#Load packages
#read in tidyverse
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.6
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.1 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.2.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(tidyr)
library(lavaan) #why do you need this package for this analysis?## This is lavaan 0.6-20
## lavaan is FREE software! Please report any bugs.library(tidySEM) #same as above
library(knitr)
library(ggplot2)
library(ggdist)
library(viridis)## Loading required package: viridisLitelibrary(paletteer)
#load psych
library(psych)##
## Attaching package: 'psych'
##
## The following object is masked from 'package:lavaan':
##
## cor2cov
##
## The following objects are masked from 'package:ggplot2':
##
## %+%, alpha#install.packages(c("tidytext", "wordcloud", "RColorBrewer"))
library(tidytext)
library(wordcloud)## Loading required package: RColorBrewerlibrary(RColorBrewer)
library(modsem)## This is modsem (1.0.22). Please report any bugs!
## OpenMP is not available! Multi-threading will not work properly!options(
scipen = 999,
digits = 6
)#Read in data
#read in data
CESSD_wide <- read.csv("CESSD.W1andW2_Wide.csv")#some light data wrangling/mean centering
CESSD_wide <- CESSD_wide %>%
mutate(c_soc_w2_c = c_soc_w2 - mean(c_soc_w2, na.rm = TRUE),
pcc_soc_w2_c = pcc_soc_w2 - mean(pcc_soc_w2, na.rm = TRUE),
c_soc_x_pcc = c_soc_w2_c * pcc_soc_w2_c
)#Longitudinal Models ##Longitudinal model 1 – c_soc and pcc_soc predicting ERI-R W2 controlling for W1 Model
#specify the model
path_model_1 <- 'eri_r_w2 ~ eri_r_w1 + c_soc_w2_c + pcc_soc_w2_c'
#now estimate the model
path_fit_1 <- sem(path_model_1, CESSD_wide, missing = "fiml", estimator = "MLR") ## Warning: lavaan->lav_data_full():
## 186 cases were deleted due to missing values in exogenous variable(s),
## while fixed.x = TRUE.summary(path_fit_1, fit.measures = T, standardized = T)## lavaan 0.6-20 ended normally after 9 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 5
##
## Used Total
## Number of observations 311 497
## Number of missing patterns 2
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 107.532 92.609
## Degrees of freedom 3 3
## P-value 0.000 0.000
## Scaling correction factor 1.161
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -290.890 -290.890
## Loglikelihood unrestricted model (H1) -290.890 -290.890
##
## Akaike (AIC) 591.780 591.780
## Bayesian (BIC) 610.479 610.479
## Sample-size adjusted Bayesian (SABIC) 594.621 594.621
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 NA
## 90 Percent confidence interval - lower 0.000 NA
## 90 Percent confidence interval - upper 0.000 NA
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## eri_r_w2 ~
## eri_r_w1 0.441 0.054 8.175 0.000 0.441 0.455
## c_soc_w2_c 0.072 0.050 1.443 0.149 0.072 0.090
## pcc_soc_w2_c 0.103 0.059 1.760 0.078 0.103 0.119
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .eri_r_w2 1.566 0.155 10.094 0.000 1.566 2.114
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .eri_r_w2 0.387 0.032 11.942 0.000 0.387 0.706##Longitudinal model 2 – c_soc and pcc_soc + interaction predicting ERI-R Model
#specify the model with itneration
path_model_2 <- 'eri_r_w2 ~ eri_r_w1 + c_soc_w2_c + pcc_soc_w2_c + c_soc_x_pcc'
#now estimate the model
path_fit_2 <- sem(path_model_2, CESSD_wide, missing = "fiml", estimator = "MLR") ## Warning: lavaan->lav_data_full():
## 186 cases were deleted due to missing values in exogenous variable(s),
## while fixed.x = TRUE.summary(path_fit_2, fit.measures = T, standardized = T)## lavaan 0.6-20 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 6
##
## Used Total
## Number of observations 311 497
## Number of missing patterns 2
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 108.897 90.193
## Degrees of freedom 4 4
## P-value 0.000 0.000
## Scaling correction factor 1.207
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -290.207 -290.207
## Loglikelihood unrestricted model (H1) -290.207 -290.207
##
## Akaike (AIC) 592.415 592.415
## Bayesian (BIC) 614.854 614.854
## Sample-size adjusted Bayesian (SABIC) 595.824 595.824
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 NA
