ARWA analysis
Quentin Lam
2024-12-11
library(bruceR)## Warning: package 'bruceR' was built under R version 4.3.3##
## bruceR (v2024.6)
## Broadly Useful Convenient and Efficient R functions
##
## Packages also loaded:
## ✔ data.table ✔ emmeans
## ✔ dplyr ✔ lmerTest
## ✔ tidyr ✔ effectsize
## ✔ stringr ✔ performance
## ✔ ggplot2 ✔ interactions
##
## Main functions of `bruceR`:
## cc() Describe() TTEST()
## add() Freq() MANOVA()
## .mean() Corr() EMMEANS()
## set.wd() Alpha() PROCESS()
## import() EFA() model_summary()
## print_table() CFA() lavaan_summary()
##
## For full functionality, please install all dependencies:
## install.packages("bruceR", dep=TRUE)
##
## Online documentation:
## https://psychbruce.github.io/bruceR
##
## To use this package in publications, please cite:
## Bao, H.-W.-S. (2024). bruceR: Broadly useful convenient and efficient R functions (Version 2024.6) [Computer software]. https://CRAN.R-project.org/package=bruceRset.wd()## ✔ Set working directory to "C:/Users/psyuser/Desktop/ARWA article"set.seed(6)
rm(list = ls())
library(tidyverse)## Warning: package 'readr' was built under R version 4.3.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ readr 2.1.5
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ data.table::between() masks dplyr::between()
## ✖ Matrix::expand() masks tidyr::expand()
## ✖ dplyr::filter() masks stats::filter()
## ✖ data.table::first() masks dplyr::first()
## ✖ lubridate::hour() masks data.table::hour()
## ✖ lubridate::isoweek() masks data.table::isoweek()
## ✖ dplyr::lag() masks stats::lag()
## ✖ data.table::last() masks dplyr::last()
## ✖ lubridate::mday() masks data.table::mday()
## ✖ lubridate::minute() masks data.table::minute()
## ✖ lubridate::month() masks data.table::month()
## ✖ Matrix::pack() masks tidyr::pack()
## ✖ lubridate::quarter() masks data.table::quarter()
## ✖ lubridate::second() masks data.table::second()
## ✖ purrr::transpose() masks data.table::transpose()
## ✖ Matrix::unpack() masks tidyr::unpack()
## ✖ lubridate::wday() masks data.table::wday()
## ✖ lubridate::week() masks data.table::week()
## ✖ lubridate::yday() masks data.table::yday()
## ✖ lubridate::year() masks data.table::year()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(mice)## Warning: package 'mice' was built under R version 4.3.3## Registered S3 methods overwritten by 'broom':
## method from
## tidy.glht jtools
## tidy.summary.glht jtools
##
## Attaching package: 'mice'
##
## The following object is masked from 'package:bruceR':
##
## cc
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following objects are masked from 'package:base':
##
## cbind, rbindlibrary(naniar)## Warning: package 'naniar' was built under R version 4.3.3library(broom)## Warning: package 'broom' was built under R version 4.3.3library(readxl)
data <- read.csv("./data/EEG_RS_lanExp.csv")
# Select the relevant columns and drop rows with NA values
data_selected <- data %>%
# select(EEGID, FatherEducation, MotherEducation, Income) %>%
mutate(Age_EEG_yr = Age_EEG / 12) %>% # convert Age_EEG from months to years
# keep unique EEGID values
distinct(EEGID, .keep_all = TRUE) %>%
dplyr::select(CWR, CDICT, ARITH, EWR, EDICT, PW, CMOI, EMOI, FatherEducation, MotherEducation, Income, Age_EEG_yr, FID, EEGID)
# Visualize the missing data pattern
vis_miss(data_selected)
# Analyze the pattern of missing data
missing_pattern <- naniar::miss_var_summary(data_selected)
print(missing_pattern)## # A tibble: 14 × 3
## variable n_miss pct_miss
## <chr> <int> <num>
## 1 CMOI 39 19.3
## 2 EMOI 39 19.3
## 3 PW 16 7.92
## 4 FatherEducation 13 6.44
## 5 Income 9 4.46
## 6 MotherEducation 7 3.47
## 7 CWR 5 2.48
## 8 EDICT 4 1.98
## 9 CDICT 3 1.49
## 10 ARITH 3 1.49
## 11 EWR 3 1.49
## 12 Age_EEG_yr 3 1.49
## 13 FID 3 1.49
## 14 EEGID 0 0# Test if the missing data is random using Little's MCAR test
mcar_test <- naniar::mcar_test(data_selected[, c("CMOI", "EMOI",
"FatherEducation",
"MotherEducation", "Income")])
print(mcar_test)## # A tibble: 1 × 4
## statistic df p.value missing.patterns
## <dbl> <dbl> <dbl> <int>
## 1 45.3 17 0.000221 9# If the missing data is random, perform imputation using the mice package
if (mcar_test$p.value > 0.05) {
print("The missing data is at random.")
imputed_data <- mice(data_selected[, c("CMOI", "EMOI",
"FatherEducation", "MotherEducation", "Income")],
method = "norm.predict", m = 5, maxit = 50, seed = 500)
completed_data <- complete(imputed_data, 1)
# Replace the original columns with the imputed data
data_selected$CMOI <- completed_data$CMOI
data_selected$EMOI <- completed_data$EMOI
data_selected$FatherEducation <- completed_data$FatherEducation
data_selected$MotherEducation <- completed_data$MotherEducation
data_selected$Income <- completed_data$Income
} else {
print("The missing data is not completely at random.")
}## [1] "The missing data is not completely at random."# Check if CMOI and EMOI are normally distributed
shapiro_test_cmo <- shapiro.test(data_selected$CMOI)
shapiro_test_emo <- shapiro.test(data_selected$EMOI)
print(shapiro_test_cmo)##
## Shapiro-Wilk normality test
##
## data: data_selected$CMOI
## W = 0.73803, p-value = 9.87e-16print(shapiro_test_emo)##
## Shapiro-Wilk normality test
##
## data: data_selected$EMOI
## W = 0.70746, p-value < 2.2e-16# Analyze the pattern of missing data
missing_pattern <- naniar::miss_var_summary(data_selected)
print(missing_pattern)## # A tibble: 14 × 3
## variable n_miss pct_miss
## <chr> <int> <num>
## 1 CMOI 39 19.3
## 2 EMOI 39 19.3
## 3 PW 16 7.92
## 4 FatherEducation 13 6.44
## 5 Income 9 4.46
## 6 MotherEducation 7 3.47
## 7 CWR 5 2.48
## 8 EDICT 4 1.98
## 9 CDICT 3 1.49
## 10 ARITH 3 1.49
## 11 EWR 3 1.49
## 12 Age_EEG_yr 3 1.49
## 13 FID 3 1.49
## 14 EEGID 0 0# Print the results of the normality tests
if (shapiro_test_cmo$p.value < 0.05) {
print("CMOI is not normally distributed.")
} else {
print("CMOI is normally distributed.")
}## [1] "CMOI is not normally distributed."if (shapiro_test_emo$p.value < 0.05) {
print("EMOI is not normally distributed.")
} else {
print("EMOI is normally distributed.")
