Analisis Pengaruh Faktor Sosial Ekonomi terhadap Stabilitas Karir Karyawan Menggunakan Structural Equation Modeling (SEM) pada Data IBM HR Analytics
Luthfiana Syakira Eka Ramadani (24031554071), Oktavia M Lumban Batu (24031554147), Sabrina Miftakhul Jana (24031554148)
2026-05-23
Import Library
library(lavaan)## Warning: package 'lavaan' was built under R version 4.5.3## This is lavaan 0.6-21
## lavaan is FREE software! Please report any bugs.library(semPlot)## Warning: package 'semPlot' was built under R version 4.5.3library(psych)## Warning: package 'psych' was built under R version 4.5.3##
## Attaching package: 'psych'## The following object is masked from 'package:lavaan':
##
## cor2covlibrary(car)## Warning: package 'car' was built under R version 4.5.3## Loading required package: carData## Warning: package 'carData' was built under R version 4.5.3## Registered S3 method overwritten by 'car':
## method from
## na.action.merMod lme4##
## Attaching package: 'car'## The following object is masked from 'package:psych':
##
## logitlibrary(dplyr)## Warning: package 'dplyr' was built under R version 4.5.3##
## Attaching package: 'dplyr'## The following object is masked from 'package:car':
##
## recode## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(semTools)## Warning: package 'semTools' was built under R version 4.5.3## ## ################################################################################# This is semTools 0.5-8## All users of R (or SEM) are invited to submit functions or ideas for functions.## #################################################################################
## Attaching package: 'semTools'## The following objects are masked from 'package:psych':
##
## reliability, skew1. Import dan Cek Struktur Data
data <- read.csv("C:/Users/Lenovo/Downloads/WA_Fn-UseC_-HR-Employee-Attrition (1).csv")
dim(data)## [1] 1470 35str(data)## 'data.frame': 1470 obs. of 35 variables:
## $ Age : int 41 49 37 33 27 32 59 30 38 36 ...
## $ Attrition : chr "Yes" "No" "Yes" "No" ...
## $ BusinessTravel : chr "Travel_Rarely" "Travel_Frequently" "Travel_Rarely" "Travel_Frequently" ...
## $ DailyRate : int 1102 279 1373 1392 591 1005 1324 1358 216 1299 ...
## $ Department : chr "Sales" "Research & Development" "Research & Development" "Research & Development" ...
## $ DistanceFromHome : int 1 8 2 3 2 2 3 24 23 27 ...
## $ Education : int 2 1 2 4 1 2 3 1 3 3 ...
## $ EducationField : chr "Life Sciences" "Life Sciences" "Other" "Life Sciences" ...
## $ EmployeeCount : int 1 1 1 1 1 1 1 1 1 1 ...
## $ EmployeeNumber : int 1 2 4 5 7 8 10 11 12 13 ...
## $ EnvironmentSatisfaction : int 2 3 4 4 1 4 3 4 4 3 ...
## $ Gender : chr "Female" "Male" "Male" "Female" ...
## $ HourlyRate : int 94 61 92 56 40 79 81 67 44 94 ...
## $ JobInvolvement : int 3 2 2 3 3 3 4 3 2 3 ...
## $ JobLevel : int 2 2 1 1 1 1 1 1 3 2 ...
## $ JobRole : chr "Sales Executive" "Research Scientist" "Laboratory Technician" "Research Scientist" ...
## $ JobSatisfaction : int 4 2 3 3 2 4 1 3 3 3 ...
## $ MaritalStatus : chr "Single" "Married" "Single" "Married" ...
## $ MonthlyIncome : int 5993 5130 2090 2909 3468 3068 2670 2693 9526 5237 ...
## $ MonthlyRate : int 19479 24907 2396 23159 16632 11864 9964 13335 8787 16577 ...
## $ NumCompaniesWorked : int 8 1 6 1 9 0 4 1 0 6 ...
## $ Over18 : chr "Y" "Y" "Y" "Y" ...
## $ OverTime : chr "Yes" "No" "Yes" "Yes" ...
## $ PercentSalaryHike : int 11 23 15 11 12 13 20 22 21 13 ...
## $ PerformanceRating : int 3 4 3 3 3 3 4 4 4 3 ...
## $ RelationshipSatisfaction: int 1 4 2 3 4 3 1 2 2 2 ...
## $ StandardHours : int 80 80 80 80 80 80 80 80 80 80 ...
## $ StockOptionLevel : int 0 1 0 0 1 0 3 1 0 2 ...
## $ TotalWorkingYears : int 8 10 7 8 6 8 12 1 10 17 ...
## $ TrainingTimesLastYear : int 0 3 3 3 3 2 3 2 2 3 ...
## $ WorkLifeBalance : int 1 3 3 3 3 2 2 3 3 2 ...
## $ YearsAtCompany : int 6 10 0 8 2 7 1 1 9 7 ...
## $ YearsInCurrentRole : int 4 7 0 7 2 7 0 0 7 7 ...
## $ YearsSinceLastPromotion : int 0 1 0 3 2 3 0 0 1 7 ...
## $ YearsWithCurrManager : int 5 7 0 0 2 6 0 0 8 7 ...head(data, 5)## Age Attrition BusinessTravel DailyRate Department
## 1 41 Yes Travel_Rarely 1102 Sales
## 2 49 No Travel_Frequently 279 Research & Development
## 3 37 Yes Travel_Rarely 1373 Research & Development
## 4 33 No Travel_Frequently 1392 Research & Development
## 5 27 No Travel_Rarely 591 Research & Development
## DistanceFromHome Education EducationField EmployeeCount EmployeeNumber
## 1 1 2 Life Sciences 1 1
## 2 8 1 Life Sciences 1 2
## 3 2 2 Other 1 4
## 4 3 4 Life Sciences 1 5
## 5 2 1 Medical 1 7
## EnvironmentSatisfaction Gender HourlyRate JobInvolvement JobLevel
## 1 2 Female 94 3 2
## 2 3 Male 61 2 2
## 3 4 Male 92 2 1
## 4 4 Female 56 3 1
## 5 1 Male 40 3 1
## JobRole JobSatisfaction MaritalStatus MonthlyIncome MonthlyRate
## 1 Sales Executive 4 Single 5993 19479
## 2 Research Scientist 2 Married 5130 24907
## 3 Laboratory Technician 3 Single 2090 2396
## 4 Research Scientist 3 Married 2909 23159
## 5 Laboratory Technician 2 Married 3468 16632
## NumCompaniesWorked Over18 OverTime PercentSalaryHike PerformanceRating
## 1 8 Y Yes 11 3
## 2 1 Y No 23 4
## 3 6 Y Yes 15 3
## 4 1 Y Yes 11 3
## 5 9 Y No 12 3
## RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears
## 1 1 80 0 8
## 2 4 80 1 10
## 3 2 80 0 7
## 4 3 80 0 8
## 5 4 80 1 6
## TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole
## 1 0 1 6 4
## 2 3 3 10 7
## 3 3 3 0 0
## 4 3 3 8 7
## 5 3 3 2 2
## YearsSinceLastPromotion YearsWithCurrManager
## 1 0 5
## 2 1 7
## 3 0 0
## 4 3 0
## 5 2 2names(data)## [1] "Age" "Attrition"
## [3] "BusinessTravel" "DailyRate"
## [5] "Department" "DistanceFromHome"
## [7] "Education" "EducationField"
## [9] "EmployeeCount" "EmployeeNumber"
## [11] "EnvironmentSatisfaction" "Gender"
## [13] "HourlyRate" "JobInvolvement"
## [15] "JobLevel" "JobRole"
## [17] "JobSatisfaction" "MaritalStatus"
## [19] "MonthlyIncome" "MonthlyRate"
## [21] "NumCompaniesWorked" "Over18"
## [23] "OverTime" "PercentSalaryHike"
## [25] "PerformanceRating" "RelationshipSatisfaction"
## [27] "StandardHours" "StockOptionLevel"
## [29] "TotalWorkingYears" "TrainingTimesLastYear"
## [31] "WorkLifeBalance" "YearsAtCompany"
## [33] "YearsInCurrentRole" "YearsSinceLastPromotion"
## [35] "YearsWithCurrManager"2. Seleksi Variabel
data_selected <- data %>%
select(
MonthlyIncome, JobLevel, TotalWorkingYears,
YearsAtCompany, YearsInCurrentRole,
YearsSinceLastPromotion, YearsWithCurrManager
)
str(data_selected)## 'data.frame': 1470 obs. of 7 variables:
## $ MonthlyIncome : int 5993 5130 2090 2909 3468 3068 2670 2693 9526 5237 ...
## $ JobLevel : int 2 2 1 1 1 1 1 1 3 2 ...
## $ TotalWorkingYears : int 8 10 7 8 6 8 12 1 10 17 ...
## $ YearsAtCompany : int 6 10 0 8 2 7 1 1 9 7 ...
## $ YearsInCurrentRole : int 4 7 0 7 2 7 0 0 7 7 ...
## $ YearsSinceLastPromotion: int 0 1 0 3 2 3 0 0 1 7 ...
## $ YearsWithCurrManager : int 5 7 0 0 2 6 0 0 8 7 ...dim(data_selected)## [1] 1470 73. Pre-Processing
3.1 Cek Missing Value dan Duplikasi
sum(is.na(data_selected))## [1] 0colMeans(is.na(data_selected)) * 100## MonthlyIncome JobLevel TotalWorkingYears
## 0 0 0
## YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion
## 0 0 0
## YearsWithCurrManager
## 0duplikat <- data_selected[duplicated(data_selected), ]
nrow(duplikat)## [1] 23.2 Konversi ke Numerik
data_numeric <- data_selected
for (col in colnames(data_numeric)) {
if (!is.numeric(data_numeric[[col]])) {
data_numeric[[col]] <- as.numeric(as.factor(data_numeric[[col]]))
}
}
str(data_numeric)## 'data.frame': 1470 obs. of 7 variables:
## $ MonthlyIncome : int 5993 5130 2090 2909 3468 3068 2670 2693 9526 5237 ...
## $ JobLevel : int 2 2 1 1 1 1 1 1 3 2 ...
## $ TotalWorkingYears : int 8 10 7 8 6 8 12 1 10 17 ...
## $ YearsAtCompany : int 6 10 0 8 2 7 1 1 9 7 ...
## $ YearsInCurrentRole : int 4 7 0 7 2 7 0 0 7 7 ...
## $ YearsSinceLastPromotion: int 0 1 0 3 2 3 0 0 1 7 ...
## $ YearsWithCurrManager : int 5 7 0 0 2 6 0 0 8 7 ...4. Statistika Deskriptif
summary(data_numeric)## MonthlyIncome JobLevel TotalWorkingYears YearsAtCompany
## Min. : 1009 Min. :1.000 Min. : 0.00 Min. : 0.000
## 1st Qu.: 2911 1st Qu.:1.000 1st Qu.: 6.00 1st Qu.: 3.000
## Median : 4919 Median :2.000 Median :10.00 Median : 5.000
## Mean : 6503 Mean :2.064 Mean :11.28 Mean : 7.008
## 3rd Qu.: 8379 3rd Qu.:3.000 3rd Qu.:15.00 3rd Qu.: 9.000
## Max. :19999 Max. :5.000 Max. :40.00 Max. :40.000
## YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
## Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.: 2.000 1st Qu.: 0.000 1st Qu.: 2.000
## Median : 3.000 Median : 1.000 Median : 3.000
## Mean : 4.229 Mean : 2.188 Mean : 4.123
## 3rd Qu.: 7.000 3rd Qu.: 3.000 3rd Qu.: 7.000
## Max. :18.000 Max. :15.000 Max. :17.000describe(data_numeric)## vars n mean sd median trimmed mad min
## MonthlyIncome 1 1470 6502.93 4707.96 4919 5667.24 3260.24 1009
## JobLevel 2 1470 2.06 1.11 2 1.90 1.48 1
## TotalWorkingYears 3 1470 11.28 7.78 10 10.37 5.93 0
## YearsAtCompany 4 1470 7.01 6.13 5 5.99 4.45 0
## YearsInCurrentRole 5 1470 4.23 3.62 3 3.85 4.45 0
## YearsSinceLastPromotion 6 1470 2.19 3.22 1 1.48 1.48 0
## YearsWithCurrManager 7 1470 4.12 3.57 3 3.77 4.45 0
## max range skew kurtosis se
## MonthlyIncome 19999 18990 1.37 0.99 122.79
## JobLevel 5 4 1.02 0.39 0.03
## TotalWorkingYears 40 40 1.11 0.91 0.20
## YearsAtCompany 40 40 1.76 3.91 0.16
## YearsInCurrentRole 18 18 0.92 0.47 0.09
## YearsSinceLastPromotion 15 15 1.98 3.59 0.08
## YearsWithCurrManager 17 17 0.83 0.16 0.09Hasil statistik deskriptif menunjukkan bahwa variabel MonthlyIncome memiliki rata-rata sebesar 6502.93 dengan standar deviasi sebesar 4707.96, yang menunjukkan adanya variasi pendapatan yang cukup besar antar karyawan. Variabel TotalWorkingYears memiliki rata-rata pengalaman kerja sebesar 11.28 tahun, sedangkan YearsAtCompany memiliki rata-rata masa kerja sebesar 7.01 tahun. Variabel YearsSinceLastPromotion memiliki rata-rata sebesar 2.19 tahun, yang menunjukkan sebagian besar karyawan belum lama memperoleh promosi jabatan.
