SEM in R

library(psych)

all=read.csv(choose.files())

#Calculating_Cronbach's Alpha

covid_concern<- alpha(data.frame(all[c("CO2", "CO3", "CO5", "CO7")]))

attitude<- alpha(data.frame(all[c("SN3", "PBC1", "PBC2")]))

social_norm<- alpha(data.frame(all[c("CO4", "AT7", "SN1", "SN2", "PMO1")]))

perc_beh_control<- alpha(data.frame(all[c("AT2", "AT4", "AT5", "AT6")]))

perc_mor_obligation<-alpha(data.frame(all[c("CO8", "AT1")]))

####sem

library(lavaan)

library(semPlot)

#all=read.csv(choose.files())

model1<- '

# Structural model

CO=~CO2+ CO3 +CO5 +CO7

AT=~SN3+ PBC1+ PBC2

SN=~CO4+ AT7+ SN1+ SN2+ PMO1

PBC=~AT2+AT4+AT5+AT6

PMO=~CO8+AT1

# Covariance structure of exogenous variables

# New parameters (indirect effect)

#Regression

AT~CO

SN~CO

PBC~CO

PMO~AT

PMO~SN

PMO~PBC

                  '

fit1<- sem(model1, data=all)

fit1

summary(fit1, rsquare = TRUE,

        fit.measures = TRUE,

        standardized = TRUE)

fitMeasures(fit1)

semPaths(fit1, what="paths", whatLabels = "stand",

         rotation = 2,

         layout = "spring",

         posCol = "black",

         edge.width = 0.5, 

         style = "Lisrel",

         fade = T,

         edge.label.position = 0.55)

###############

# Extract the correlation matrix

all.cor <- cor(all[], method = "pearson", use = "pairwise.complete.obs")

all.cor

# Correlogram

corrplot(all.cor, order = "hclust",

         tl.col = "black", tl.srt = 80,

         addCoef.col = "black",

         number.cex = 0.8,

         cl.cex = 1,

         tl.cex = 0.8)

library(corrplot)

library(RColorBrewer)

#library(psych)

#corPlot(data, cex =1.2, main="", 

#       cex.lab = 1.2,

#        cex.axis =1.2,

#       cex.main = 1.2,

#      cex.sub = 1.2)

library(psych)

cor.plot(all.cor,numbers=TRUE,colors=TRUE,

         n=51,main=NULL,labels=NULL,

         cex =1,

         cex.lab = 1,

         cex.axis =1, #right side level

         cex.main = 1,

         cex.sub = 1)