}## [1] "EMOI is not normally distributed."# Choose imputation method based on normality test results
imputation_method <- ifelse(shapiro_test_cmo$p.value < 0.05 | shapiro_test_emo$p.value < 0.05, "pmm", "norm.predict")
# Perform imputation using the mice package
imputed_data <- mice(data_selected[, c("CMOI", "EMOI",
"FatherEducation", "MotherEducation", "Income")], method = imputation_method, m = 5, maxit = 50, seed = 500)##
## iter imp variable
## 1 1 CMOI EMOI FatherEducation MotherEducation Income
## 1 2 CMOI EMOI FatherEducation MotherEducation Income
## 1 3 CMOI EMOI FatherEducation MotherEducation Income
## 1 4 CMOI EMOI FatherEducation MotherEducation Income
## 1 5 CMOI EMOI FatherEducation MotherEducation Income
## 2 1 CMOI EMOI FatherEducation MotherEducation Income
## 2 2 CMOI EMOI FatherEducation MotherEducation Income
## 2 3 CMOI EMOI FatherEducation MotherEducation Income
## 2 4 CMOI EMOI FatherEducation MotherEducation Income
## 2 5 CMOI EMOI FatherEducation MotherEducation Income
## 3 1 CMOI EMOI FatherEducation MotherEducation Income
## 3 2 CMOI EMOI FatherEducation MotherEducation Income
## 3 3 CMOI EMOI FatherEducation MotherEducation Income
## 3 4 CMOI EMOI FatherEducation MotherEducation Income
## 3 5 CMOI EMOI FatherEducation MotherEducation Income
## 4 1 CMOI EMOI FatherEducation MotherEducation Income
## 4 2 CMOI EMOI FatherEducation MotherEducation Income
## 4 3 CMOI EMOI FatherEducation MotherEducation Income
## 4 4 CMOI EMOI FatherEducation MotherEducation Income
## 4 5 CMOI EMOI FatherEducation MotherEducation Income
## 5 1 CMOI EMOI FatherEducation MotherEducation Income
## 5 2 CMOI EMOI FatherEducation MotherEducation Income
## 5 3 CMOI EMOI FatherEducation MotherEducation Income
## 5 4 CMOI EMOI FatherEducation MotherEducation Income
## 5 5 CMOI EMOI FatherEducation MotherEducation Income
## 6 1 CMOI EMOI FatherEducation MotherEducation Income
## 6 2 CMOI EMOI FatherEducation MotherEducation Income
## 6 3 CMOI EMOI FatherEducation MotherEducation Income
## 6 4 CMOI EMOI FatherEducation MotherEducation Income
## 6 5 CMOI EMOI FatherEducation MotherEducation Income
## 7 1 CMOI EMOI FatherEducation MotherEducation Income
## 7 2 CMOI EMOI FatherEducation MotherEducation Income
## 7 3 CMOI EMOI FatherEducation MotherEducation Income
## 7 4 CMOI EMOI FatherEducation MotherEducation Income
## 7 5 CMOI EMOI FatherEducation MotherEducation Income
## 8 1 CMOI EMOI FatherEducation MotherEducation Income
## 8 2 CMOI EMOI FatherEducation MotherEducation Income
## 8 3 CMOI EMOI FatherEducation MotherEducation Income
## 8 4 CMOI EMOI FatherEducation MotherEducation Income
## 8 5 CMOI EMOI FatherEducation MotherEducation Income
## 9 1 CMOI EMOI FatherEducation MotherEducation Income
## 9 2 CMOI EMOI FatherEducation MotherEducation Income
## 9 3 CMOI EMOI FatherEducation MotherEducation Income
## 9 4 CMOI EMOI FatherEducation MotherEducation Income
## 9 5 CMOI EMOI FatherEducation MotherEducation Income
## 10 1 CMOI EMOI FatherEducation MotherEducation Income
## 10 2 CMOI EMOI FatherEducation MotherEducation Income
## 10 3 CMOI EMOI FatherEducation MotherEducation Income
## 10 4 CMOI EMOI FatherEducation MotherEducation Income
## 10 5 CMOI EMOI FatherEducation MotherEducation Income
## 11 1 CMOI EMOI FatherEducation MotherEducation Income
## 11 2 CMOI EMOI FatherEducation MotherEducation Income
## 11 3 CMOI EMOI FatherEducation MotherEducation Income
## 11 4 CMOI EMOI FatherEducation MotherEducation Income
## 11 5 CMOI EMOI FatherEducation MotherEducation Income
## 12 1 CMOI EMOI FatherEducation MotherEducation Income
## 12 2 CMOI EMOI FatherEducation MotherEducation Income
## 12 3 CMOI EMOI FatherEducation MotherEducation Income
## 12 4 CMOI EMOI FatherEducation MotherEducation Income
## 12 5 CMOI EMOI FatherEducation MotherEducation Income
## 13 1 CMOI EMOI FatherEducation MotherEducation Income
## 13 2 CMOI EMOI FatherEducation MotherEducation Income
## 13 3 CMOI EMOI FatherEducation MotherEducation Income
## 13 4 CMOI EMOI FatherEducation MotherEducation Income
## 13 5 CMOI EMOI FatherEducation MotherEducation Income
## 14 1 CMOI EMOI FatherEducation MotherEducation Income
## 14 2 CMOI EMOI FatherEducation MotherEducation Income
## 14 3 CMOI EMOI FatherEducation MotherEducation Income
## 14 4 CMOI EMOI FatherEducation MotherEducation Income
## 14 5 CMOI EMOI FatherEducation MotherEducation Income
## 15 1 CMOI EMOI FatherEducation MotherEducation Income
## 15 2 CMOI EMOI FatherEducation MotherEducation Income
## 15 3 CMOI EMOI FatherEducation MotherEducation Income
## 15 4 CMOI EMOI FatherEducation MotherEducation Income
## 15 5 CMOI EMOI FatherEducation MotherEducation Income
## 16 1 CMOI EMOI FatherEducation MotherEducation Income
## 16 2 CMOI EMOI FatherEducation MotherEducation Income
## 16 3 CMOI EMOI FatherEducation MotherEducation Income
## 16 4 CMOI EMOI FatherEducation MotherEducation Income
## 16 5 CMOI EMOI FatherEducation MotherEducation Income
## 17 1 CMOI EMOI FatherEducation MotherEducation Income
## 17 2 CMOI EMOI FatherEducation MotherEducation Income
## 17 3 CMOI EMOI FatherEducation MotherEducation Income
## 17 4 CMOI EMOI FatherEducation MotherEducation Income
## 17 5 CMOI EMOI FatherEducation MotherEducation Income
## 18 1 CMOI EMOI FatherEducation MotherEducation Income
## 18 2 CMOI EMOI FatherEducation MotherEducation Income
## 18 3 CMOI EMOI FatherEducation MotherEducation Income
## 18 4 CMOI EMOI FatherEducation MotherEducation Income
## 18 5 CMOI EMOI FatherEducation MotherEducation Income
## 19 1 CMOI EMOI FatherEducation MotherEducation Income
## 19 2 CMOI EMOI FatherEducation MotherEducation Income
## 19 3 CMOI EMOI FatherEducation MotherEducation Income
## 19 4 CMOI EMOI FatherEducation MotherEducation Income
## 19 5 CMOI EMOI FatherEducation MotherEducation Income
## 20 1 CMOI EMOI FatherEducation MotherEducation Income
## 20 2 CMOI EMOI FatherEducation MotherEducation Income
## 20 3 CMOI EMOI FatherEducation MotherEducation Income
## 20 4 CMOI EMOI FatherEducation MotherEducation Income
## 20 5 CMOI EMOI FatherEducation MotherEducation Income
## 21 1 CMOI EMOI FatherEducation MotherEducation Income
## 21 2 CMOI EMOI FatherEducation MotherEducation Income
## 21 3 CMOI EMOI FatherEducation MotherEducation Income
## 21 4 CMOI EMOI FatherEducation MotherEducation Income
## 21 5 CMOI EMOI FatherEducation MotherEducation Income
## 22 1 CMOI EMOI FatherEducation MotherEducation Income
## 22 2 CMOI EMOI FatherEducation MotherEducation Income
## 22 3 CMOI EMOI FatherEducation MotherEducation Income
## 22 4 CMOI EMOI FatherEducation MotherEducation Income
## 22 5 CMOI EMOI FatherEducation MotherEducation Income
## 23 1 CMOI EMOI FatherEducation MotherEducation Income
## 23 2 CMOI EMOI FatherEducation MotherEducation Income
## 23 3 CMOI EMOI FatherEducation MotherEducation Income
## 23 4 CMOI EMOI FatherEducation MotherEducation Income
## 23 5 CMOI EMOI FatherEducation MotherEducation Income
## 24 1 CMOI EMOI FatherEducation MotherEducation Income
## 24 2 CMOI EMOI FatherEducation MotherEducation Income
## 24 3 CMOI EMOI FatherEducation MotherEducation Income
## 24 4 CMOI EMOI FatherEducation MotherEducation Income
## 24 5 CMOI EMOI FatherEducation MotherEducation Income
## 25 1 CMOI EMOI FatherEducation MotherEducation Income
## 25 2 CMOI EMOI FatherEducation MotherEducation Income
## 25 3 CMOI EMOI FatherEducation MotherEducation Income
## 25 4 CMOI EMOI FatherEducation MotherEducation Income
## 25 5 CMOI EMOI FatherEducation MotherEducation Income
## 26 1 CMOI EMOI FatherEducation MotherEducation Income
## 26 2 CMOI EMOI FatherEducation MotherEducation Income
## 26 3 CMOI EMOI FatherEducation MotherEducation Income
## 26 4 CMOI EMOI FatherEducation MotherEducation Income
## 26 5 CMOI EMOI FatherEducation MotherEducation Income
## 27 1 CMOI EMOI FatherEducation MotherEducation Income
## 27 2 CMOI EMOI FatherEducation MotherEducation Income
## 27 3 CMOI EMOI FatherEducation MotherEducation Income
## 27 4 CMOI EMOI FatherEducation MotherEducation Income
## 27 5 CMOI EMOI FatherEducation MotherEducation Income
## 28 1 CMOI EMOI FatherEducation MotherEducation Income
## 28 2 CMOI EMOI FatherEducation MotherEducation Income
## 28 3 CMOI EMOI FatherEducation MotherEducation Income
## 28 4 CMOI EMOI FatherEducation MotherEducation Income
## 28 5 CMOI EMOI FatherEducation MotherEducation Income
## 29 1 CMOI EMOI FatherEducation MotherEducation Income
## 29 2 CMOI EMOI FatherEducation MotherEducation Income
## 29 3 CMOI EMOI FatherEducation MotherEducation Income
## 29 4 CMOI EMOI FatherEducation MotherEducation Income
## 29 5 CMOI EMOI FatherEducation MotherEducation Income
## 30 1 CMOI EMOI FatherEducation MotherEducation Income
## 30 2 CMOI EMOI FatherEducation MotherEducation Income
## 30 3 CMOI EMOI FatherEducation MotherEducation Income
## 30 4 CMOI EMOI FatherEducation MotherEducation Income
## 30 5 CMOI EMOI FatherEducation MotherEducation Income
## 31 1 CMOI EMOI FatherEducation MotherEducation Income
## 31 2 CMOI