Olah Data
2022-11-24
Baca Data
Data hasil kuesioner
if(!require(googlesheets4)){
install.packages("googlesheets4")
library(googlesheets4)
}
gs4_deauth()
form <- "https://docs.google.com/spreadsheets/d/1BctPP-J7X2qz6bm6QTCVDAZDNS3l37G9godqdfIng0Q/edit#gid=752027602"
raw_data <- NULL
raw_data <- data.frame(read_sheet(form))
# library(readxl)
# data <- read_excel("Kuesioner Penelitian (Responses).xlsx")
# membuang timestamp
raw_data <- raw_data[,-1]
# membuang pertanyaan x1-18 yang double
raw_data <- raw_data[,-20]
# Mengganti nama variabel x1 : kolom 2 - 22
colnames(raw_data)[2:22] <- paste0("x1-",1:21)
# Mengganti nama variabel x2 : kolom 35 - 56
colnames(raw_data)[35:56] <- paste0("x2-",1:22)
# Mengganti nama variabel x3 : kolom 23 - 34
colnames(raw_data)[23:34] <- paste0("x3-",1:12)
# Mengganti nama variabel y1 : kolom 57 - 68
colnames(raw_data)[57:68] <- paste0("y1-",1:12)
# Mengganti nama variabel y2 : kolom 69 - 79
colnames(raw_data)[69:79] <- paste0("y2-",1:11)
# Konversi jawaban ke angka 1 hingga 5
for (i in 2:ncol(raw_data)){
raw_data[,i] <- sapply(raw_data[,i], switch,
"Sangat Setuju" = 5,
"Setuju" = 4,
"Ragu-ragu" = 3,
"Tidak Setuju" = 2,
"Sangat Tidak Setuju" = 1)
}
library(downloadthis)Banyaknya responden adalah orang.
Data dengan konversi jawaban bisa diunduh di sini
Pembagian Data
Variabel \(X_1\) terdiri atas \(X_{11}\), \(X_{12}\), \(X_{13}\), dan \(X_{14}\).
Variabel \(X_2\) terdiri atas \(X_{21}\), \(X_{22}\), \(X_{23}\), \(X_{24}\), dan \(X_{25}\).
Variabel \(X_3\) terdiri atas \(X_{31}\), \(X_{32}\), dan \(X_{33}\).
Variabel \(Y_1\) terdiri atas \(Y_{11}\), \(Y_{12}\), dan \(Y_{13}\).
Variabel \(Y_2\) terdiri atas \(Y_{21}\), \(Y_{22}\), \(Y_{23}\), dan \(Y_{24}\).
| No | Variabel | Indikator | Item |
|---|---|---|---|
| Pendidikan Kewirausahaan (\(X_1\)) |
|
x1.1 s/d x1.5 | |
|
x1.6 s/d x1.10 | ||
|
x1.11 s/d x1.16 | ||
|
x1.17 s/d x1.21 | ||
| Efikasi Diri (\(X_2\)) |
|
x2.1 s/d x2.6 | |
|
x2.7 s/d x2.10 | ||
|
x2.11 s/d x2.15 | ||
|
x2.16 s/d x2.19 | ||
|
x2.20 s/d x2.22 | ||
| Peran Orang Tua (\(X_3\)) |
|
x3.1 s/d x3.4 | |
|
x3.5 s/d x3.8 | ||
|
x3.9 s/d x3.12 | ||
| Sikap berwirausaha (\(Y_1\)) |
|
y1.1 s/d y1.4 | |
|
y1.5 s/d y1.8 | ||
|
y1.9 s/d y1.12 | ||
| Niat berusaha mahasiswa (\(Y_2\)) |
|
y2.1 s/d y2.2 | |
|
y2.3 s/d y2.5 | ||
|
y2.6 s/d y2.8 | ||
|
y2.9 s/d y2.11 |
data <- raw_data[10:209,]
x11 <- apply(data[, 2:6], 1, mean)
x12 <- apply(data[, 7:11], 1, mean)
x13 <- apply(data[, 12:17], 1, mean)
x14 <- apply(data[, 17:21], 1, mean)
x21 <- apply(data[, 35:40], 1, mean)
x22 <- apply(data[, 41:44], 1, mean)
x23 <- apply(data[, 45:49], 1, mean)
x24 <- apply(data[, 50:53], 1, mean)
x25 <- apply(data[, 54:56], 1, mean)
x31 <- apply(data[, 23:26], 1, mean)
x32 <- apply(data[, 27:30], 1, mean)
x33 <- apply(data[, 31:34], 1, mean)
y11 <- apply(data[, 57:60], 1, mean)
y12 <- apply(data[, 61:64], 1, mean)
y13 <- apply(data[, 65:68], 1, mean)
y21 <- apply(data[, 69:70], 1, mean)
y22 <- apply(data[, 71:73], 1, mean)
y23 <- apply(data[, 74:76], 1, mean)
y24 <- apply(data[, 77:79], 1, mean)
dat <- data.frame(x11, x12, x13, x14,
x21, x22, x23, x24, x25,
x31, x32, x33,
y11, y12, y13,
y21, y22, y23, y24)Deskripsi Data
Variabel \(X_1\)
# fungsi untuk membuat distribusi frekuensi
sebaran <- function(data){
data.frame(Variabel = names(data),
N = nrow(data),
Minimum = apply(data, 2, min),
Maximum = apply(data, 2, max),
Rerata = round(apply(data, 2, mean),4),
Std_Deviation = round(apply(data, 2, sd),4),
Variance = round(apply(data, 2, var),4),
row.names = NULL)
}
dat_x1 <- data.frame(x11,x12,x13,x14)
dat_x2 <- data.frame(x21,x22,x23,x24,x25)
dat_x3 <- data.frame(x31,x32,x33)
dat_y1 <- data.frame(y11,y12,y13)
dat_y2 <- data.frame(y21,y22,y23,y24)Distribusi frekuensi variabel \(X_1\)
sebaran(dat_x1)Nilai rata-rata untuk variabel \(X_1\) adalah: 4.1727
Variabel \(X_2\)
Distribusi frekuensi variabel \(X_2\)
sebaran(dat_x2)Nilai rata-rata untuk variabel \(X_2\) adalah: 3.9711
Variabel \(X_3\)
Distribusi frekuensi variabel \(X_3\)
sebaran(dat_x3)Nilai rata-rata untuk variabel \(X_3\) adalah: 3.83
Variabel \(Y_1\)
Distribusi frekuensi variabel \(Y_1\)
sebaran(dat_y1)Nilai rata-rata untuk variabel \(Y_1\) adalah: 3.8409
Variabel \(Y_2\)
Distribusi frekuensi variabel \(Y_2\)
sebaran(dat_y2)Nilai rata-rata untuk variabel \(Y_2\) adalah: 3.6252
CFA
Confirmatory Factor Analysis (CFA) \(X_1\)
Package yang digunakan: lavaan
if(!require(lavaan)){
install.packages("lavaan")
library(lavaan)
}
#if(!require(tidySEM)){
# install.packages("tidySEM")
# library(tidySEM)
#}
if(!require(semPlot)){
install.packages("semPlot")
library(semPlot)
}
if(!require(semTools)){
install.packages("semTools")
library(semTools)
}mod1 <- 'x1 =~ x11 + x12 + x13 + x14'
fit <- cfa(mod1, data = dat)
summary(fit, fit.measures = T, standardized = T)## lavaan 0.6-12 ended normally after 30 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 8
##
## Number of observations 200
##
## Model Test User Model:
##
## Test statistic 54.337
## Degrees of freedom 2
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 795.562
## Degrees of freedom 6
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.934
## Tucker-Lewis Index (TLI) 0.801
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -224.075
## Loglikelihood unrestricted model (H1) -196.907
##
## Akaike (AIC) 464.150
## Bayesian (BIC) 490.537
## Sample-size adjusted Bayesian (BIC) 465.192
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.362
## 90 Percent confidence interval - lower 0.282
## 90 Percent confidence interval - upper 0.448
## P-value RMSEA <= 0.05 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.033
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## x1 =~
## x11 1.000 0.422 0.864
## x12 1.097 0.061 17.871 0.000 0.463 0.901
## x13 1.107 0.063 17.545 0.000 0.467 0.893
## x14 1.123 0.059 18.921 0.000 0.474 0.928
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .x11 0.061 0.007 8.246 0.000 0.061 0.254
## .x12 0.049 0.007 7.360 0.000 0.049 0.187
## .x13 0.055 0.007 7.614 0.000 0.055 0.202
## .x14 0.036 0.006 6.225 0.000 0.036 0.138
## x1 0.178 0.023 7.592 0.000 1.000 1.000standardizedSolution(fit)semPaths(fit, what = "path", whatLabels = "stand", rotation = 1)
lavInspect(fit, what = "std")## $lambda
## x1
## x11 0.864
## x12 0.901
## x13 0.893
## x14 0.928
##
## $theta
## x11 x12 x13 x14
## x11 0.254
## x12 0.000 0.187
## x13 0.000 0.000 0.202
## x14 0.000 0.000 0.000 0.138
##
## $psi
## x1
## x1 1Reliability Komposit dan Konvergen validity
Reliabilitas komposit menggunakan fungsi
semTools::compRelSEM()
semTools::reliability(fit)## x1
## alpha 0.9425130
## omega 0.9430212
## omega2 0.9430212
## omega3 0.9427553
## avevar 0.8056643semTools::AVE(fit)## x1
## 0.806semTools::compRelSEM(fit) # composite reliability## x1
## 0.943Perhitungan reliabilitas komposit secara manual
sum(inspect(fit,"std")$lambda)^2/(sum(inspect(fit,"std")$lambda)^2 + sum(inspect(fit,"std")$theta))## [1] 0.9426913Confirmatory Factor Analysis (CFA) \(X_2\)
mod2 <- 'x2 =~ x21 + x22 + x23 + x24 + x25'
fit <- cfa(mod2, data = dat)
summary(fit, fit.measures = T)## lavaan 0.6-12 ended normally after 34 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 10
##
## Number of observations 200
##
## Model Test User Model:
##
## Test statistic 27.807
## Degrees of freedom 5
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 1193.995