## 90 Percent confidence interval - lower 0.000 NA
## 90 Percent confidence interval - upper 0.000 NA
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## eri_r_w2 ~
## eri_r_w1 0.443 0.054 8.219 0.000 0.443 0.457
## c_soc_w2_c 0.078 0.051 1.538 0.124 0.078 0.097
## pcc_soc_w2_c 0.110 0.060 1.826 0.068 0.110 0.127
## c_soc_x_pcc 0.043 0.042 1.015 0.310 0.043 0.058
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .eri_r_w2 1.535 0.153 10.014 0.000 1.535 2.072
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .eri_r_w2 0.385 0.032 11.994 0.000 0.385 0.702##Longitudinal model 3 – c_soc and pcc_soc predicting ERI-R W2 controlling for W1 Model
#specify the model
path_model_3 <- 'eri_e_w2 ~ eri_e_w1 + c_soc_w2_c + pcc_soc_w2_c'
#now estimate the model
path_fit_3 <- sem(path_model_3, CESSD_wide, missing = "fiml", estimator = "MLR") ## Warning: lavaan->lav_data_full():
## 188 cases were deleted due to missing values in exogenous variable(s),
## while fixed.x = TRUE.summary(path_fit_3, fit.measures = T, standardized = T)## lavaan 0.6-20 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 5
##
## Used Total
## Number of observations 309 497
## Number of missing patterns 2
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 106.385 90.664
## Degrees of freedom 3 3
## P-value 0.000 0.000
## Scaling correction factor 1.173
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -302.496 -302.496
## Loglikelihood unrestricted model (H1) -302.496 -302.496
##
## Akaike (AIC) 614.992 614.992
## Bayesian (BIC) 633.659 633.659
## Sample-size adjusted Bayesian (SABIC) 617.801 617.801
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 NA
## 90 Percent confidence interval - lower 0.000 NA
## 90 Percent confidence interval - upper 0.000 NA
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## eri_e_w2 ~
## eri_e_w1 0.430 0.050 8.573 0.000 0.430 0.428
## c_soc_w2_c 0.147 0.061 2.396 0.017 0.147 0.174
## pcc_soc_w2_c 0.080 0.061 1.298 0.194 0.080 0.088
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .eri_e_w2 1.438 0.119 12.093 0.000 1.438 1.859
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .eri_e_w2 0.423 0.033 12.851 0.000 0.423 0.707##Longitudinal model 4 – c_soc and pcc_soc + interaction predicting ERI-R Model
#specify the model with itneration
path_model_4 <- 'eri_e_w2 ~ eri_e_w1 + c_soc_w2_c + pcc_soc_w2_c + c_soc_x_pcc'
#now estimate the model
path_fit_4 <- sem(path_model_4, CESSD_wide, missing = "fiml", estimator = "MLR") ## Warning: lavaan->lav_data_full():
## 188 cases were deleted due to missing values in exogenous variable(s),
## while fixed.x = TRUE.summary(path_fit_4, fit.measures = T, standardized = T)## Warning: lavaan->lav_fit_cfi_lavobject():
## computation of robust CFI resulted in NA values.## Warning: lavaan->lav_fit_rmsea_lavobject():
## computation of robust RMSEA resulted in NA values.## lavaan 0.6-20 ended normally after 12 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 6
##
## Used Total
## Number of observations 309 497
## Number of missing patterns 2
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 108.825 89.287
## Degrees of freedom 4 4
## P-value 0.000 0.000
## Scaling correction factor 1.219
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -301.276 -301.276
## Loglikelihood unrestricted model (H1) -301.276 -301.276
##
## Akaike (AIC) 614.552 614.552
## Bayesian (BIC) 636.952 636.952
## Sample-size adjusted Bayesian (SABIC) 617.922 617.922
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 NA
## 90 Percent confidence interval - lower 0.000 NA
## 90 Percent confidence interval - upper 0.000 NA
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## eri_e_w2 ~
## eri_e_w1 0.429 0.050 8.572 0.000 0.429 0.427
## c_soc_w2_c 0.153 0.062 2.463 0.014 0.153 0.181
## pcc_soc_w2_c 0.089 0.061 1.453 0.146 0.089 0.099
## c_soc_x_pcc 0.060 0.045 1.335 0.182 0.060 0.076
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .eri_e_w2 1.406 0.119 11.772 0.000 1.406 1.818
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .eri_e_w2 0.419 0.033 12.861 0.000 0.419 0.701