EMOI FatherEducation MotherEducation Income
## 31 3 CMOI EMOI FatherEducation MotherEducation Income
## 31 4 CMOI EMOI FatherEducation MotherEducation Income
## 31 5 CMOI EMOI FatherEducation MotherEducation Income
## 32 1 CMOI EMOI FatherEducation MotherEducation Income
## 32 2 CMOI EMOI FatherEducation MotherEducation Income
## 32 3 CMOI EMOI FatherEducation MotherEducation Income
## 32 4 CMOI EMOI FatherEducation MotherEducation Income
## 32 5 CMOI EMOI FatherEducation MotherEducation Income
## 33 1 CMOI EMOI FatherEducation MotherEducation Income
## 33 2 CMOI EMOI FatherEducation MotherEducation Income
## 33 3 CMOI EMOI FatherEducation MotherEducation Income
## 33 4 CMOI EMOI FatherEducation MotherEducation Income
## 33 5 CMOI EMOI FatherEducation MotherEducation Income
## 34 1 CMOI EMOI FatherEducation MotherEducation Income
## 34 2 CMOI EMOI FatherEducation MotherEducation Income
## 34 3 CMOI EMOI FatherEducation MotherEducation Income
## 34 4 CMOI EMOI FatherEducation MotherEducation Income
## 34 5 CMOI EMOI FatherEducation MotherEducation Income
## 35 1 CMOI EMOI FatherEducation MotherEducation Income
## 35 2 CMOI EMOI FatherEducation MotherEducation Income
## 35 3 CMOI EMOI FatherEducation MotherEducation Income
## 35 4 CMOI EMOI FatherEducation MotherEducation Income
## 35 5 CMOI EMOI FatherEducation MotherEducation Income
## 36 1 CMOI EMOI FatherEducation MotherEducation Income
## 36 2 CMOI EMOI FatherEducation MotherEducation Income
## 36 3 CMOI EMOI FatherEducation MotherEducation Income
## 36 4 CMOI EMOI FatherEducation MotherEducation Income
## 36 5 CMOI EMOI FatherEducation MotherEducation Income
## 37 1 CMOI EMOI FatherEducation MotherEducation Income
## 37 2 CMOI EMOI FatherEducation MotherEducation Income
## 37 3 CMOI EMOI FatherEducation MotherEducation Income
## 37 4 CMOI EMOI FatherEducation MotherEducation Income
## 37 5 CMOI EMOI FatherEducation MotherEducation Income
## 38 1 CMOI EMOI FatherEducation MotherEducation Income
## 38 2 CMOI EMOI FatherEducation MotherEducation Income
## 38 3 CMOI EMOI FatherEducation MotherEducation Income
## 38 4 CMOI EMOI FatherEducation MotherEducation Income
## 38 5 CMOI EMOI FatherEducation MotherEducation Income
## 39 1 CMOI EMOI FatherEducation MotherEducation Income
## 39 2 CMOI EMOI FatherEducation MotherEducation Income
## 39 3 CMOI EMOI FatherEducation MotherEducation Income
## 39 4 CMOI EMOI FatherEducation MotherEducation Income
## 39 5 CMOI EMOI FatherEducation MotherEducation Income
## 40 1 CMOI EMOI FatherEducation MotherEducation Income
## 40 2 CMOI EMOI FatherEducation MotherEducation Income
## 40 3 CMOI EMOI FatherEducation MotherEducation Income
## 40 4 CMOI EMOI FatherEducation MotherEducation Income
## 40 5 CMOI EMOI FatherEducation MotherEducation Income
## 41 1 CMOI EMOI FatherEducation MotherEducation Income
## 41 2 CMOI EMOI FatherEducation MotherEducation Income
## 41 3 CMOI EMOI FatherEducation MotherEducation Income
## 41 4 CMOI EMOI FatherEducation MotherEducation Income
## 41 5 CMOI EMOI FatherEducation MotherEducation Income
## 42 1 CMOI EMOI FatherEducation MotherEducation Income
## 42 2 CMOI EMOI FatherEducation MotherEducation Income
## 42 3 CMOI EMOI FatherEducation MotherEducation Income
## 42 4 CMOI EMOI FatherEducation MotherEducation Income
## 42 5 CMOI EMOI FatherEducation MotherEducation Income
## 43 1 CMOI EMOI FatherEducation MotherEducation Income
## 43 2 CMOI EMOI FatherEducation MotherEducation Income
## 43 3 CMOI EMOI FatherEducation MotherEducation Income
## 43 4 CMOI EMOI FatherEducation MotherEducation Income
## 43 5 CMOI EMOI FatherEducation MotherEducation Income
## 44 1 CMOI EMOI FatherEducation MotherEducation Income
## 44 2 CMOI EMOI FatherEducation MotherEducation Income
## 44 3 CMOI EMOI FatherEducation MotherEducation Income
## 44 4 CMOI EMOI FatherEducation MotherEducation Income
## 44 5 CMOI EMOI FatherEducation MotherEducation Income
## 45 1 CMOI EMOI FatherEducation MotherEducation Income
## 45 2 CMOI EMOI FatherEducation MotherEducation Income
## 45 3 CMOI EMOI FatherEducation MotherEducation Income
## 45 4 CMOI EMOI FatherEducation MotherEducation Income
## 45 5 CMOI EMOI FatherEducation MotherEducation Income
## 46 1 CMOI EMOI FatherEducation MotherEducation Income
## 46 2 CMOI EMOI FatherEducation MotherEducation Income
## 46 3 CMOI EMOI FatherEducation MotherEducation Income
## 46 4 CMOI EMOI FatherEducation MotherEducation Income
## 46 5 CMOI EMOI FatherEducation MotherEducation Income
## 47 1 CMOI EMOI FatherEducation MotherEducation Income
## 47 2 CMOI EMOI FatherEducation MotherEducation Income
## 47 3 CMOI EMOI FatherEducation MotherEducation Income
## 47 4 CMOI EMOI FatherEducation MotherEducation Income
## 47 5 CMOI EMOI FatherEducation MotherEducation Income
## 48 1 CMOI EMOI FatherEducation MotherEducation Income
## 48 2 CMOI EMOI FatherEducation MotherEducation Income
## 48 3 CMOI EMOI FatherEducation MotherEducation Income
## 48 4 CMOI EMOI FatherEducation MotherEducation Income
## 48 5 CMOI EMOI FatherEducation MotherEducation Income
## 49 1 CMOI EMOI FatherEducation MotherEducation Income
## 49 2 CMOI EMOI FatherEducation MotherEducation Income
## 49 3 CMOI EMOI FatherEducation MotherEducation Income
## 49 4 CMOI EMOI FatherEducation MotherEducation Income
## 49 5 CMOI EMOI FatherEducation MotherEducation Income
## 50 1 CMOI EMOI FatherEducation MotherEducation Income
## 50 2 CMOI EMOI FatherEducation MotherEducation Income
## 50 3 CMOI EMOI FatherEducation MotherEducation Income
## 50 4 CMOI EMOI FatherEducation MotherEducation Income
## 50 5 CMOI EMOI FatherEducation MotherEducation Incomecompleted_data <- complete(imputed_data, 1)
# Replace the original columns with the imputed data
data_selected$CMOI <- completed_data$CMOI
data_selected$EMOI <- completed_data$EMOI
data_selected$FatherEducation <- completed_data$FatherEducation
data_selected$MotherEducation <- completed_data$MotherEducation
data_selected$Income <- completed_data$Income
# Select the relevant columns and drop rows with NA values
education_income_data <- data_selected %>%
select(EEGID, FatherEducation, MotherEducation, Income) %>%
drop_na()
# Perform PCA
pca_result <- prcomp(education_income_data %>% select(-EEGID), scale. = TRUE)
# Extract the first principal component and add SubjectID
pca_scores <- education_income_data %>%
select(EEGID) %>%
mutate(SES = -pca_result$x[, 1]) # add minus so that higher scores indicate higher SES
# Merge the PCA scores back into the original data
data_income <- data_selected %>%
left_join(pca_scores, by = "EEGID")
# output the data_income to csv
write.csv(data_income, file = "./data/EEG_RS_lanExp_income_imputated_all_v2.csv", row.names = FALSE)# library(lme4)
library(tidyverse)
library(lmerTest)
library(conflicted)
data_income <- read.csv("./data/EEG_RS_lanExp_income_imputated_all_v2.csv")
# Center the variables
data_income <- data_income %>%
mutate(
PW_c = scale(PW, center = TRUE, scale = FALSE),
CMOI_c = scale(CMOI, center = TRUE, scale = FALSE),
EMOI_c = scale(EMOI, center = TRUE, scale = FALSE),
Age_EEG_yr_c = scale(Age_EEG_yr, center = TRUE, scale = FALSE),
SES_c = scale(SES, center = TRUE, scale = FALSE),
ARITH_c = scale(ARITH, center = TRUE, scale = FALSE)
)
# keep only the columns data for the analysis
data_income <- data_income %>%
select(CWR, CDICT, ARITH, EWR, EDICT, PW_c, CMOI_c, EMOI_c, Age_EEG_yr_c, SES_c, ARITH_c, FID, EEGID, Age_EEG_yr) %>%
drop_na()
write.csv(data_income, file = "./data/model_data_180.csv", row.names = F)
demo_info <- read.csv("./data/assessment-resting-state-v8-200-drop-duplicated.csv")
# left join data_income with demo_info by selected column age gender
demo_data_summary <- data_income %>%
left_join(demo_info %>% select(EEGID, Gender), by = "EEGID", suffix = c("", "")) %>%
summarise(count = n(),
mean_age = mean(Age_EEG_yr, na.rm = TRUE),
gender_count = list(table(Gender))
)
knitr::kable(demo_data_summary)| count | mean_age | gender_count |
|---|---|---|
| 180 | 8.135648 | 73, 107 |
# Fit separate models for each response variable
model_CWR <- lmerTest::lmer(CWR ~ PW_c + Age_EEG_yr_c + SES_c + CMOI_c + ARITH_c + (1 | FID), data = data_income)
model_CDICT <- lmerTest::lmer(CDICT ~ PW_c + Age_EEG_yr_c + SES_c + CMOI_c + ARITH_c + (1 | FID), data = data_income)
model_EWR <- lmerTest::lmer(EWR ~ PW_c + Age_EEG_yr_c + SES_c + EMOI_c + ARITH_c + (1 | FID), data = data_income)
model_EDICT <- lmerTest::lmer(EDICT ~ PW_c + Age_EEG_yr_c + SES_c + EMOI_c + ARITH_c + (1 | FID), data = data_income)
# Print the model summaries
summary(model_CWR)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CWR ~ PW_c + Age_EEG_yr_c + SES_c + CMOI_c + ARITH_c + (1 | FID)
## Data: data_income
##
## REML criterion at convergence: 1589.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.37465 -0.49008 -0.04215 0.44863 2.12748
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 424.8 20.61
## Residual 199.6 14.13
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 75.3246 2.3252 92.5248 32.394 < 2e-16 ***