## Degrees of freedom 10
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.981
## Tucker-Lewis Index (TLI) 0.961
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -371.764
## Loglikelihood unrestricted model (H1) -357.860
##
## Akaike (AIC) 763.528
## Bayesian (BIC) 796.511
## Sample-size adjusted Bayesian (BIC) 764.830
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.151
## 90 Percent confidence interval - lower 0.099
## 90 Percent confidence interval - upper 0.208
## P-value RMSEA <= 0.05 0.001
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.016
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## x2 =~
## x21 1.000
## x22 1.023 0.049 20.838 0.000
## x23 0.901 0.043 20.929 0.000
## x24 0.894 0.042 21.481 0.000
## x25 0.983 0.047 20.918 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .x21 0.089 0.011 8.418 0.000
## .x22 0.071 0.009 7.934 0.000
## .x23 0.054 0.007 7.890 0.000
## .x24 0.047 0.006 7.589 0.000
## .x25 0.065 0.008 7.895 0.000
## x2 0.360 0.044 8.121 0.000standardizedSolution(fit)#lay <- get_layout("", "", "x2", "", "",
# "x21","x22","x23","x24","x25", rows = 2)
#graph_sem(fit)
semPaths(fit, what = "path", whatLabels = "stand", rotation = 1)
lavInspect(fit, what = "std")## $lambda
## x2
## x21 0.896
## x22 0.917
## x23 0.918
## x24 0.927
## x25 0.918
##
## $theta
## x21 x22 x23 x24 x25
## x21 0.197
## x22 0.000 0.159
## x23 0.000 0.000 0.156
## x24 0.000 0.000 0.000 0.140
## x25 0.000 0.000 0.000 0.000 0.157
##
## $psi
## x2
## x2 1Reliability Komposit dan Konvergen validity
semTools::reliability(fit)## x2
## alpha 0.9616131
## omega 0.9622675
## omega2 0.9622675
## omega3 0.9620207
## avevar 0.8364920semTools::AVE(fit)## x2
## 0.836semTools::compRelSEM(fit) # composite reliability## x2
## 0.962Perhitungan reliabilitas komposit secara manual
sum(inspect(fit,"std")$lambda)^2/(sum(inspect(fit,"std")$lambda)^2 + sum(inspect(fit,"std")$theta))## [1] 0.9628043Confirmatory Factor Analysis (CFA) \(X_3\)
mod3 <- 'x3 =~ x31 + x32 + x33'
fit <- cfa(mod3, data = dat)
summary(fit, fit.measures = T)## lavaan 0.6-12 ended normally after 17 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 6
##
## Number of observations 200
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 349.350
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -513.155
## Loglikelihood unrestricted model (H1) -513.155
##
## Akaike (AIC) 1038.310
## Bayesian (BIC) 1058.100
## Sample-size adjusted Bayesian (BIC) 1039.092
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value RMSEA <= 0.05 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## x3 =~
## x31 1.000
## x32 1.510 0.120 12.589 0.000
## x33 1.449 0.115 12.571 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .x31 0.191 0.022 8.586 0.000
## .x32 0.130 0.029 4.472 0.000
## .x33 0.128 0.027 4.714 0.000
## x3 0.246 0.041 6.005 0.000standardizedSolution(fit)#graph_sem(fit)
semPaths(fit, what = "path", whatLabels = "stand", rotation = 1)
lavInspect(fit, what = "std")## $lambda
## x3
## x31 0.750
## x32 0.901
## x33 0.895
##
## $theta
## x31 x32 x33
## x31 0.438
## x32 0.000 0.189
## x33 0.000 0.000 0.199
##
## $psi
## x3
## x3 1Reliability Komposit dan Konvergen validity
semTools::reliability(fit)## x3
## alpha 0.8821535
## omega 0.8954410
## omega2 0.8954410
## omega3 0.8954410
## avevar 0.7461529semTools::AVE(fit)## x3
## 0.746semTools::compRelSEM(fit) # composite reliability## x3
## 0.895Perhitungan reliabilitas komposit secara manual
sum(inspect(fit,"std")$lambda)^2/(sum(inspect(fit,"std")$lambda)^2 + sum(inspect(fit,"std")$theta))## [1] 0.8870264Confirmatory Factor Analysis (CFA) \(Y_1\)
mod4 <- 'y1 =~ y11 + y12 + y13'
fit <- cfa(mod4, data = dat)
summary(fit, fit.measures = T)## lavaan 0.6-12 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 6
##
## Number of observations 200
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 246.222
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -457.557
## Loglikelihood unrestricted model (H1) -457.557
##
## Akaike (AIC) 927.113
## Bayesian (BIC) 946.903
## Sample-size adjusted Bayesian (BIC) 927.895
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value RMSEA <= 0.05 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## y1 =~
## y11 1.000
## y12 0.855 0.083 10.329 0.000
## y13 0.998 0.097 10.256 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .y11 0.244 0.032 7.742 0.000
## .y12 0.076 0.016 4.627 0.000
## .y13 0.155 0.025 6.152 0.000
## y1 0.286 0.051 5.601 0.000standardizedSolution(fit)#graph_sem(fit)
semPaths(fit, what = "path", whatLabels = "stand", rotation = 1)
lavInspect(fit, what = "std")## $lambda
## y1
## y11 0.735
## y12 0.856
## y13 0.805
##
## $theta
## y11 y12 y13
## y11 0.460
## y12 0.000 0.267
## y13 0.000 0.000 0.352
##
## $psi
## y1
## y1 1Reliability Komposit dan Konvergen validity
semTools::reliability(fit)## y1
## alpha 0.8286532
## omega 0.8307704
## omega2 0.8307704
## omega3 0.8307704
## avevar 0.6218878semTools::AVE(fit)## y1
## 0.622semTools::compRelSEM(fit) # composite reliability## y1
## 0.831Perhitungan reliabilitas komposit secara manual
sum(inspect(fit,"std")$lambda)^2/(sum(inspect(fit,"std")$lambda)^2 + sum(inspect(fit,"std")$theta))## [1] 0.8418983Confirmatory Factor Analysis (CFA) \(Y_2\)
mod5 <- 'y2 =~ y21 + y22 + y23 + y24'
fit <- cfa(mod5, data = dat)
summary(fit, fit.measures = T)## lavaan 0.6-12 ended normally after 23 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 8
##
## Number of observations 200
##
## Model Test User Model:
##
## Test statistic 40.550
## Degrees of freedom 2
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 247.914
## Degrees of freedom 6
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.841
## Tucker-Lewis Index (TLI) 0.522
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -776.676
## Loglikelihood unrestricted model (H1) -756.401
##
## Akaike (AIC) 1569.352
## Bayesian (BIC) 1595.739
## Sample-size adjusted Bayesian (BIC) 1570.394
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.310
## 90 Percent confidence interval - lower 0.232
## 90 Percent confidence interval - upper 0.397
## P-value RMSEA <= 0.05 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.092
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## y2 =~
## y21 1.000
## y22 0.890 0.164 5.430 0.000
## y23 1.444 0.193 7.472 0.000
## y24 1.015 0.136 7.467 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .y21 0.361 0.041 8.784 0.000
## .y22 0.563 0.060 9.446 0.000
## .y23 0.109 0.038 2.860 0.004
## .y24 0.193 0.027 7.189 0.000
## y2 0.191 0.046 4.144 0.000standardizedSolution(fit)semPaths(fit, what = "path", whatLabels = "stand", rotation = 1)
lavInspect(fit, what = "std")## $lambda
## y2
## y21 0.589
## y22 0.461
## y23 0.886
## y24 0.711
##
## $theta
## y21 y22 y23 y24
## y21 0.653
## y22 0.000 0.788
## y23 0.000 0.000 0.215
## y24 0.000 0.000 0.000 0.495
##
## $psi
## y2
## y2 1Reliability Komposit dan Konvergen validity
semTools::reliability(fit)## y2
## alpha 0.7536757
## omega 0.7469534
## omega2 0.7469534
## omega3 0.7267026
## avevar 0.4337205semTools::AVE(fit)## y2
## 0.434semTools::compRelSEM(fit) # composite reliability## y2
## 0.727Karena nilai AVE = 0.4337205 kurang dari 0.5, maka terdapat faktor yang tidak valid. Faktor yang tidak valid adalah faktor dengan standardized loadings terkecil (\(y_{22}\))
