045 16.343 0.000 1.000 1.000
## RIz 0.234 0.047 4.964 0.000 1.000 1.000
## wx1 0.742 0.042 17.862 0.000 1.000 1.000
## wy1 0.269 0.041 6.478 0.000 1.000 1.000
## wz1 0.691 0.049 14.042 0.000 1.000 1.000
## .wx2 0.737 0.030 24.819 0.000 0.938 0.938
## .wy2 0.246 0.025 9.947 0.000 0.892 0.892
## .wz2 0.733 0.025 28.750 0.000 0.879 0.879
## .wx3 0.730 0.030 24.494 0.000 0.870 0.870
## .wy3 0.191 0.012 15.314 0.000 0.713 0.713
## .wz3 0.725 0.029 25.249 0.000 0.826 0.826
## .a1F 0.000 0.000 0.000
## .a2F 0.000 0.000 0.000
## .a3F 0.000 0.000 0.000
## .b1 0.000 0.000 0.000
## .b2 0.000 0.000 0.000
## .b3 0.000 0.000 0.000
## .m1 0.000 0.000 0.000
## .m2 0.000 0.000 0.000
## .m3 0.000 0.000 0.000fitMeasures(RICLPM_Family_fit_Sex, fit.measures = c("chisq","df","pvalue","rmsea","srmr","cfi"))## chisq df pvalue rmsea srmr cfi
## 27.736 6.000 0.000 0.028 0.010 0.999Constrained lagged-parameters for multigroups
Multigroup Peers
MG_Family <- '
RIx =~ 1*a1F + 1*a2F + 1*a3F
RIy =~ 1*b1 + 1*b2 + 1*b3
RIz =~ 1*m1 + 1*m2 + 1*m3
wx1 =~ 1*a1F
wx2 =~ 1*a2F
wx3 =~ 1*a3F
wy1 =~ 1*b1
wy2 =~ 1*b2
wy3 =~ 1*b3
wz1 =~ 1*m1
wz2 =~ 1*m2
wz3 =~ 1*m3
# Estimate lagged effects between within-person centered variables (constrain
# autoregressive effects across groups)
wx2 ~ c(a1, a1)*wx1 + c(b1, b1)*wy1 + c(c1, c1)*wz1
wy2 ~ c(d1, d1)*wx1 + c(e1, e1)*wy1 + c(f1, f1)*wz1
wz2 ~ c(g1, g1)*wx1 + c(h1, h1)*wy1 + c(i1, i1)*wz1
wx3 ~ c(a2, a2)*wx2 + c(b2, b2)*wy2 + c(c2, c2)*wz2
wy3 ~ c(d2, d2)*wx2 + c(e2, e2)*wy2 + c(f2, f2)*wz2
wz3 ~ c(g2, g2)*wx2 + c(h2, h2)*wy2 + c(i2, i2)*wz2
wx1 ~~ wy1
wx1 ~~ wz1
wy1 ~~ wz1
wx2 ~~ wy2
wx2 ~~ wz2
wy2 ~~ wz2
wx3 ~~ wy3
wx3 ~~ wz3
wy3 ~~ wz3
RIx ~~ RIx
RIy ~~ RIy
RIz ~~ RIz
RIx ~~ RIy
RIx ~~ RIz
RIy ~~ RIz
wx1 ~~ wx1
wy1 ~~ wy1
wz1 ~~ wz1
wx2 ~~ wx2
wy2 ~~ wy2
wz2 ~~ wz2
wx3 ~~ wx3
wy3 ~~ wy3
wz3 ~~ wz3'
MG_Family_Peers_fit <- lavaan(MG_Family,
data = Data,
missing = 'fiml',
meanstructure = TRUE,
int.ov.free = TRUE,
group = "Resilience_Peers")
anova(RICLPM_Family_fit_Peers, MG_Family_Peers_fit)##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## RICLPM_Family_fit_Peers 6 151860 152590 30.420
## MG_Family_Peers_fit 24 151842 152443 47.533 17.113 0 18 0.5153Multigroup Gender
MG_Family_Sex_fit <- lavaan(MG_Family,
data = Data,
missing = 'fiml',
meanstructure = TRUE,
int.ov.free = TRUE,
group = "Sex")
anova(RICLPM_Family_fit_Sex, MG_Family_Sex_fit)##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## RICLPM_Family_fit_Sex 6 151231 151961 27.736
## MG_Family_Sex_fit 24 151218 151819 50.702 22.966 0.0076314 18 0.1919Ayla Pollmann - 2024