## PW_c 145.8202 64.3788 157.5965 2.265 0.02487 *
## Age_EEG_yr_c 12.2365 3.0922 140.5076 3.957 0.00012 ***
## SES_c 1.0522 1.5998 96.7442 0.658 0.51230
## CMOI_c 5.1292 3.0743 156.9521 1.668 0.09723 .
## ARITH_c 2.4775 0.4994 173.5785 4.961 1.66e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c A_EEG_ SES_c CMOI_c
## PW_c 0.015
## Ag_EEG_yr_c -0.014 0.127
## SES_c -0.021 -0.093 -0.190
## CMOI_c -0.040 -0.041 0.138 -0.049
## ARITH_c 0.000 -0.169 -0.638 0.221 0.030summary(model_CDICT)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CDICT ~ PW_c + Age_EEG_yr_c + SES_c + CMOI_c + ARITH_c + (1 |
## FID)
## Data: data_income
##
## REML criterion at convergence: 1155.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.01949 -0.59068 0.06333 0.59453 2.20665
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 27.46 5.240
## Residual 19.60 4.427
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 25.39702 0.62336 93.64021 40.742 < 2e-16 ***
## PW_c 32.70999 18.86733 168.57786 1.734 0.0848 .
## Age_EEG_yr_c 1.08602 0.85605 136.50649 1.269 0.2067
## SES_c -0.05553 0.43024 97.30063 -0.129 0.8976
## CMOI_c 0.43704 0.85857 145.17260 0.509 0.6115
## ARITH_c 0.70107 0.14323 171.66027 4.895 2.26e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c A_EEG_ SES_c CMOI_c
## PW_c 0.012
## Ag_EEG_yr_c -0.017 0.137
## SES_c -0.020 -0.102 -0.206
## CMOI_c -0.043 -0.020 0.151 -0.051
## ARITH_c -0.003 -0.175 -0.660 0.240 0.020summary(model_EWR)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EWR ~ PW_c + Age_EEG_yr_c + SES_c + EMOI_c + ARITH_c + (1 | FID)
## Data: data_income
##
## REML criterion at convergence: 1286.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.04257 -0.43286 -0.08804 0.43022 3.06768
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 68.09 8.252
## Residual 37.26 6.104
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 19.0472 0.9472 91.1184 20.108 < 2e-16 ***
## PW_c 59.4364 27.1520 161.9289 2.189 0.030026 *
## Age_EEG_yr_c 3.8218 1.2779 138.1279 2.991 0.003297 **
## SES_c -4.1051 0.6579 96.1083 -6.240 1.18e-08 ***
## EMOI_c 4.0537 1.2033 143.0241 3.369 0.000970 ***
## ARITH_c 0.7341 0.2091 173.9392 3.511 0.000569 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c A_EEG_ SES_c EMOI_c
## PW_c 0.014
## Ag_EEG_yr_c -0.015 0.131
## SES_c -0.017 -0.093 -0.208
## EMOI_c 0.039 0.030 -0.155 0.136
## ARITH_c -0.002 -0.172 -0.642 0.221 -0.044summary(model_EDICT)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EDICT ~ PW_c + Age_EEG_yr_c + SES_c + EMOI_c + ARITH_c + (1 |
## FID)
## Data: data_income
##
## REML criterion at convergence: 1037.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.1929 -0.4497 -0.1271 0.3985 2.2033
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 14.273 3.778
## Residual 9.738 3.121
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 7.5914 0.4464 94.9915 17.005 < 2e-16 ***
## PW_c 26.8802 13.3956 167.9086 2.007 0.04639 *
## Age_EEG_yr_c 1.8857 0.6124 138.1532 3.079 0.00250 **
## SES_c -1.6874 0.3107 99.5468 -5.432 3.96e-07 ***
## EMOI_c 1.8976 0.5772 138.8588 3.288 0.00128 **
## ARITH_c 0.3308 0.1020 172.2103 3.243 0.00142 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c A_EEG_ SES_c EMOI_c
## PW_c 0.012
## Ag_EEG_yr_c -0.016 0.136
## SES_c -0.016 -0.099 -0.217
## EMOI_c 0.039 0.018 -0.162 0.139
## ARITH_c -0.003 -0.174 -0.654 0.232 -0.038# Fit the models with centered variables
moderate_CWR_MOI <- lmerTest::lmer(CWR ~ PW_c * CMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
moderate_CDICT_MOI <- lmerTest::lmer(CDICT ~ PW_c * CMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
moderate_EWR_MOI <- lmerTest::lmer(EWR ~ PW_c * EMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
moderate_EDICT_MOI <- lmerTest::lmer(EDICT ~ PW_c * EMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
# Print the model summaries
summary(moderate_CWR_MOI)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CWR ~ PW_c * CMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## Data: data_income
##
## REML criterion at convergence: 1577.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.41796 -0.48799 -0.01672 0.46316 2.16707
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 421.0 20.52
## Residual 199.7 14.13
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 75.4081 2.3180 92.7194 32.532 < 2e-16 ***
## PW_c 149.0621 64.3486 156.6435 2.316 0.0218 *
## CMOI_c 5.2039 3.0672 155.4031 1.697 0.0918 .
## SES_c 0.9084 1.5984 96.9826 0.568 0.5711
## ARITH_c 2.3471 0.5094 172.5239 4.608 7.88e-06 ***
## Age_EEG_yr_c 12.7796 3.1143 140.7418 4.104 6.86e-05 ***
## PW_c:CMOI_c 112.1024 87.5803 130.2120 1.280 0.2028
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c CMOI_c SES_c ARITH_ A_EEG_
## PW_c 0.016
## CMOI_c -0.040 -0.040
## SES_c -0.023 -0.096 -0.050
## ARITH_c -0.006 -0.174 0.026 0.230
## Ag_EEG_yr_c -0.010 0.131 0.139 -0.198 -0.647
## PW_c:CMOI_c 0.028 0.040 0.014 -0.071 -0.206 0.139summary(moderate_CDICT_MOI)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CDICT ~ PW_c * CMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 |
## FID)
## Data: data_income
##
## REML criterion at convergence: 1145.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.99093 -0.51839 0.06323 0.56310 2.24396
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 28.47 5.335
## Residual 19.06 4.366
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 25.37098 0.62917 92.89698 40.324 < 2e-16 ***
## PW_c 31.34968 18.81683 166.06885 1.666 0.0976 .
## CMOI_c 0.46624 0.86173 147.44708 0.541 0.5893
## SES_c -0.02012 0.43501 96.66255 -0.046 0.9632
## ARITH_c 0.73321 0.14637 171.74968 5.009 1.35e-06 ***
## Age_EEG_yr_c 0.95176 0.86854 137.00244 1.096 0.2751
## PW_c:CMOI_c -32.34363 26.04269 139.57623 -1.242 0.2163
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c CMOI_c SES_c ARITH_ A_EEG_
## PW_c 0.014
## CMOI_c -0.043 -0.024
## SES_c -0.022 -0.103 -0.049
## ARITH_c -0.009 -0.179 0.025 0.246
## Ag_EEG_yr_c -0.012 0.140 0.145 -0.211 -0.666
## PW_c:CMOI_c 0.030 0.041 -0.023 -0.072 -0.207 0.142summary(moderate_EWR_MOI)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EWR ~ PW_c * EMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## Data: data_income
##
## REML criterion at convergence: 1277.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.04347 -0.42291 -0.09249 0.44761 3.06411
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 68.34 8.267
## Residual 37.50 6.124
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 19.0563 0.9498 91.0243 20.064 < 2e-16 ***
## PW_c 59.5830 27.2316 160.8970 2.188 0.030111 *
## EMOI_c 4.0549 1.2062 142.8776 3.362 0.000994 ***
## SES_c -4.1195 0.6612 95.8856 -6.231 1.24e-08 ***
## ARITH_c 0.7238 0.2129 172.9974 3.400 0.000838 ***
## Age_EEG_yr_c 3.8689 1.2915 138.6082 2.996 0.003246 **
## PW_c:EMOI_c -10.3001 34.7692 127.4813 -0.296 0.767526
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c EMOI_c SES_c ARITH_ A_EEG_
## PW_c 0.014
## EMOI_c 0.039 0.030
## SES_c -0.019 -0.094 0.135
## ARITH_c -0.008 -0.172 -0.045 0.230
## Ag_EEG_yr_c -0.011 0.132 -0.153 -0.215 -0.649
## PW_c:EMOI_c -0.033 -0.018 -0.008 0.075 0.174 -0.128summary(moderate_EDICT_MOI)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EDICT ~ PW_c * EMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 |
## FID)
## Data: data_income
##
## REML criterion at convergence: 1029.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.1827 -0.4509 -0.1276 0.4052 2.1953
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 14.283 3.779
## Residual 9.825 3.134
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 7.5898 0.4474 94.9860 16.965 < 2e-16 ***
## PW_c 26.8965 13.4392 167.0170 2.001 0.04697 *
## EMOI_c 1.8948 0.5786 139.4389 3.275 0.00133 **
## SES_c -1.6850 0.3120 99.3648 -5.400 4.55e-07 ***
## ARITH_c 0.3332 0.1039 171.6256 3.207 0.00160 **
## Age_EEG_yr_c 1.8757 0.6189 138.6194 3.030 0.00291 **
## PW_c:EMOI_c 1.6212 17.3837 137.1756 0.093 0.92583
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c EMOI_c SES_c ARITH_ A_EEG_
## PW_c 0.012
## EMOI_c 0.040 0.018
## SES_c -0.019 -0.100 0.136
## ARITH_c -0.009 -0.174 -0.041 0.241
## Ag_EEG_yr_c -0.012 0.137 -0.157 -0.224 -0.661
## PW_c:EMOI_c -0.034 -0.015 -0.025 0.075 0.177 -0.130For the CMOI and EMOI moderation effect, the results are as follows: For CWR, the moderation effect of CMOI is significant (p = .049) and PW significantly correlates with CWR (p = .01). For CDICT, the moderation effect of CMOI is insignificant (p = .45) but PW significantly correlates with CDICT (p = .01). For EWR, the moderation effect of EMOI is insignificant (p = .39) but PW significantly correlates with EWR (p = .038). For EDICT, the moderation effect of EMOI is also insignificant (p = .85) and PW insignificantly correlates with EDICT (p = .09).