inspect(fit,"std")$lambda## y2
## y21 0.589
## y22 0.461
## y23 0.886
## y24 0.711\(y_{22}\) dikeluarkan dari model.
mod5 <- 'y2 =~ y21 + y23 + y24'
fit <- cfa(mod5, data = dat)
summary(fit, fit.measures = T)## lavaan 0.6-12 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 6
##
## Number of observations 200
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 169.150
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -545.655
## Loglikelihood unrestricted model (H1) -545.655
##
## Akaike (AIC) 1103.311
## Bayesian (BIC) 1123.101
## Sample-size adjusted Bayesian (BIC) 1104.092
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value RMSEA <= 0.05 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## y2 =~
## y21 1.000
## y23 1.530 0.234 6.550 0.000
## y24 1.121 0.158 7.101 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .y21 0.383 0.043 8.872 0.000
## .y23 0.112 0.048 2.339 0.019
## .y24 0.178 0.031 5.792 0.000
## y2 0.169 0.044 3.808 0.000standardizedSolution(fit)semPaths(fit, what = "path", whatLabels = "stand", rotation = 1)
lavInspect(fit, what = "std")## $lambda
## y2
## y21 0.554
## y23 0.883
## y24 0.738
##
## $theta
## y21 y23 y24
## y21 0.693
## y23 0.000 0.220
## y24 0.000 0.000 0.455
##
## $psi
## y2
## y2 1Reliability Komposit dan Konvergen validity
semTools::reliability(fit)## y2
## alpha 0.7572136
## omega 0.7705845
## omega2 0.7705845
## omega3 0.7705845
## avevar 0.5367130semTools::AVE(fit)## y2
## 0.537semTools::compRelSEM(fit) # composite reliability## y2
## 0.771Nilai AVE sudah di atas 0.5 (semua faktor sudah valid).
SEM
Model 1: Model Awal
modsem1 <- 'PKWU =~ x11 + x12 + x13 + x14
ED =~ x21 + x22 + x23 + x24 + x25
POT =~ x31 + x32 + x33
SKP =~ y11 + y12 + y13
NKWU =~ y23 + y24
# Regression
SKP ~ PKWU + ED + POT
NKWU ~ PKWU + ED + POT
NKWU ~ SKP'
fit1 <- sem(modsem1, data = dat, estimator = "MLR")
summary(fit1, fit.measures = T, standardized = T)## lavaan 0.6-12 ended normally after 103 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 44
##
## Number of observations 200
##
## Model Test User Model:
## Standard Robust
## Test Statistic 324.578 263.235
## Degrees of freedom 109 109
## P-value (Chi-square) 0.000 0.000
## Scaling correction factor 1.233
## Yuan-Bentler correction (Mplus variant)
##
## Model Test Baseline Model:
##
## Test statistic 3727.602 3155.133
## Degrees of freedom 136 136
## P-value 0.000 0.000
## Scaling correction factor 1.181
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.940 0.949
## Tucker-Lewis Index (TLI) 0.925 0.936
##
## Robust Comparative Fit Index (CFI) 0.947
## Robust Tucker-Lewis Index (TLI) 0.933
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1522.404 -1522.404
## Scaling correction factor 1.536
## for the MLR correction
## Loglikelihood unrestricted model (H1) -1360.115 -1360.115
## Scaling correction factor 1.320
## for the MLR correction
##
## Akaike (AIC) 3132.809 3132.809
## Bayesian (BIC) 3277.935 3277.935
## Sample-size adjusted Bayesian (BIC) 3138.538 3138.538
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.099 0.084
## 90 Percent confidence interval - lower 0.087 0.072
## 90 Percent confidence interval - upper 0.112 0.096
## P-value RMSEA <= 0.05 0.000 0.000
##
## Robust RMSEA 0.093
## 90 Percent confidence interval - lower 0.079
## 90 Percent confidence interval - upper 0.108
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.046 0.046
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU =~
## x11 1.000 0.414 0.847
## x12 1.090 0.058 18.884 0.000 0.451 0.879
## x13 1.152 0.088 13.108 0.000 0.477 0.911
## x14 1.158 0.090 12.929 0.000 0.479 0.939
## ED =~
## x21 1.000 0.607 0.906
## x22 1.017 0.052 19.478 0.000 0.617 0.921
## x23 0.886 0.060 14.811 0.000 0.537 0.913
## x24 0.880 0.053 16.568 0.000 0.534 0.923
## x25 0.970 0.057 17.114 0.000 0.589 0.916
## POT =~
## x31 1.000 0.504 0.762
## x32 1.491 0.148 10.074 0.000 0.751 0.904
## x33 1.409 0.134 10.510 0.000 0.710 0.884
## SKP =~
## y11 1.000 0.530 0.728
## y12 0.851 0.069 12.349 0.000 0.452 0.845
## y13 1.028 0.078 13.117 0.000 0.545 0.822
## NKWU =~
## y23 1.000 0.568 0.796
## y24 0.901 0.078 11.511 0.000 0.512 0.819
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## SKP ~
## PKWU 0.409 0.110 3.706 0.000 0.319 0.319
## ED 0.225 0.101 2.240 0.025 0.258 0.258
## POT 0.382 0.125 3.052 0.002 0.363 0.363
## NKWU ~
## PKWU -0.155 0.135 -1.147 0.251 -0.113 -0.113
## ED 0.405 0.133 3.057 0.002 0.433 0.433
## POT 0.021 0.139 0.151 0.880 0.019 0.019
## SKP 0.722 0.192 3.753 0.000 0.675 0.675
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU ~~
## ED 0.193 0.053 3.612 0.000 0.767 0.767
## POT 0.146 0.044 3.290 0.001 0.702 0.702
## ED ~~
## POT 0.256 0.052 4.953 0.000 0.837 0.837
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .x11 0.067 0.015 4.596 0.000 0.067 0.283
## .x12 0.060 0.010 5.773 0.000 0.060 0.228
## .x13 0.046 0.007 6.248 0.000 0.046 0.170
## .x14 0.031 0.006 4.995 0.000 0.031 0.118
## .x21 0.081 0.017 4.688 0.000 0.081 0.180
## .x22 0.068 0.011 5.920 0.000 0.068 0.152
## .x23 0.058 0.011 5.110 0.000 0.058 0.166
## .x24 0.050 0.008 6.229 0.000 0.050 0.149
## .x25 0.067 0.012 5.694 0.000 0.067 0.162
## .x31 0.184 0.028 6.566 0.000 0.184 0.420
## .x32 0.127 0.022 5.864 0.000 0.127 0.183
## .x33 0.140 0.023 6.043 0.000 0.140 0.218
## .y11 0.249 0.040 6.259 0.000 0.249 0.470
## .y12 0.082 0.015 5.513 0.000 0.082 0.286
## .y13 0.143 0.028 5.077 0.000 0.143 0.325
## .y23 0.186 0.029 6.358 0.000 0.186 0.366
## .y24 0.129 0.026 4.980 0.000 0.129 0.329
## PKWU 0.171 0.055 3.105 0.002 1.000 1.000
## ED 0.368 0.058 6.332 0.000 1.000 1.000
## POT 0.254 0.058 4.351 0.000 1.000 1.000
## .SKP 0.072 0.018 3.972 0.000 0.255 0.255
## .NKWU 0.011 0.020 0.567 0.570 0.035 0.035standardizedSolution(fit1)semPaths(fit1, what = "paths", whatLabels = "stand", rotation = 3)
lavInspect(fit1, what = "std")## $lambda