# Fit the model with PW as predictor, SES as moderator, and Age_EEG_yr as covariate
moderate_CWR_EIF <- lmerTest::lmer(CWR ~ PW_c * SES_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
moderate_CDICT_EIF <- lmerTest::lmer(CDICT ~ PW_c * SES_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
# moderate_ARITH_EIF <- lmerTest::lmer(ARITH ~ PW_c * SES_c + Age_EEG_yr_c + (1 | FID), data = data_income)
moderate_EWR_EIF <- lmerTest::lmer(EWR ~ PW_c * SES_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
moderate_EDICT_EIF <- lmerTest::lmer(EDICT ~ PW_c * SES_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
# Print the model summary
summary(moderate_CWR_EIF)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CWR ~ PW_c * SES_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## Data: data_income
##
## REML criterion at convergence: 1579.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.35358 -0.48973 -0.03684 0.45417 2.12615
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 431.1 20.76
## Residual 199.2 14.11
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 75.2745 2.3421 90.3429 32.139 < 2e-16 ***
## PW_c 142.5211 65.2020 160.5455 2.186 0.030276 *
## SES_c 0.9730 1.6240 96.9061 0.599 0.550477
## CMOI_c 5.0972 3.0854 156.0051 1.652 0.100538
## ARITH_c 2.4765 0.5008 172.3200 4.945 1.8e-06 ***
## Age_EEG_yr_c 12.2707 3.1051 138.7439 3.952 0.000123 ***
## PW_c:SES_c 15.3266 44.5201 146.4451 0.344 0.731144
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c SES_c CMOI_c ARITH_ A_EEG_
## PW_c 0.023
## SES_c -0.012 -0.070
## CMOI_c -0.040 -0.043 -0.050
## ARITH_c -0.002 -0.172 0.213 0.030
## Ag_EEG_yr_c -0.014 0.124 -0.189 0.138 -0.636
## PW_c:SES_c -0.058 -0.149 -0.138 0.005 0.032 0.011summary(moderate_CDICT_EIF)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CDICT ~ PW_c * SES_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 |
## FID)
## Data: data_income
##
## REML criterion at convergence: 1148
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.97368 -0.58949 0.04713 0.58529 2.13975
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 27.54 5.248
## Residual 19.60 4.427
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 25.3618 0.6252 93.1220 40.565 < 2e-16 ***
## PW_c 30.6808 19.0079 169.9476 1.614 0.108
## SES_c -0.1158 0.4358 99.5354 -0.266 0.791
## CMOI_c 0.4392 0.8592 144.3530 0.511 0.610
## ARITH_c 0.7057 0.1434 170.8559 4.921 2.02e-06 ***
## Age_EEG_yr_c 1.0938 0.8568 135.6227 1.277 0.204
## PW_c:SES_c 11.8036 13.1207 161.3320 0.900 0.370
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c SES_c CMOI_c ARITH_ A_EEG_
## PW_c 0.019
## SES_c -0.010 -0.082
## CMOI_c -0.043 -0.021 -0.051
## ARITH_c -0.005 -0.178 0.231 0.020
## Ag_EEG_yr_c -0.017 0.135 -0.204 0.151 -0.659
## PW_c:SES_c -0.062 -0.118 -0.153 0.002 0.038 0.009# summary(moderate_ARITH_EIF)
summary(moderate_EWR_EIF)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EWR ~ PW_c * SES_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## Data: data_income
##
## REML criterion at convergence: 1278.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.02838 -0.42962 -0.08467 0.43147 3.05137
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 68.90 8.300
## Residual 37.29 6.107
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 19.0334 0.9533 89.2165 19.966 < 2e-16 ***
## PW_c 58.4663 27.4715 164.5728 2.128 0.03481 *
## SES_c -4.1307 0.6678 96.6422 -6.185 1.49e-08 ***
## EMOI_c 4.0560 1.2077 141.6001 3.358 0.00101 **
## ARITH_c 0.7335 0.2098 172.9834 3.496 0.00060 ***
## Age_EEG_yr_c 3.8328 1.2827 136.4223 2.988 0.00333 **
## PW_c:SES_c 4.8386 18.8389 151.8050 0.257 0.79765
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c SES_c EMOI_c ARITH_ A_EEG_
## PW_c 0.022
## SES_c -0.008 -0.071
## EMOI_c 0.039 0.033 0.136
## ARITH_c -0.004 -0.175 0.213 -0.045
## Ag_EEG_yr_c -0.016 0.128 -0.207 -0.155 -0.640
## PW_c:SES_c -0.060 -0.138 -0.144 -0.014 0.035 0.012summary(moderate_EDICT_EIF)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EDICT ~ PW_c * SES_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 |
## FID)
## Data: data_income
##
## REML criterion at convergence: 1030.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.1753 -0.4382 -0.1199 0.4112 2.2306
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 14.150 3.762
## Residual 9.871 3.142
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 7.6023 0.4468 94.2080 17.015 < 2e-16 ***
## PW_c 27.6209 13.5346 169.7847 2.041 0.04282 *
## SES_c -1.6676 0.3141 101.3757 -5.310 6.5e-07 ***
## EMOI_c 1.8966 0.5775 137.1496 3.284 0.00130 **
## ARITH_c 0.3312 0.1023 171.0476 3.239 0.00144 **
## Age_EEG_yr_c 1.8763 0.6127 136.7996 3.062 0.00264 **
## PW_c:SES_c -3.7340 9.3396 161.1939 -0.400 0.68983
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c SES_c EMOI_c ARITH_ A_EEG_
## PW_c 0.019
## SES_c -0.006 -0.079
## EMOI_c 0.040 0.018 0.139
## ARITH_c -0.006 -0.178 0.224 -0.037
## Ag_EEG_yr_c -0.017 0.135 -0.217 -0.163 -0.654
## PW_c:SES_c -0.063 -0.119 -0.153 -0.012 0.038 0.011For the CMOI and EMOI moderation effect, the results are as follows: For CWR, the moderation effect of CMOI is significant (p = .049) and PW significantly correlates with CWR (p = .01). For CDICT, the moderation effect of CMOI is insignificant (p = .45) but PW significantly correlates with CDICT (p = .01). For EWR, the moderation effect of EMOI is insignificant (p = .39) but PW significantly correlates with EWR (p = .038). For EDICT, the moderation effect of EMOI is also insignificant (p = .85) and PW insignificantly correlates with EDICT (p = .09).
And for CWR and CDICT, alpha power significantly correlate with then (p = .01 and p = .02, respectively). However, the moderation effect of Education Income Factor (EIF) is not significant for CWR and CDICT (both p > .05). Alpha power did not significantly correlate with ARITH (p = .06) and the moderation effect of EIF is also insignificant (p = .65). Alpha power significantly correlate with then (p = .04 and p = .029, respectively). The moderation effect of EIF is insignificant for EWR and EDICT (both p > .05).
# Fit the models with centered variables
model_CWR_MOI <- lmerTest::lmer(CWR ~ PW_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
model_CDICT_MOI <- lmerTest::lmer(CDICT ~ PW_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
# moderate_ARITH_MOI <- lmerTest::lmer(ARITH ~ PW_c + CMOI_c + Age_EEG_yr_c + (1 | FID), data = data_income)
model_EWR_MOI <- lmerTest::lmer(EWR ~ PW_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
model_EDICT_MOI <- lmerTest::lmer(EDICT ~ PW_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID), data = data_income)
#summary
summary(model_CWR_MOI)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CWR ~ PW_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## Data: data_income
##
## REML criterion at convergence: 1592.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.4062 -0.4918 -0.0408 0.4519 2.1368
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 422.6 20.56
## Residual 199.3 14.12
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 75.3570 2.3195 93.6263 32.489 < 2e-16 ***
## PW_c 149.7652 64.0086 159.2098 2.340 0.0205 *
## CMOI_c 5.2373 3.0649 158.1111 1.709 0.0894 .
## ARITH_c 2.4063 0.4863 174.9892 4.949 1.75e-06 ***
## Age_EEG_yr_c 12.6178 3.0301 137.0659 4.164 5.50e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c CMOI_c ARITH_
## PW_c 0.013
## CMOI_c -0.041 -0.046
## ARITH_c 0.004 -0.153 0.042
## Ag_EEG_yr_c -0.018 0.112 0.132 -0.622summary(model_CDICT_MOI)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CDICT ~ PW_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## Data: data_income
##
## REML criterion at convergence: 1155.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.01658 -0.59043 0.05636 0.60295 2.20857
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 27.04 5.200
## Residual 19.61 4.429
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 25.3961 0.6199 94.6403 40.969 < 2e-16 ***