## PKWU ED POT SKP NKWU
## x11 0.847 0.000 0.000 0.000 0.000
## x12 0.879 0.000 0.000 0.000 0.000
## x13 0.911 0.000 0.000 0.000 0.000
## x14 0.939 0.000 0.000 0.000 0.000
## x21 0.000 0.906 0.000 0.000 0.000
## x22 0.000 0.921 0.000 0.000 0.000
## x23 0.000 0.913 0.000 0.000 0.000
## x24 0.000 0.923 0.000 0.000 0.000
## x25 0.000 0.916 0.000 0.000 0.000
## x31 0.000 0.000 0.762 0.000 0.000
## x32 0.000 0.000 0.904 0.000 0.000
## x33 0.000 0.000 0.884 0.000 0.000
## y11 0.000 0.000 0.000 0.728 0.000
## y12 0.000 0.000 0.000 0.845 0.000
## y13 0.000 0.000 0.000 0.822 0.000
## y23 0.000 0.000 0.000 0.000 0.796
## y24 0.000 0.000 0.000 0.000 0.819
##
## $theta
## x11 x12 x13 x14 x21 x22 x23 x24 x25 x31 x32 x33
## x11 0.283
## x12 0.000 0.228
## x13 0.000 0.000 0.170
## x14 0.000 0.000 0.000 0.118
## x21 0.000 0.000 0.000 0.000 0.180
## x22 0.000 0.000 0.000 0.000 0.000 0.152
## x23 0.000 0.000 0.000 0.000 0.000 0.000 0.166
## x24 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.149
## x25 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.162
## x31 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.420
## x32 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.183
## x33 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.218
## y11 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## y12 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## y13 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## y23 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## y24 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## y11 y12 y13 y23 y24
## x11
## x12
## x13
## x14
## x21
## x22
## x23
## x24
## x25
## x31
## x32
## x33
## y11 0.470
## y12 0.000 0.286
## y13 0.000 0.000 0.325
## y23 0.000 0.000 0.000 0.366
## y24 0.000 0.000 0.000 0.000 0.329
##
## $psi
## PKWU ED POT SKP NKWU
## PKWU 1.000
## ED 0.767 1.000
## POT 0.702 0.837 1.000
## SKP 0.000 0.000 0.000 0.255
## NKWU 0.000 0.000 0.000 0.000 0.035
##
## $beta
## PKWU ED POT SKP NKWU
## PKWU 0.000 0.000 0.000 0.000 0
## ED 0.000 0.000 0.000 0.000 0
## POT 0.000 0.000 0.000 0.000 0
## SKP 0.319 0.258 0.363 0.000 0
## NKWU -0.113 0.433 0.019 0.675 0Reliability Komposit dan Konvergen validity
semTools::reliability(fit1)## PKWU ED POT SKP NKWU
## alpha 0.9425130 0.9616131 0.8821535 0.8286532 0.7851762
## omega 0.9418486 0.9626247 0.8955416 0.8312010 0.7872959
## omega2 0.9418486 0.9626247 0.8955416 0.8312010 0.7872959
## omega3 0.9377383 0.9630932 0.8972242 0.8309890 0.7872962
## avevar 0.8024747 0.8379197 0.7459212 0.6229458 0.6498190semTools::AVE(fit1)## PKWU ED POT SKP NKWU
## 0.802 0.838 0.746 0.623 0.650semTools::compRelSEM(fit1) # composite reliability## PKWU ED POT SKP NKWU
## 0.938 0.963 0.897 0.831 0.787Discriminant Validity
semTools::discriminantValidity(fit1)htmt(modsem1, dat)## PKWU ED POT SKP NKWU
## PKWU 1.000
## ED 0.751 1.000
## POT 0.698 0.851 1.000
## SKP 0.750 0.792 0.810 1.000
## NKWU 0.730 0.897 0.836 0.953 1.000Model performance
sumber yang digunakan untuk membuat pengukuran kinerja model diambil dari https://rdrr.io/cran/performance/man/model_performance.lavaan.html
Berikut adalah fungsi kinerja untuk menentukan model
performance berdasarkan acuan di atas.
kinerja <- function(model){
a <- lavaan::fitmeasures(model, c("chisq.scaled", "pvalue.scaled", "df.scaled", "srmr", "rmsea.scaled",
"gfi", "agfi", "cfi.scaled", "ifi.scaled", "nnfi.scaled", "aic"))
tabel <- NULL
tabel <- data.frame(ukuran = names(a[1:3]),
koefisien = round(a[1:3], 2))
tabel <- rbind(tabel, data.frame(ukuran = "Cmin", koefisien = round(a[1]/a[3],2)))
tabel <- rbind(tabel, data.frame(ukuran = names(a[4:11]), koefisien = round(a[4:11], 2)))
tabel$kriteria <- c("kecil", ">= 0.05", "---", "<= 2.00", "<= 0.08", "<= 0.08", ">= 0.90",
">= 0.90", ">= 0.90", ">= 0.90", ">= 0.90", "Kecil")
tabel$kesimpulan[1] <- "Baik, terpenuhi"
tabel$kesimpulan[2] <- ifelse(tabel$koefisien[2] >= 0.05, "Baik, terpenuhi", "Tidak terpenuhi")
tabel$kesimpulan[3] <- "---"
tabel$kesimpulan[4] <- ifelse(tabel$koefisien[4] <= 2, "Baik, terpenuhi", "Tidak terpenuhi")
tabel$kesimpulan[5] <- ifelse(tabel$koefisien[5] <= 0.08, "Baik, terpenuhi", "Tidak terpenuhi")
tabel$kesimpulan[6] <- ifelse(tabel$koefisien[6] <= 0.08, "Baik, terpenuhi", "Tidak terpenuhi")
tabel$kesimpulan[7] <- ifelse(tabel$koefisien[7] >= 0.9, "Baik, terpenuhi", "Tidak terpenuhi")
tabel$kesimpulan[8] <- ifelse(tabel$koefisien[8] >= 0.9, "Baik, terpenuhi", "Tidak terpenuhi")
tabel$kesimpulan[9] <- ifelse(tabel$koefisien[9] >= 0.9, "Baik, terpenuhi", "Tidak terpenuhi")
tabel$kesimpulan[10] <- ifelse(tabel$koefisien[10] >= 0.9, "Baik, terpenuhi", "Tidak terpenuhi")
tabel$kesimpulan[11] <- ifelse(tabel$koefisien[11] >= 0.9, "Baik, terpenuhi", "Tidak terpenuhi")
tabel$kesimpulan[12] <- "Kecil"
print(tabel, row.names = F)
}Berikut adalah kinerja dari model 1
kinerja_mod1 <- kinerja(fit1)## ukuran koefisien kriteria kesimpulan
## chisq.scaled 263.24 kecil Baik, terpenuhi
## pvalue.scaled 0.00 >= 0.05 Tidak terpenuhi
## df.scaled 109.00 --- ---
## Cmin 2.42 <= 2.00 Tidak terpenuhi
## srmr 0.05 <= 0.08 Baik, terpenuhi
## rmsea.scaled 0.08 <= 0.08 Baik, terpenuhi
## gfi 0.84 >= 0.90 Tidak terpenuhi
## agfi 0.77 >= 0.90 Tidak terpenuhi
## cfi.scaled 0.95 >= 0.90 Baik, terpenuhi
## ifi.scaled 0.95 >= 0.90 Baik, terpenuhi
## nnfi.scaled 0.94 >= 0.90 Baik, terpenuhi
## aic 3132.81 Kecil KecilModel 2
\(y_{21}\) dan \(y_{22}\) dikeluarkan dari model
modsem2 <- 'PKWU =~ x11 + x12 + x13 + x14
ED =~ x22 + x23 + x24
POT =~ x31 + x32 + x33
SKP =~ y11 + y12 + y13
NKWU =~ y21 + y23 + y24
# Regression
SKP ~ PKWU + ED + POT
NKWU ~ PKWU + ED + POT
NKWU ~ SKP
'
fit2 <- sem(modsem2, data = dat, estimator = "MLR")
summary(fit2, fit.measures = T, standardized = T)## lavaan 0.6-12 ended normally after 91 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 42
##
## Number of observations 200
##
## Model Test User Model:
## Standard Robust
## Test Statistic 275.922 238.028
## Degrees of freedom 94 94
## P-value (Chi-square) 0.000 0.000
## Scaling correction factor 1.159
## Yuan-Bentler correction (Mplus variant)
##
## Model Test Baseline Model:
##
## Test statistic 3093.765 2800.154
## Degrees of freedom 120 120
## P-value 0.000 0.000
## Scaling correction factor 1.105
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.939 0.946
## Tucker-Lewis Index (TLI) 0.922 0.931
##
## Robust Comparative Fit Index (CFI) 0.944
## Robust Tucker-Lewis Index (TLI) 0.928
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1640.300 -1640.300
## Scaling correction factor 1.483
## for the MLR correction
## Loglikelihood unrestricted model (H1) -1502.339 -1502.339
## Scaling correction factor 1.259
## for the MLR correction
##
## Akaike (AIC) 3364.599 3364.599
## Bayesian (BIC) 3503.128 3503.128
## Sample-size adjusted Bayesian (BIC) 3370.068 3370.068
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.098 0.088
## 90 Percent confidence interval - lower 0.085 0.075
## 90 Percent confidence interval - upper 0.112 0.100
## P-value RMSEA <= 0.05 0.000 0.000
##
## Robust RMSEA 0.094
## 90 Percent confidence interval - lower 0.079
## 90 Percent confidence interval - upper 0.109
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.051 0.051
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU =~
## x11 1.000 0.415 0.848
## x12 1.090 0.058 18.938 0.000 0.452 0.879
## x13 1.150 0.088 13.122 0.000 0.477 0.911
## x14 1.155 0.089 12.985 0.000 0.479 0.938
## ED =~
## x22 1.000 0.607 0.907
## x23 0.898 0.046 19.610 0.000 0.545 0.926
## x24 0.883 0.044 20.234 0.000 0.536 0.927
## POT =~
## x31 1.000 0.502 0.759
## x32 1.499 0.149 10.046 0.000 0.753 0.905
## x33 1.414 0.135 10.472 0.000 0.710 0.885
## SKP =~
## y11 1.000 0.534 0.733
## y12 0.840 0.070 11.971 0.000 0.448 0.838
## y13 1.026 0.076 13.479 0.000 0.548 0.825
## NKWU =~
## y21 1.000 0.384 0.517
## y23 1.525 0.216 7.068 0.000 0.586 0.821
## y24 1.323 0.210 6.300 0.000 0.508 0.813
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## SKP ~
## PKWU 0.415 0.111 3.725 0.000 0.322 0.322
## ED 0.200 0.099 2.024 0.043 0.227 0.227
## POT 0.417 0.127 3.277 0.001 0.393 0.393
## NKWU ~
## PKWU -0.138 0.094 -1.465 0.143 -0.149 -0.149
## ED 0.211 0.088 2.393 0.017 0.333 0.333
## POT 0.061 0.092 0.663 0.508 0.080 0.080
## SKP 0.527 0.144 3.674 0.000 0.732 0.732
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU ~~
## ED 0.192 0.054 3.580 0.000 0.764 0.764
## POT 0.146 0.044 3.289 0.001 0.701 0.701
## ED ~~
## POT 0.250 0.050 5.044 0.000 0.819 0.819
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .x11 0.067 0.015 4.584 0.000 0.067 0.281
## .x12 0.060 0.010 5.777 0.000 0.060 0.227
## .x13 0.046 0.007 6.204 0.000 0.046 0.170
## .x14 0.031 0.006 5.015 0.000 0.031 0.120
## .x22 0.080 0.015 5.476 0.000 0.080 0.178
## .x23 0.049 0.012 4.132 0.000 0.049 0.143
## .x24 0.047 0.009 5.459 0.000 0.047 0.142
## .x31 0.185 0.028 6.549 0.000 0.185 0.424
## .x32 0.125 0.022 5.776 0.000 0.125 0.180
## .x33 0.140 0.023 6.103 0.000 0.140 0.217
## .y11 0.246 0.039 6.346 0.000 0.246 0.463
## .y12 0.085 0.015 5.637 0.000 0.085 0.297
## .y13 0.141 0.027 5.181 0.000 0.141 0.319
## .y21 0.404 0.046 8.859 0.000 0.404 0.733
## .y23 0.166 0.028 5.869 0.000 0.166 0.326
## .y24 0.132 0.024 5.502 0.000 0.132 0.339
## PKWU 0.172 0.055 3.111 0.002 1.000 1.000
## ED 0.369 0.055 6.669 0.000 1.000 1.000
## POT 0.252 0.058 4.331 0.000 1.000 1.000
## .SKP 0.073 0.018 3.974 0.000 0.255 0.255
## .NKWU 0.009 0.009 0.948 0.343 0.058 0.058standardizedSolution(fit2)semPaths(fit2, what = "paths", whatLabels = "stand", rotation = 3)
lavInspect(fit2, what = "std")## $lambda
## PKWU ED POT SKP NKWU
## x11 0.848 0.000 0.000 0.000 0.000
## x12 0.879 0.000 0.000 0.000 0.000
## x13 0.911 0.000 0.000 0.000 0.000
## x14 0.938 0.000 0.000 0.000 0.000
## x22 0.000 0.907 0.000 0.000 0.000
## x23 0.000 0.926 0.000 0.000 0.000
## x24 0.000 0.927 0.000 0.000 0.000
## x31 0.000 0.000 0.759 0.000 0.000
## x32 0.000 0.000 0.905 0.000 0.000
## x33 0.000 0.000 0.885 0.000 0.000
## y11 0.000 0.000 0.000 0.733 0.000
## y12 0.000 0.000 0.000 0.838 0.000
## y13 0.000 0.000 0.000 0.825 0.000
## y21 0.000 0.000 0.000 0.000 0.517
## y23 0.000 0.000 0.000 0.000 0.821
## y24 0.000 0.000 0.000 0.000 0.813
##
## $theta
## x11 x12 x13 x14 x22 x23 x24 x31 x32 x33 y11 y12
## x11 0.281
## x12 0.000 0.227
## x13 0.000 0.000 0.170
## x14 0.000 0.000 0.000 0.120
## x22 0.000 0.000 0.000 0.000 0.178
## x23 0.000 0.000 0.000 0.000 0.000 0.143
## x24 0.000 0.000 0.000 0.000 0.000 0.000 0.142
## x31 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.424
## x32 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.180
## x33 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.217
## y11 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.463
## y12 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.297
## y13 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## y21 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## y23 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## y24 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## y13 y21 y23 y24
## x11
## x12
## x13
## x14
## x22
## x23
## x24
## x31
## x32
## x33
## y11
## y12
## y13 0.319
## y21 0.000 0.733
## y23 0.000 0.000 0.326
## y24 0.000 0.000 0.000 0.339
##
## $psi
## PKWU ED POT SKP NKWU
## PKWU 1.000
## ED 0.764 1.000
## POT 0.701 0.819 1.000
## SKP 0.000 0.000 0.000 0.255
## NKWU 0.000 0.000 0.000 0.000 0.058
##
## $beta
## PKWU ED POT SKP NKWU
## PKWU 0.000 0.000 0.000 0.000 0
## ED 0.000 0.000 0.000 0.000 0
## POT 0.000 0.000 0.000 0.000 0
## SKP 0.322 0.227 0.393 0.000 0
## NKWU -0.149 0.333 0.080 0.732 0Reliability Komposit dan Konvergen validity
semTools::reliability(fit2)## PKWU ED POT SKP NKWU
## alpha 0.9425130 0.9393789 0.8821535 0.8286532 0.7572136
## omega 0.9419499 0.9416111 0.8955624 0.8322241 0.7566716
## omega2 0.9419499 0.9416111 0.8955624 0.8322241 0.7566716
## omega3 0.9381461 0.9428717 0.8968696 0.8328099 0.7453517
## avevar 0.8027534 0.8435642 0.7460763 0.6248713 0.5159670semTools::AVE(fit2)## PKWU ED POT SKP NKWU
## 0.803 0.844 0.746 0.625 0.516semTools::compRelSEM(fit2) # composite reliability## PKWU ED POT SKP NKWU
## 0.938 0.943 0.897 0.833 0.745Discriminant Validity
semTools::discriminantValidity(fit2)
htmt(modsem2, dat)Berikut adalah kinerja dari model 2
kinerja_mod2 <- kinerja(fit2)## ukuran koefisien kriteria kesimpulan
## chisq.scaled 238.03 kecil Baik, terpenuhi
## pvalue.scaled 0.00 >= 0.05 Tidak terpenuhi
## df.scaled 94.00 --- ---
## Cmin 2.53 <= 2.00 Tidak terpenuhi
## srmr 0.05 <= 0.08 Baik, terpenuhi
## rmsea.scaled 0.09 <= 0.08 Tidak terpenuhi
## gfi 0.84 >= 0.90 Tidak terpenuhi
## agfi 0.78 >= 0.90 Tidak terpenuhi
## cfi.scaled 0.95 >= 0.90 Baik, terpenuhi
## ifi.scaled 0.95 >= 0.90 Baik, terpenuhi
## nnfi.scaled 0.93 >= 0.90 Baik, terpenuhi
## aic 3364.60 Kecil KecilModel 3
\(y_{11}\) dan \(x_{31}\) dikeluarkan dari model
modsem3 <- 'PKWU =~ x12 + x13 + x14
ED =~ x22 + x23 + x24
POT =~ x32 + x33
SKP =~ y12 + y13
NKWU =~ y23 + y24
# Regression
SKP ~ PKWU + ED + POT
NKWU ~ PKWU + ED + POT
NKWU ~ SKP
'
fit3 <- sem(modsem3, data = dat, estimator = "MLR")