## PW_c 32.5640 18.7253 170.1683 1.739 0.0838 .
## CMOI_c 0.4304 0.8540 146.0560 0.504 0.6151
## ARITH_c 0.7068 0.1386 169.4170 5.100 9.02e-07 ***
## Age_EEG_yr_c 1.0590 0.8341 132.6667 1.270 0.2064
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c CMOI_c ARITH_
## PW_c 0.010
## CMOI_c -0.044 -0.025
## ARITH_c 0.002 -0.156 0.032
## Ag_EEG_yr_c -0.021 0.120 0.145 -0.644summary(model_EWR_MOI)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EWR ~ PW_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## Data: data_income
##
## REML criterion at convergence: 1320.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.8439 -0.3833 -0.1098 0.3792 3.1284
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 102.8 10.140
## Residual 37.6 6.132
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 18.9695 1.1158 90.0722 17.000 < 2e-16 ***
## PW_c 46.6254 28.9245 149.0982 1.612 0.109084
## EMOI_c 5.2681 1.3486 156.0441 3.906 0.000139 ***
## ARITH_c 0.8817 0.2235 173.0758 3.944 0.000116 ***
## Age_EEG_yr_c 2.6127 1.4278 136.7909 1.830 0.069444 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c EMOI_c ARITH_
## PW_c 0.014
## EMOI_c 0.040 0.068
## ARITH_c 0.004 -0.154 -0.085
## Ag_EEG_yr_c -0.016 0.106 -0.120 -0.601summary(model_EDICT_MOI)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EDICT ~ PW_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## Data: data_income
##
## REML criterion at convergence: 1063.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.1006 -0.4502 -0.1160 0.3749 2.2228
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 19.817 4.452
## Residual 9.899 3.146
## Number of obs: 180, groups: FID, 101
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 7.5532 0.5055 93.5471 14.942 < 2e-16 ***
## PW_c 19.2719 14.1400 161.3052 1.363 0.174803
## EMOI_c 2.3700 0.6311 147.0155 3.755 0.000249 ***
## ARITH_c 0.4160 0.1073 174.7598 3.878 0.000149 ***
## Age_EEG_yr_c 1.3217 0.6628 135.7659 1.994 0.048162 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c EMOI_c ARITH_
## PW_c 0.013
## EMOI_c 0.041 0.049
## ARITH_c 0.002 -0.155 -0.079
## Ag_EEG_yr_c -0.018 0.113 -0.129 -0.620# Perform the likelihood ratio test
comparison_CWR <- anova(model_CWR_MOI, moderate_CWR_MOI)## refitting model(s) with ML (instead of REML)# Print the comparison results
print(comparison_CWR)## Data: data_income
## Models:
## model_CWR_MOI: CWR ~ PW_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## moderate_CWR_MOI: CWR ~ PW_c * CMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## npar AIC BIC logLik deviance Chisq Df Pr(>Chisq)
## model_CWR_MOI 7 1628.2 1650.6 -807.12 1614.2
## moderate_CWR_MOI 9 1630.1 1658.8 -806.05 1612.1 2.1533 2 0.3407# Perform the likelihood ratio test
comparison_CWR_EIF <- anova(model_CWR, moderate_CWR_EIF)## refitting model(s) with ML (instead of REML)# Print the comparison results
print(comparison_CWR_EIF)## Data: data_income
## Models:
## model_CWR: CWR ~ PW_c + Age_EEG_yr_c + SES_c + CMOI_c + ARITH_c + (1 | FID)
## moderate_CWR_EIF: CWR ~ PW_c * SES_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## npar AIC BIC logLik deviance Chisq Df Pr(>Chisq)
## model_CWR 8 1629.8 1655.3 -806.89 1613.8
## moderate_CWR_EIF 9 1631.7 1660.4 -806.85 1613.7 0.0968 1 0.7557# Perform the likelihood ratio test
comparison_CDICT <- anova(model_CDICT_MOI, moderate_CDICT_MOI)## refitting model(s) with ML (instead of REML)# Print the comparison results
print(comparison_CDICT)## Data: data_income
## Models:
## model_CDICT_MOI: CDICT ~ PW_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## moderate_CDICT_MOI: CDICT ~ PW_c * CMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## npar AIC BIC logLik deviance Chisq Df Pr(>Chisq)
## model_CDICT_MOI 7 1178.7 1201.1 -582.35 1164.7
## moderate_CDICT_MOI 9 1181.2 1210.0 -581.61 1163.2 1.4909 2 0.4745# Perform the likelihood ratio test
comparison_CDICT_EIF <- anova(model_CDICT, moderate_CDICT_EIF)## refitting model(s) with ML (instead of REML)# Print the comparison results
print(comparison_CDICT_EIF)## Data: data_income
## Models:
## model_CDICT: CDICT ~ PW_c + Age_EEG_yr_c + SES_c + CMOI_c + ARITH_c + (1 | FID)
## moderate_CDICT_EIF: CDICT ~ PW_c * SES_c + CMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## npar AIC BIC logLik deviance Chisq Df Pr(>Chisq)
## model_CDICT 8 1180.7 1206.2 -582.35 1164.7
## moderate_CDICT_EIF 9 1181.9 1210.6 -581.93 1163.9 0.8324 1 0.3616# Perform the likelihood ratio test
comparison_EWR <- anova(model_EWR_MOI, moderate_EWR_MOI)## refitting model(s) with ML (instead of REML)# Print the comparison results
print(comparison_EWR)## Data: data_income
## Models:
## model_EWR_MOI: EWR ~ PW_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## moderate_EWR_MOI: EWR ~ PW_c * EMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## npar AIC BIC logLik deviance Chisq Df Pr(>Chisq)
## model_EWR_MOI 7 1348.6 1371.0 -667.30 1334.6
## moderate_EWR_MOI 9 1317.8 1346.5 -649.89 1299.8 34.832 2 2.731e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# Perform the likelihood ratio test
comparison_EWR_EIF <- anova(model_EWR, moderate_EWR_EIF)## refitting model(s) with ML (instead of REML)# Print the comparison results
print(comparison_EWR_EIF)## Data: data_income
## Models:
## model_EWR: EWR ~ PW_c + Age_EEG_yr_c + SES_c + EMOI_c + ARITH_c + (1 | FID)
## moderate_EWR_EIF: EWR ~ PW_c * SES_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## npar AIC BIC logLik deviance Chisq Df Pr(>Chisq)
## model_EWR 8 1315.9 1341.4 -649.93 1299.9
## moderate_EWR_EIF 9 1317.8 1346.5 -649.91 1299.8 0.05 1 0.823# Perform the likelihood ratio test
comparison_EDICT <- anova(model_EDICT_MOI, moderate_EDICT_MOI)## refitting model(s) with ML (instead of REML)# Print the comparison results
print(comparison_EDICT)## Data: data_income
## Models:
## model_EDICT_MOI: EDICT ~ PW_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## moderate_EDICT_MOI: EDICT ~ PW_c * EMOI_c + SES_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## npar AIC BIC logLik deviance Chisq Df Pr(>Chisq)
## model_EDICT_MOI 7 1083.3 1105.7 -534.67 1069.3
## moderate_EDICT_MOI 9 1060.0 1088.7 -520.99 1042.0 27.342 2 1.156e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# Perform the likelihood ratio test
comparison_EDICT_EIF <- anova(model_EDICT, moderate_EDICT_EIF)## refitting model(s) with ML (instead of REML)# Print the comparison results
print(comparison_EDICT_EIF)## Data: data_income
## Models:
## model_EDICT: EDICT ~ PW_c + Age_EEG_yr_c + SES_c + EMOI_c + ARITH_c + (1 | FID)
## moderate_EDICT_EIF: EDICT ~ PW_c * SES_c + EMOI_c + ARITH_c + Age_EEG_yr_c + (1 | FID)
## npar AIC BIC logLik deviance Chisq Df Pr(>Chisq)
## model_EDICT 8 1058.0 1083.5 -521.00 1042.0
## moderate_EDICT_EIF 9 1059.8 1088.5 -520.91 1041.8 0.1816 1 0.67data_child <- read.csv("./data/model_data_180.csv")
data_parent_raw <- read_excel("./data/CRF_ADATA_20230620.xlsx")## Warning: Expecting logical in BQM1490 / R1490C1807: got '曾有懶眼需遮蓋眼睛'## Warning: Expecting logical in BQM1491 / R1491C1807: got '曾有懶眼需遮蓋眼睛'## Warning: Expecting logical in BQM1492 / R1492C1807: got '曾有懶眼需遮蓋眼睛'## Warning: Expecting logical in BQM1493 / R1493C1807: got '曾有懶眼需遮蓋眼睛'## Warning: Expecting logical in BQM1498 / R1498C1807: got
## '兩眼有白內障已動手術換晶片'## Warning: Expecting logical in BQM1499 / R1499C1807: got
## '兩眼有白內障已動手術換晶片'## Warning: Expecting logical in BQM1500 / R1500C1807: got
## '兩眼有白內障已動手術換晶片'## Warning: Expecting logical in BQM1501 / R1501C1807: got
## '兩眼有白內障已動手術換晶片'## Warning: Expecting logical in BQM1733 / R1733C1807: got
## '右眼有外斜視問題但幸運地未影響他的立體感建立閱讀距離視力正常'## Warning: Expecting logical in BQM1734 / R1734C1807: got
## '右眼有外斜視問題但幸運地未影響他的立體感建立閱讀距離視力正常'## Warning: Expecting logical in BQM1735 / R1735C1807: got
## '右眼有外斜視問題但幸運地未影響他的立體感建立閱讀距離視力正常'# Filter rows where LP1-LP5 contain at least one '10'
data_parent <- data_parent_raw %>%
semi_join(data_child, by = c("EEGID", "FID"))
# dplyr::filter(if_any(LP1:LP5, ~ .x == 10))
# # View the filtered data
# View(data_dys)
data_parent_s <- data_parent %>%
dplyr::select(SubjectID, FID, EEGID,
MSWR, MCDICT, MARITH,
FSWR, FCDICT, FARITH, LearningProblem, LP1, LP2, LP3, LP4, LP5) %>%
dplyr::filter(!(rowSums(is.na(select(., MSWR, MCDICT, MARITH, FSWR, FCDICT, FARITH))) == 6)) %>%
dplyr::mutate(
PSWR = case_when(
is.na(MSWR) & is.na(FSWR) ~ NA_real_, # If both are NA, PSWR is NA
is.na(MSWR) ~ FSWR, # If MSWR is NA, PSWR is FSWR
is.na(FSWR) ~ MSWR, # If FSWR is NA, PSWR is MSWR
TRUE ~ (MSWR + FSWR) / 2 # If both have values, PSWR is the average
),
PCDICT = case_when(
is.na(MCDICT) & is.na(FCDICT) ~ NA_real_,
is.na(MCDICT) ~ FCDICT,
is.na(FCDICT) ~ MCDICT,
TRUE ~ (MCDICT + FCDICT) / 2
),
PARITH = case_when(
is.na(MARITH) & is.na(FARITH) ~ NA_real_,
is.na(MARITH) ~ FARITH,
is.na(FARITH) ~ MARITH,
TRUE ~ (MARITH + FARITH) / 2
)
) %>%
dplyr::mutate(
PSWR_z = scale(PSWR), # Calculate z-score for PSWR
PCDICT_z = scale(PCDICT), # Calculate z-score for PCDICT
PARITH_z = scale(PARITH) # Calculate z-score for PARITH
)
# Create a subset where at least one of the z-scores is lower than -1
risk_data <- data_parent_s %>%
dplyr::filter(
PSWR_z < -1 | PCDICT_z < -1 | PARITH_z < -1
) %>%
dplyr::select(SubjectID, FID, EEGID, PSWR_z, PCDICT_z, PARITH_z)## Warning: Using one column matrices in `filter()` was deprecated in dplyr 1.1.0.