summary(fit3, fit.measures = T, standardized = T)## lavaan 0.6-12 ended normally after 75 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 34
##
## Number of observations 200
##
## Model Test User Model:
## Standard Robust
## Test Statistic 123.276 106.445
## Degrees of freedom 44 44
## P-value (Chi-square) 0.000 0.000
## Scaling correction factor 1.158
## Yuan-Bentler correction (Mplus variant)
##
## Model Test Baseline Model:
##
## Test statistic 2386.797 2187.548
## Degrees of freedom 66 66
## P-value 0.000 0.000
## Scaling correction factor 1.091
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.966 0.971
## Tucker-Lewis Index (TLI) 0.949 0.956
##
## Robust Comparative Fit Index (CFI) 0.969
## Robust Tucker-Lewis Index (TLI) 0.953
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1131.014 -1131.014
## Scaling correction factor 1.451
## for the MLR correction
## Loglikelihood unrestricted model (H1) -1069.376 -1069.376
## Scaling correction factor 1.286
## for the MLR correction
##
## Akaike (AIC) 2330.028 2330.028
## Bayesian (BIC) 2442.171 2442.171
## Sample-size adjusted Bayesian (BIC) 2334.455 2334.455
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.095 0.084
## 90 Percent confidence interval - lower 0.075 0.065
## 90 Percent confidence interval - upper 0.115 0.103
## P-value RMSEA <= 0.05 0.000 0.002
##
## Robust RMSEA 0.091
## 90 Percent confidence interval - lower 0.069
## 90 Percent confidence interval - upper 0.113
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.040 0.040
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU =~
## x12 1.000 0.437 0.851
## x13 1.092 0.064 17.170 0.000 0.477 0.912
## x14 1.118 0.057 19.735 0.000 0.489 0.957
## ED =~
## x22 1.000 0.608 0.907
## x23 0.896 0.046 19.554 0.000 0.545 0.925
## x24 0.882 0.043 20.286 0.000 0.536 0.926
## POT =~
## x32 1.000 0.765 0.920
## x33 0.919 0.046 19.896 0.000 0.703 0.876
## SKP =~
## y12 1.000 0.450 0.842
## y13 1.209 0.116 10.442 0.000 0.544 0.819
## NKWU =~
## y23 1.000 0.564 0.792
## y24 0.912 0.079 11.559 0.000 0.515 0.824
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## SKP ~
## PKWU 0.351 0.098 3.567 0.000 0.341 0.341
## ED 0.248 0.093 2.663 0.008 0.336 0.336
## POT 0.161 0.061 2.648 0.008 0.274 0.274
## NKWU ~
## PKWU -0.169 0.137 -1.239 0.216 -0.131 -0.131
## ED 0.313 0.140 2.245 0.025 0.338 0.338
## POT 0.102 0.090 1.137 0.255 0.139 0.139
## SKP 0.842 0.264 3.195 0.001 0.671 0.671
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU ~~
## ED 0.203 0.053 3.867 0.000 0.766 0.766
## POT 0.230 0.051 4.528 0.000 0.689 0.689
## ED ~~
## POT 0.375 0.054 6.980 0.000 0.806 0.806
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .x12 0.073 0.012 6.331 0.000 0.073 0.276
## .x13 0.046 0.008 5.730 0.000 0.046 0.168
## .x14 0.022 0.006 3.458 0.001 0.022 0.084
## .x22 0.079 0.015 5.415 0.000 0.079 0.176
## .x23 0.050 0.012 4.128 0.000 0.050 0.144
## .x24 0.048 0.009 5.525 0.000 0.048 0.142
## .x32 0.106 0.025 4.206 0.000 0.106 0.153
## .x33 0.150 0.026 5.666 0.000 0.150 0.233
## .y12 0.083 0.018 4.760 0.000 0.083 0.292
## .y13 0.145 0.028 5.249 0.000 0.145 0.329
## .y23 0.190 0.030 6.400 0.000 0.190 0.373
## .y24 0.126 0.026 4.854 0.000 0.126 0.322
## PKWU 0.191 0.054 3.543 0.000 1.000 1.000
## ED 0.369 0.055 6.681 0.000 1.000 1.000
## POT 0.586 0.065 9.008 0.000 1.000 1.000
## .SKP 0.049 0.013 3.716 0.000 0.243 0.243
## .NKWU 0.012 0.020 0.612 0.541 0.039 0.039standardizedSolution(fit3)semPaths(fit3, what = "paths", whatLabels = "stand", rotation = 3)
lavInspect(fit3, what = "std")## $lambda
## PKWU ED POT SKP NKWU
## x12 0.851 0.000 0.000 0.000 0.000
## x13 0.912 0.000 0.000 0.000 0.000
## x14 0.957 0.000 0.000 0.000 0.000
## x22 0.000 0.907 0.000 0.000 0.000
## x23 0.000 0.925 0.000 0.000 0.000
## x24 0.000 0.926 0.000 0.000 0.000
## x32 0.000 0.000 0.920 0.000 0.000
## x33 0.000 0.000 0.876 0.000 0.000
## y12 0.000 0.000 0.000 0.842 0.000
## y13 0.000 0.000 0.000 0.819 0.000
## y23 0.000 0.000 0.000 0.000 0.792
## y24 0.000 0.000 0.000 0.000 0.824
##
## $theta
## x12 x13 x14 x22 x23 x24 x32 x33 y12 y13 y23 y24
## x12 0.276
## x13 0.000 0.168
## x14 0.000 0.000 0.084
## x22 0.000 0.000 0.000 0.176
## x23 0.000 0.000 0.000 0.000 0.144
## x24 0.000 0.000 0.000 0.000 0.000 0.142
## x32 0.000 0.000 0.000 0.000 0.000 0.000 0.153
## x33 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.233
## y12 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.292
## y13 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.329
## y23 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.373
## y24 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.322
##
## $psi
## PKWU ED POT SKP NKWU
## PKWU 1.000
## ED 0.766 1.000
## POT 0.689 0.806 1.000
## SKP 0.000 0.000 0.000 0.243
## NKWU 0.000 0.000 0.000 0.000 0.039
##
## $beta
## PKWU ED POT SKP NKWU
## PKWU 0.000 0.000 0.000 0.000 0
## ED 0.000 0.000 0.000 0.000 0
## POT 0.000 0.000 0.000 0.000 0
## SKP 0.341 0.336 0.274 0.000 0
## NKWU -0.131 0.338 0.139 0.671 0Reliability Komposit dan Konvergen validity
semTools::reliability(fit3)## PKWU ED POT SKP NKWU
## alpha 0.9315885 0.9393789 0.8923855 0.8049280 0.7851762
## omega 0.9332951 0.9416544 0.8939867 0.8121942 0.7868536
## omega2 0.9332951 0.9416544 0.8939867 0.8121942 0.7868536
## omega3 0.9343787 0.9429270 0.8939861 0.8121939 0.7868533
## avevar 0.8237657 0.8436793 0.8085737 0.6856996 0.6490909semTools::AVE(fit3)## PKWU ED POT SKP NKWU
## 0.824 0.844 0.809 0.686 0.649semTools::compRelSEM(fit3) # composite reliability## PKWU ED POT SKP NKWU
## 0.934 0.943 0.894 0.812 0.787Discriminant Validity
semTools::discriminantValidity(fit3)
htmt(modsem3, dat)Berikut adalah kinerja dari model 3
kinerja_mod3 <- kinerja(fit3)## ukuran koefisien kriteria kesimpulan
## chisq.scaled 106.45 kecil Baik, terpenuhi
## pvalue.scaled 0.00 >= 0.05 Tidak terpenuhi
## df.scaled 44.00 --- ---
## Cmin 2.42 <= 2.00 Tidak terpenuhi
## srmr 0.04 <= 0.08 Baik, terpenuhi
## rmsea.scaled 0.08 <= 0.08 Baik, terpenuhi
## gfi 0.90 >= 0.90 Baik, terpenuhi
## agfi 0.83 >= 0.90 Tidak terpenuhi
## cfi.scaled 0.97 >= 0.90 Baik, terpenuhi
## ifi.scaled 0.97 >= 0.90 Baik, terpenuhi
## nnfi.scaled 0.96 >= 0.90 Baik, terpenuhi
## aic 2330.03 Kecil KecilModel 4
dikeluarkan dari model
modsem4 <- 'PKWU =~ x13 + x14
ED =~ x23 + x24