## ℹ Please use one dimensional logical vectors instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.# Select risk child from child_data where EEGID and FID match with risk_data
risk_child <- data_child %>%
dplyr::inner_join(risk_data, by = c("EEGID", "FID"))
# Fit separate models for each response variable
model_CWR_risk <- lmerTest::lmer(CWR ~ PW_c + Age_EEG_yr_c + SES_c + CMOI_c + ARITH_c + (1 | FID), data = risk_child)
model_CDICT_risk <- lmerTest::lmer(CDICT ~ PW_c + Age_EEG_yr_c + SES_c + CMOI_c + ARITH_c + (1 | FID), data = risk_child)## boundary (singular) fit: see help('isSingular')model_EWR_risk <- lmerTest::lmer(EWR ~ PW_c + Age_EEG_yr_c + SES_c + EMOI_c + ARITH_c + (1 | FID), data = risk_child)## boundary (singular) fit: see help('isSingular')model_EDICT_risk <- lmerTest::lmer(EDICT ~ PW_c + Age_EEG_yr_c + SES_c + EMOI_c + ARITH_c + (1 | FID), data = risk_child)
# Print the model summaries
summary(model_CWR_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CWR ~ PW_c + Age_EEG_yr_c + SES_c + CMOI_c + ARITH_c + (1 | FID)
## Data: risk_child
##
## REML criterion at convergence: 34.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.9745 -0.1842 -0.0086 0.2552 0.9655
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 460.31 21.455
## Residual 38.85 6.233
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 47.267 20.077 3.292 2.354 0.0922 .
## PW_c -391.825 233.868 2.662 -1.675 0.2039
## Age_EEG_yr_c 46.590 19.036 3.727 2.447 0.0753 .
## SES_c 8.996 13.424 2.120 0.670 0.5683
## CMOI_c -2.572 10.223 1.909 -0.252 0.8258
## ARITH_c -2.583 2.473 2.820 -1.044 0.3774
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c A_EEG_ SES_c CMOI_c
## PW_c 0.487
## Ag_EEG_yr_c -0.650 -0.388
## SES_c -0.758 -0.266 0.318
## CMOI_c 0.035 0.242 0.275 -0.005
## ARITH_c 0.601 0.614 -0.688 -0.336 0.167summary(model_CDICT_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CDICT ~ PW_c + Age_EEG_yr_c + SES_c + CMOI_c + ARITH_c + (1 |
## FID)
## Data: risk_child
##
## REML criterion at convergence: 29.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.0927 -0.4329 -0.1442 0.6071 0.9402
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 0.00 0.000
## Residual 27.37 5.231
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 12.807 5.970 4.000 2.145 0.0985 .
## PW_c -36.294 127.625 4.000 -0.284 0.7902
## Age_EEG_yr_c 9.078 6.730 4.000 1.349 0.2486
## SES_c 5.337 2.819 4.000 1.894 0.1312
## CMOI_c -3.071 2.067 4.000 -1.486 0.2116
## ARITH_c -1.342 1.075 4.000 -1.249 0.2799
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c A_EEG_ SES_c CMOI_c
## PW_c 0.499
## Ag_EEG_yr_c -0.819 -0.128
## SES_c -0.769 -0.335 0.513
## CMOI_c 0.261 0.565 0.058 -0.201
## ARITH_c 0.811 0.198 -0.912 -0.584 0.166
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')summary(model_EWR_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EWR ~ PW_c + Age_EEG_yr_c + SES_c + EMOI_c + ARITH_c + (1 | FID)
## Data: risk_child
##
## REML criterion at convergence: 31.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.92879 -0.47819 -0.05944 0.31982 1.27497
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 0.00 0.000
## Residual 41.56 6.447
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.344 7.304 4.000 0.184 0.8630
## PW_c -152.901 156.459 4.000 -0.977 0.3838
## Age_EEG_yr_c 13.787 8.297 4.000 1.662 0.1719
## SES_c 7.639 3.475 4.000 2.198 0.0928 .
## EMOI_c 10.053 2.271 4.000 4.426 0.0115 *
## ARITH_c -1.736 1.322 4.000 -1.313 0.2593
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c A_EEG_ SES_c EMOI_c
## PW_c 0.487
## Ag_EEG_yr_c -0.825 -0.125
## SES_c -0.769 -0.336 0.511
## EMOI_c -0.233 -0.559 -0.065 0.202
## ARITH_c 0.810 0.191 -0.913 -0.582 -0.154
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')summary(model_EDICT_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EDICT ~ PW_c + Age_EEG_yr_c + SES_c + EMOI_c + ARITH_c + (1 |
## FID)
## Data: risk_child
##
## REML criterion at convergence: 21
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.87347 -0.26579 0.01841 0.23442 0.79370
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 10.129 3.183
## Residual 1.491 1.221
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.8167 3.3176 3.1694 0.849 0.455
## PW_c 56.5792 44.1714 2.8560 1.281 0.294
## Age_EEG_yr_c 4.6889 3.2316 3.7608 1.451 0.225
## SES_c 1.3402 2.0865 1.7679 0.642 0.594
## EMOI_c 4.1022 1.4018 1.5074 2.926 0.137
## ARITH_c -0.4921 0.4625 3.1653 -1.064 0.362
##
## Correlation of Fixed Effects:
## (Intr) PW_c A_EEG_ SES_c EMOI_c
## PW_c 0.534
## Ag_EEG_yr_c -0.713 -0.411
## SES_c -0.768 -0.316 0.374
## EMOI_c -0.062 -0.291 -0.194 0.050
## ARITH_c 0.673 0.589 -0.764 -0.404 -0.192# Fit the models with centered variables
moderate_CWR_MOI_risk <- lmerTest::lmer(CWR ~ PW_c * CMOI_c + Age_EEG_yr_c + ARITH_c + SES_c + (1 | FID), data = risk_child)## boundary (singular) fit: see help('isSingular')moderate_CDICT_MOI_risk <- lmerTest::lmer(CDICT ~ PW_c * CMOI_c + Age_EEG_yr_c + ARITH_c + SES_c + (1 | FID), data = risk_child)## boundary (singular) fit: see help('isSingular')moderate_EWR_MOI_risk <- lmerTest::lmer(EWR ~ PW_c * EMOI_c + Age_EEG_yr_c + ARITH_c + SES_c + (1 | FID), data = risk_child)## boundary (singular) fit: see help('isSingular')moderate_EDICT_MOI_risk <- lmerTest::lmer(EDICT ~ PW_c * EMOI_c + Age_EEG_yr_c + ARITH_c + SES_c + (1 | FID), data = risk_child)
# Print the model summaries
summary(moderate_CWR_MOI_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CWR ~ PW_c * CMOI_c + Age_EEG_yr_c + ARITH_c + SES_c + (1 | FID)
## Data: risk_child
##
## REML criterion at convergence: 21
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.18631 -0.21094 -0.00348 0.36388 0.91812
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 0.00 0.000
## Residual 94.13 9.702
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 39.7855 11.0875 3.0000 3.588 0.0371 *