POT =~ x32 + x33
SKP =~ y12 + y13
NKWU =~ y23 + y24
# Regression
SKP ~ PKWU + ED + POT
NKWU ~ PKWU + ED + POT
NKWU ~ SKP
'
fit4 <- sem(modsem4, data = dat, estimator = "MLR")
summary(fit4, fit.measures = T, standardized = T)## lavaan 0.6-12 ended normally after 69 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 30
##
## Number of observations 200
##
## Model Test User Model:
## Standard Robust
## Test Statistic 69.587 60.052
## Degrees of freedom 25 25
## P-value (Chi-square) 0.000 0.000
## Scaling correction factor 1.159
## Yuan-Bentler correction (Mplus variant)
##
## Model Test Baseline Model:
##
## Test statistic 1814.420 1649.676
## Degrees of freedom 45 45
## P-value 0.000 0.000
## Scaling correction factor 1.100
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.975 0.978
## Tucker-Lewis Index (TLI) 0.955 0.961
##
## Robust Comparative Fit Index (CFI) 0.977
## Robust Tucker-Lewis Index (TLI) 0.959
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1036.229 -1036.229
## Scaling correction factor 1.428
## for the MLR correction
## Loglikelihood unrestricted model (H1) -1001.435 -1001.435
## Scaling correction factor 1.306
## for the MLR correction
##
## Akaike (AIC) 2132.457 2132.457
## Bayesian (BIC) 2231.407 2231.407
## Sample-size adjusted Bayesian (BIC) 2136.364 2136.364
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.094 0.084
## 90 Percent confidence interval - lower 0.068 0.059
## 90 Percent confidence interval - upper 0.121 0.109
## P-value RMSEA <= 0.05 0.004 0.016
##
## Robust RMSEA 0.090
## 90 Percent confidence interval - lower 0.061
## 90 Percent confidence interval - upper 0.120
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.032 0.032
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU =~
## x13 1.000 0.494 0.944
## x14 0.951 0.050 18.859 0.000 0.470 0.920
## ED =~
## x23 1.000 0.543 0.923
## x24 1.005 0.043 23.285 0.000 0.546 0.943
## POT =~
## x32 1.000 0.766 0.921
## x33 0.918 0.046 19.933 0.000 0.703 0.875
## SKP =~
## y12 1.000 0.448 0.837
## y13 1.221 0.118 10.365 0.000 0.546 0.823
## NKWU =~
## y23 1.000 0.570 0.799
## y24 0.895 0.076 11.757 0.000 0.510 0.816
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## SKP ~
## PKWU 0.338 0.099 3.432 0.001 0.373 0.373
## ED 0.236 0.102 2.309 0.021 0.286 0.286
## POT 0.168 0.060 2.824 0.005 0.288 0.288
## NKWU ~
## PKWU -0.149 0.135 -1.103 0.270 -0.130 -0.130
## ED 0.298 0.144 2.064 0.039 0.284 0.284
## POT 0.125 0.088 1.427 0.154 0.169 0.169
## SKP 0.892 0.267 3.336 0.001 0.701 0.701
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU ~~
## ED 0.206 0.051 4.032 0.000 0.769 0.769
## POT 0.273 0.050 5.415 0.000 0.722 0.722
## ED ~~
## POT 0.326 0.054 5.985 0.000 0.783 0.783
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .x13 0.030 0.009 3.426 0.001 0.030 0.109
## .x14 0.040 0.009 4.337 0.000 0.040 0.153
## .x23 0.051 0.013 3.879 0.000 0.051 0.148
## .x24 0.037 0.009 3.916 0.000 0.037 0.110
## .x32 0.105 0.025 4.127 0.000 0.105 0.152
## .x33 0.151 0.026 5.781 0.000 0.151 0.234
## .y12 0.085 0.018 4.870 0.000 0.085 0.299
## .y13 0.142 0.028 5.088 0.000 0.142 0.322
## .y23 0.184 0.029 6.323 0.000 0.184 0.362
## .y24 0.130 0.025 5.127 0.000 0.130 0.334
## PKWU 0.244 0.052 4.726 0.000 1.000 1.000
## ED 0.295 0.056 5.271 0.000 1.000 1.000
## POT 0.586 0.065 8.992 0.000 1.000 1.000
## .SKP 0.050 0.013 3.712 0.000 0.247 0.247
## .NKWU 0.012 0.021 0.591 0.554 0.038 0.038standardizedSolution(fit4)semPaths(fit4, what = "paths", whatLabels = "stand", rotation = 3)
lavInspect(fit4, what = "std")## $lambda
## PKWU ED POT SKP NKWU
## x13 0.944 0.000 0.000 0.000 0.000
## x14 0.920 0.000 0.000 0.000 0.000
## x23 0.000 0.923 0.000 0.000 0.000
## x24 0.000 0.943 0.000 0.000 0.000
## x32 0.000 0.000 0.921 0.000 0.000
## x33 0.000 0.000 0.875 0.000 0.000
## y12 0.000 0.000 0.000 0.837 0.000
## y13 0.000 0.000 0.000 0.823 0.000
## y23 0.000 0.000 0.000 0.000 0.799
## y24 0.000 0.000 0.000 0.000 0.816
##
## $theta
## x13 x14 x23 x24 x32 x33 y12 y13 y23 y24
## x13 0.109
## x14 0.000 0.153
## x23 0.000 0.000 0.148
## x24 0.000 0.000 0.000 0.110
## x32 0.000 0.000 0.000 0.000 0.152
## x33 0.000 0.000 0.000 0.000 0.000 0.234
## y12 0.000 0.000 0.000 0.000 0.000 0.000 0.299
## y13 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.322
## y23 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.362
## y24 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.334
##
## $psi
## PKWU ED POT SKP NKWU
## PKWU 1.000
## ED 0.769 1.000
## POT 0.722 0.783 1.000
## SKP 0.000 0.000 0.000 0.247
## NKWU 0.000 0.000 0.000 0.000 0.038
##
## $beta
## PKWU ED POT SKP NKWU
## PKWU 0.000 0.000 0.000 0.000 0
## ED 0.000 0.000 0.000 0.000 0
## POT 0.000 0.000 0.000 0.000 0
## SKP 0.373 0.286 0.288 0.000 0
## NKWU -0.130 0.284 0.169 0.701 0Reliability Komposit dan Konvergen validity
semTools::reliability(fit4)## PKWU ED POT SKP NKWU
## alpha 0.9296282 0.9309420 0.8923855 0.8049280 0.7851762
## omega 0.9302122 0.9309483 0.8940399 0.8129831 0.7875752
## omega2 0.9302122 0.9309483 0.8940399 0.8129831 0.7875752
## omega3 0.9302123 0.9309484 0.8940397 0.8129831 0.7875751
## avevar 0.8696008 0.8708177 0.8086698 0.6870198 0.6502788semTools::AVE(fit4)## PKWU ED POT SKP NKWU
## 0.870 0.871 0.809 0.687 0.650semTools::compRelSEM(fit4) # composite reliability## PKWU ED POT SKP NKWU
## 0.930 0.931 0.894 0.813 0.788Discriminant Validity
semTools::discriminantValidity(fit4)
htmt(modsem4, dat)Berikut adalah kinerja dari model 4
kinerja_mod4 <- kinerja(fit4)## ukuran koefisien kriteria kesimpulan
## chisq.scaled 60.05 kecil Baik, terpenuhi
## pvalue.scaled 0.00 >= 0.05 Tidak terpenuhi
## df.scaled 25.00 --- ---
## Cmin 2.40 <= 2.00 Tidak terpenuhi
## srmr 0.03 <= 0.08 Baik, terpenuhi
## rmsea.scaled 0.08 <= 0.08 Baik, terpenuhi
## gfi 0.93 >= 0.90 Baik, terpenuhi
## agfi 0.86 >= 0.90 Tidak terpenuhi
## cfi.scaled 0.98 >= 0.90 Baik, terpenuhi
## ifi.scaled 0.98 >= 0.90 Baik, terpenuhi
## nnfi.scaled 0.96 >= 0.90 Baik, terpenuhi
## aic 2132.46 Kecil KecilModel 5
dikeluarkan dari model
modsem5 <- 'PKWU =~ x13 + x14
ED =~ x23 + x24
POT =~ x32 + x33
SKP =~ y12 + y13
NKWU =~ y23 + y24
# Regression
SKP ~ b1*PKWU + b2*ED + b3*POT
NKWU ~ b4*PKWU + b5*ED + b6*POT
NKWU ~ b8*SKP
# indirect effect
PKWU_SKP_NKWU := b1*b8
ED_SKP_NKWU := b2*b8
POT_SKP_NKWU := b3*b8
# total effect
tot_PKWU := b1*b8 + b4