## PW_c -1275.4716 323.5912 3.0000 -3.942 0.0291 *
## CMOI_c -9.8221 4.0440 3.0000 -2.429 0.0934 .
## Age_EEG_yr_c 26.9640 14.4136 3.0000 1.871 0.1581
## ARITH_c 0.2571 2.3185 3.0000 0.111 0.9187
## SES_c 11.2730 5.2293 3.0000 2.156 0.1201
## PW_c:CMOI_c -415.5473 180.7504 3.0000 -2.299 0.1051
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c CMOI_c A_EEG_ ARITH_ SES_c
## PW_c 0.400
## CMOI_c 0.263 0.609
## Ag_EEG_yr_c -0.683 0.260 0.207
## ARITH_c 0.670 -0.224 -0.027 -0.934
## SES_c -0.769 -0.261 -0.198 0.432 -0.490
## PW_c:CMOI_c 0.051 0.682 0.318 0.500 -0.510 -0.023
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')summary(moderate_CDICT_MOI_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CDICT ~ PW_c * CMOI_c + Age_EEG_yr_c + ARITH_c + SES_c + (1 |
## FID)
## Data: risk_child
##
## REML criterion at convergence: 17.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.15261 -0.19123 0.01820 0.05252 1.09631
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 0.00 0.000
## Residual 25.44 5.044
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 12.4718 5.7642 3.0000 2.164 0.119
## PW_c -167.1960 168.2304 3.0000 -0.994 0.394
## CMOI_c -3.8342 2.1024 3.0000 -1.824 0.166
## Age_EEG_yr_c 4.8014 7.4934 3.0000 0.641 0.567
## ARITH_c -0.6398 1.2054 3.0000 -0.531 0.632
## SES_c 5.4089 2.7186 3.0000 1.990 0.141
## PW_c:CMOI_c -107.2364 93.9695 3.0000 -1.141 0.337
##
## Correlation of Fixed Effects:
## (Intr) PW_c CMOI_c A_EEG_ ARITH_ SES_c
## PW_c 0.400
## CMOI_c 0.263 0.609
## Ag_EEG_yr_c -0.683 0.260 0.207
## ARITH_c 0.670 -0.224 -0.027 -0.934
## SES_c -0.769 -0.261 -0.198 0.432 -0.490
## PW_c:CMOI_c 0.051 0.682 0.318 0.500 -0.510 -0.023
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')summary(moderate_EWR_MOI_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EWR ~ PW_c * EMOI_c + Age_EEG_yr_c + ARITH_c + SES_c + (1 | FID)
## Data: risk_child
##
## REML criterion at convergence: 19.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.9290 -0.2733 0.0251 0.1667 1.2733
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 0.00 0.000
## Residual 48.29 6.949
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.121 7.881 3.000 0.142 0.8959
## PW_c -252.169 225.215 3.000 -1.120 0.3444
## EMOI_c 10.596 2.581 3.000 4.105 0.0262 *
## Age_EEG_yr_c 10.372 10.313 3.000 1.006 0.3886
## ARITH_c -1.176 1.656 3.000 -0.710 0.5288
## SES_c 7.695 3.747 3.000 2.054 0.1323
## PW_c:EMOI_c 77.398 116.372 3.000 0.665 0.5536
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c EMOI_c A_EEG_ ARITH_ SES_c
## PW_c 0.392
## EMOI_c -0.235 -0.607
## Ag_EEG_yr_c -0.693 0.249 -0.211
## ARITH_c 0.675 -0.214 0.036 -0.935
## SES_c -0.769 -0.267 0.199 0.432 -0.490
## PW_c:EMOI_c -0.043 -0.663 0.317 -0.498 0.509 0.022
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')summary(moderate_EDICT_MOI_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EDICT ~ PW_c * EMOI_c + Age_EEG_yr_c + ARITH_c + SES_c + (1 |
## FID)
## Data: risk_child
##
## REML criterion at convergence: 9.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.54230 -0.14263 0.00175 0.13111 0.53433
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 47.03380 6.8581
## Residual 0.05735 0.2395
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 6.51837 4.98280 2.01825 1.308 0.3199
## PW_c 245.01130 25.19749 1.00355 9.724 0.0648 .
## EMOI_c 2.59440 2.79204 1.97657 0.929 0.4519
## Age_EEG_yr_c 5.66073 4.30728 2.04123 1.314 0.3170
## ARITH_c -0.51161 0.10823 0.98657 -4.727 0.1352
## SES_c -0.03226 3.94460 1.96991 -0.008 0.9942
## PW_c:EMOI_c -67.28330 9.67150 1.00129 -6.957 0.0907 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c EMOI_c A_EEG_ ARITH_ SES_c
## PW_c 0.095
## EMOI_c 0.141 -0.071
## Ag_EEG_yr_c -0.439 0.036 -0.533
## ARITH_c 0.072 -0.072 -0.001 -0.142
## SES_c -0.744 -0.044 -0.057 0.137 -0.035
## PW_c:EMOI_c -0.069 -0.926 0.064 -0.070 0.328 0.032# Fit the model with PW as predictor, SES as moderator, and Age_EEG_yr as covariate
moderate_CWR_EIF_risk <- lmerTest::lmer(CWR ~ PW_c * SES_c + CMOI_c + SES_c + Age_EEG_yr_c + (1 | FID), data = risk_child)
moderate_CDICT_EIF_risk <- lmerTest::lmer(CDICT ~ PW_c * SES_c + CMOI_c + SES_c + Age_EEG_yr_c + (1 | FID), data = risk_child)## boundary (singular) fit: see help('isSingular')moderate_EWR_EIF_risk <- lmerTest::lmer(EWR ~ PW_c * SES_c + EMOI_c + SES_c + Age_EEG_yr_c + (1 | FID), data = risk_child)## boundary (singular) fit: see help('isSingular')moderate_EDICT_EIF_risk <- lmerTest::lmer(EDICT ~ PW_c * SES_c + EMOI_c + SES_c + Age_EEG_yr_c + (1 | FID), data = risk_child)
# Print the model summary
summary(moderate_CWR_EIF_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CWR ~ PW_c * SES_c + CMOI_c + SES_c + Age_EEG_yr_c + (1 | FID)
## Data: risk_child
##
## REML criterion at convergence: 23.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.81420 -0.09451 -0.01441 0.11805 0.85910
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 1186.83 34.45
## Residual 21.71 4.66
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 46.7894 26.7469 2.1201 1.749 0.215
## PW_c -750.2901 408.9639 2.0273 -1.835 0.206
## SES_c 17.3845 21.9782 2.3240 0.791 0.502
## CMOI_c -0.0619 15.7194 1.5964 -0.004 0.997
## Age_EEG_yr_c 35.9734 21.7300 1.6105 1.655 0.268
## PW_c:SES_c 795.0427 554.7877 2.1593 1.433 0.280
##
## Correlation of Fixed Effects:
## (Intr) PW_c SES_c CMOI_c A_EEG_
## PW_c 0.367
## SES_c -0.782 -0.411
## CMOI_c -0.107 0.019 0.067
## Ag_EEG_yr_c -0.422 -0.073 0.162 0.543
## PW_c:SES_c -0.360 -0.939 0.424 0.011 0.089summary(moderate_CDICT_EIF_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: CDICT ~ PW_c * SES_c + CMOI_c + SES_c + Age_EEG_yr_c + (1 | FID)
## Data: risk_child
##
## REML criterion at convergence: 12.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.7944 -0.5729 0.0236 0.2196 1.3729
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 0.000 0.000
## Residual 6.196 2.489
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 32.4064 3.4221 4.0000 9.470 0.000694 ***
## PW_c 604.1896 146.9194 4.0000 4.112 0.014703 *
## SES_c -8.3099 2.7795 4.0000 -2.990 0.040349 *
## CMOI_c -0.8215 1.0498 4.0000 -0.783 0.477642
## Age_EEG_yr_c 0.6910 1.3240 4.0000 0.522 0.629300
## PW_c:SES_c -619.4038 136.6301 4.0000 -4.533 0.010550 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c SES_c CMOI_c A_EEG_
## PW_c 0.915
## SES_c -0.923 -0.885
## CMOI_c 0.433 0.556 -0.399
## Ag_EEG_yr_c -0.266 -0.058 0.088 0.429
## PW_c:SES_c -0.874 -0.914 0.920 -0.383 0.121
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')summary(moderate_EWR_EIF_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EWR ~ PW_c * SES_c + EMOI_c + SES_c + Age_EEG_yr_c + (1 | FID)
## Data: risk_child
##
## REML criterion at convergence: 19.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.78742 -0.32892 -0.14194 0.06274 1.69441
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 0.0 0.000
## Residual 34.4 5.865
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 21.122 8.036 4.000 2.628 0.0583 .
## PW_c 429.543 347.434 4.000 1.236 0.2840
## SES_c -5.377 6.587 4.000 -0.816 0.4602
## EMOI_c 8.111 2.219 4.000 3.656 0.0217 *
## Age_EEG_yr_c 3.192 3.102 4.000 1.029 0.3616
## PW_c:SES_c -552.010 323.232 4.000 -1.708 0.1629
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c SES_c EMOI_c A_EEG_
## PW_c 0.913
## SES_c -0.923 -0.887
## EMOI_c -0.426 -0.560 0.411
## Ag_EEG_yr_c -0.278 -0.063 0.088 -0.418
## PW_c:SES_c -0.875 -0.916 0.921 0.391 0.122
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')summary(moderate_EDICT_EIF_risk)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: EDICT ~ PW_c * SES_c + EMOI_c + SES_c + Age_EEG_yr_c + (1 | FID)
## Data: risk_child
##
## REML criterion at convergence: 8.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.96146 -0.38801 -0.06736 0.31322 1.11140
##
## Random effects:
## Groups Name Variance Std.Dev.
## FID (Intercept) 2.467 1.571
## Residual 1.847 1.359
## Number of obs: 10, groups: FID, 6
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 9.2222 2.4197 2.8484 3.811 0.0348 *
## PW_c 244.9616 89.7875 3.7791 2.728 0.0559 .
## SES_c -3.4107 2.0525 2.5187 -1.662 0.2122
## EMOI_c 3.8421 0.8218 1.0827 4.675 0.1199
## Age_EEG_yr_c 1.2703 1.2398 0.9165 1.025 0.5043
## PW_c:SES_c -229.4077 98.2913 3.1630 -2.334 0.0973 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PW_c SES_c EMOI_c A_EEG_
## PW_c 0.823
## SES_c -0.899 -0.814
## EMOI_c -0.123 -0.286 0.136
## Ag_EEG_yr_c -0.377 -0.126 0.190 -0.494
## PW_c:SES_c -0.793 -0.911 0.848 0.142 0.190