tot_ED := b2*b8 + b5
tot_POT := b3*b8 + b6
'
fit5 <- sem(modsem5, data = dat, estimator = "MLR")
summary(fit5, fit.measures = T, standardized = T)## lavaan 0.6-12 ended normally after 69 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 30
##
## Number of observations 200
##
## Model Test User Model:
## Standard Robust
## Test Statistic 69.587 60.052
## Degrees of freedom 25 25
## P-value (Chi-square) 0.000 0.000
## Scaling correction factor 1.159
## Yuan-Bentler correction (Mplus variant)
##
## Model Test Baseline Model:
##
## Test statistic 1814.420 1649.676
## Degrees of freedom 45 45
## P-value 0.000 0.000
## Scaling correction factor 1.100
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.975 0.978
## Tucker-Lewis Index (TLI) 0.955 0.961
##
## Robust Comparative Fit Index (CFI) 0.977
## Robust Tucker-Lewis Index (TLI) 0.959
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1036.229 -1036.229
## Scaling correction factor 1.428
## for the MLR correction
## Loglikelihood unrestricted model (H1) -1001.435 -1001.435
## Scaling correction factor 1.306
## for the MLR correction
##
## Akaike (AIC) 2132.457 2132.457
## Bayesian (BIC) 2231.407 2231.407
## Sample-size adjusted Bayesian (BIC) 2136.364 2136.364
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.094 0.084
## 90 Percent confidence interval - lower 0.068 0.059
## 90 Percent confidence interval - upper 0.121 0.109
## P-value RMSEA <= 0.05 0.004 0.016
##
## Robust RMSEA 0.090
## 90 Percent confidence interval - lower 0.061
## 90 Percent confidence interval - upper 0.120
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.032 0.032
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU =~
## x13 1.000 0.494 0.944
## x14 0.951 0.050 18.859 0.000 0.470 0.920
## ED =~
## x23 1.000 0.543 0.923
## x24 1.005 0.043 23.285 0.000 0.546 0.943
## POT =~
## x32 1.000 0.766 0.921
## x33 0.918 0.046 19.933 0.000 0.703 0.875
## SKP =~
## y12 1.000 0.448 0.837
## y13 1.221 0.118 10.365 0.000 0.546 0.823
## NKWU =~
## y23 1.000 0.570 0.799
## y24 0.895 0.076 11.757 0.000 0.510 0.816
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## SKP ~
## PKWU (b1) 0.338 0.099 3.432 0.001 0.373 0.373
## ED (b2) 0.236 0.102 2.309 0.021 0.286 0.286
## POT (b3) 0.168 0.060 2.824 0.005 0.288 0.288
## NKWU ~
## PKWU (b4) -0.149 0.135 -1.103 0.270 -0.130 -0.130
## ED (b5) 0.298 0.144 2.064 0.039 0.284 0.284
## POT (b6) 0.125 0.088 1.427 0.154 0.169 0.169
## SKP (b8) 0.892 0.267 3.336 0.001 0.701 0.701
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU ~~
## ED 0.206 0.051 4.032 0.000 0.769 0.769
## POT 0.273 0.050 5.415 0.000 0.722 0.722
## ED ~~
## POT 0.326 0.054 5.985 0.000 0.783 0.783
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .x13 0.030 0.009 3.426 0.001 0.030 0.109
## .x14 0.040 0.009 4.337 0.000 0.040 0.153
## .x23 0.051 0.013 3.879 0.000 0.051 0.148
## .x24 0.037 0.009 3.916 0.000 0.037 0.110
## .x32 0.105 0.025 4.127 0.000 0.105 0.152
## .x33 0.151 0.026 5.781 0.000 0.151 0.234
## .y12 0.085 0.018 4.870 0.000 0.085 0.299
## .y13 0.142 0.028 5.088 0.000 0.142 0.322
## .y23 0.184 0.029 6.323 0.000 0.184 0.362
## .y24 0.130 0.025 5.127 0.000 0.130 0.334
## PKWU 0.244 0.052 4.726 0.000 1.000 1.000
## ED 0.295 0.056 5.271 0.000 1.000 1.000
## POT 0.586 0.065 8.992 0.000 1.000 1.000
## .SKP 0.050 0.013 3.712 0.000 0.247 0.247
## .NKWU 0.012 0.021 0.591 0.554 0.038 0.038
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## PKWU_SKP_NKWU 0.302 0.127 2.375 0.018 0.262 0.262
## ED_SKP_NKWU 0.210 0.101 2.073 0.038 0.201 0.201
## POT_SKP_NKWU 0.150 0.074 2.036 0.042 0.202 0.202
## tot_PKWU 0.152 0.116 1.312 0.189 0.132 0.132
## tot_ED 0.508 0.136 3.750 0.000 0.485 0.485
## tot_POT 0.276 0.081 3.396 0.001 0.371 0.371standardizedSolution(fit5)semPaths(fit5, what = "paths", whatLabels = "stand", rotation = 3)
lavInspect(fit5, what = "std")## $lambda
## PKWU ED POT SKP NKWU
## x13 0.944 0.000 0.000 0.000 0.000
## x14 0.920 0.000 0.000 0.000 0.000
## x23 0.000 0.923 0.000 0.000 0.000
## x24 0.000 0.943 0.000 0.000 0.000
## x32 0.000 0.000 0.921 0.000 0.000
## x33 0.000 0.000 0.875 0.000 0.000
## y12 0.000 0.000 0.000 0.837 0.000
## y13 0.000 0.000 0.000 0.823 0.000
## y23 0.000 0.000 0.000 0.000 0.799
## y24 0.000 0.000 0.000 0.000 0.816
##
## $theta
## x13 x14 x23 x24 x32 x33 y12 y13 y23 y24
## x13 0.109
## x14 0.000 0.153
## x23 0.000 0.000 0.148
## x24 0.000 0.000 0.000 0.110
## x32 0.000 0.000 0.000 0.000 0.152
## x33 0.000 0.000 0.000 0.000 0.000 0.234
## y12 0.000 0.000 0.000 0.000 0.000 0.000 0.299
## y13 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.322
## y23 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.362
## y24 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.334
##
## $psi
## PKWU ED POT SKP NKWU
## PKWU 1.000
## ED 0.769 1.000
## POT 0.722 0.783 1.000
## SKP 0.000 0.000 0.000 0.247
## NKWU 0.000 0.000 0.000 0.000 0.038
##
## $beta
## PKWU ED POT SKP NKWU
## PKWU 0.000 0.000 0.000 0.000 0
## ED 0.000 0.000 0.000 0.000 0
## POT 0.000 0.000 0.000 0.000 0
## SKP 0.373 0.286 0.288 0.000 0
## NKWU -0.130 0.284 0.169 0.701 0Reliability Komposit dan Konvergen validity
semTools::reliability(fit5)## PKWU ED POT SKP NKWU
## alpha 0.9296282 0.9309420 0.8923855 0.8049280 0.7851762
## omega 0.9302122 0.9309483 0.8940399 0.8129831 0.7875752
## omega2 0.9302122 0.9309483 0.8940399 0.8129831 0.7875752
## omega3 0.9302123 0.9309484 0.8940397 0.8129831 0.7875751
## avevar 0.8696008 0.8708177 0.8086698 0.6870198 0.6502788semTools::AVE(fit5)## PKWU ED POT SKP NKWU
## 0.870 0.871 0.809 0.687 0.650semTools::compRelSEM(fit5) # composite reliability## PKWU ED POT SKP NKWU
## 0.930 0.931 0.894 0.813 0.788Discriminant Validity
semTools::discriminantValidity(fit5)
htmt(modsem5, dat)Berikut adalah kinerja dari model 5
kinerja_mod5 <- kinerja(fit5)## ukuran koefisien kriteria kesimpulan
## chisq.scaled 60.05 kecil Baik, terpenuhi
## pvalue.scaled 0.00 >= 0.05 Tidak terpenuhi
## df.scaled 25.00 --- ---
## Cmin 2.40 <= 2.00 Tidak terpenuhi
## srmr 0.03 <= 0.08 Baik, terpenuhi
## rmsea.scaled 0.08 <= 0.08 Baik, terpenuhi
## gfi 0.93 >= 0.90 Baik, terpenuhi
## agfi 0.86 >= 0.90 Tidak terpenuhi
## cfi.scaled 0.98 >= 0.90 Baik, terpenuhi
## ifi.scaled 0.98 >= 0.90 Baik, terpenuhi
## nnfi.scaled 0.96 >= 0.90 Baik, terpenuhi
## aic 2132.46 Kecil Kecil