5. Normalisasi Z-Score
data_z <- as.data.frame(lapply(data_numeric, function(x) {
if (is.numeric(x)) (x - mean(x, na.rm = TRUE)) / sd(x, na.rm = TRUE)
else x
}))
head(data_z)## MonthlyIncome JobLevel TotalWorkingYears YearsAtCompany YearsInCurrentRole
## 1 -0.1083127 -0.05776789 -0.4214990 -0.164557109 -0.06327437
## 2 -0.2916193 -0.05776789 -0.1644554 0.488341541 0.76473737
## 3 -0.9373347 -0.96115930 -0.5500208 -1.143905083 -1.16729002
## 4 -0.7633739 -0.96115930 -0.4214990 0.161892216 0.76473737
## 5 -0.6446387 -0.96115930 -0.6785426 -0.817455758 -0.61528219
## 6 -0.7296013 -0.96115930 -0.4214990 -0.001332446 0.76473737
## YearsSinceLastPromotion YearsWithCurrManager
## 1 -0.67891464 0.2457504
## 2 -0.36858985 0.8062671
## 3 -0.67891464 -1.1555415
## 4 0.25205973 -1.1555415
## 5 -0.05826506 -0.5950247
## 6 0.25205973 0.5260087round(colMeans(data_z), 4)## MonthlyIncome JobLevel TotalWorkingYears
## 0 0 0
## YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion
## 0 0 0
## YearsWithCurrManager
## 06. Visualisasi Distribusi Data
par(mfrow = c(2, 4), mar = c(4, 4, 2, 1))
for (col in colnames(data_z)) {
hist(data_z[[col]], main = col, xlab = col,
col = "darkblue", border = "white")
}
par(mfrow = c(1, 1))
Berdasarkan histogram distribusi data, sebagian besar variabel memiliki pola distribusi yang cukup baik. Namun, beberapa variabel seperti MonthlyIncome, YearsAtCompany, dan YearsSinceLastPromotion terlihat cenderung skewed ke kanan, yang menunjukkan adanya beberapa karyawan dengan nilai jauh lebih tinggi dibandingkan mayoritas responden.
7. Uji Asumsi
7.1 Uji Normalitas Multivariat
mardia(data_z)
## Call: mardia(x = data_z)
##
## Mardia tests of multivariate skew and kurtosis
## Use describe(x) the to get univariate tests
## n.obs = 1470 num.vars = 7
## b1p = 28.83 skew = 7062.76 with probability <= 0
## small sample skew = 7080.78 with probability <= 0
## b2p = 110.28 kurtosis = 80.74 with probability <= 0Hasil uji normalitas multivariat menggunakan Mardia menunjukkan nilai skew sebesar 7062.76 dan kurtosis sebesar 80.74 dengan probabilitas ≤ 0.05. Hal ini menunjukkan bahwa data belum memenuhi asumsi normalitas multivariat secara sempurna. Namun, karena jumlah sampel penelitian cukup besar yaitu 1470 observasi, analisis SEM masih dapat dilakukan.
7.2 KMO
r <- cor(data_z)
KMO(r)## Kaiser-Meyer-Olkin factor adequacy
## Call: KMO(r = r)
## Overall MSA = 0.83
## MSA for each item =
## MonthlyIncome JobLevel TotalWorkingYears
## 0.73 0.73 0.95
## YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion
## 0.84 0.88 0.93
## YearsWithCurrManager
## 0.86Hasil uji KMO memperoleh nilai Overall MSA sebesar 0.83. Karena nilai KMO lebih besar dari 0.50, maka data dinyatakan layak dan memadai untuk dilakukan analisis faktor. Nilai MSA masing-masing variabel juga berada di atas 0.50, sehingga seluruh indikator dapat digunakan dalam analisis lanjutan.
7.3 Uji Multikolinearitas (VIF)
data_vif <- na.omit(data_z)
model_vif <- lm(YearsAtCompany ~ MonthlyIncome + JobLevel +
TotalWorkingYears + YearsInCurrentRole +
YearsSinceLastPromotion + YearsWithCurrManager,
data = data_vif)
vif(model_vif)## MonthlyIncome JobLevel TotalWorkingYears
## 10.670736 11.067071 2.946665
## YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
## 2.310836 1.541154 2.208788Hasil uji multikolinearitas menunjukkan bahwa sebagian besar variabel memiliki nilai VIF di bawah 10, sehingga tidak terjadi multikolinearitas yang serius. Namun, variabel MonthlyIncome memiliki nilai VIF sebesar 10.67 dan JobLevel sebesar 11.07, yang menunjukkan adanya hubungan yang cukup kuat antara kedua variabel tersebut.
8. Confirmatory Factor Analysis (CFA) per Konstruk
8.1 CFA X Faktor Sosial Ekonomi Karyawan
model_cfa_x <- '
SosialEkonomi =~ MonthlyIncome + JobLevel + TotalWorkingYears
'
fit_x <- cfa(model_cfa_x, data = data_z, std.lv = TRUE)
summary(fit_x, fit.measures = TRUE, standardized = TRUE)## lavaan 0.6-21 ended normally after 30 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 6
##
## Number of observations 1470
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 4856.332
## 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) -3827.853
## Loglikelihood unrestricted model (H1) -3827.853
##
## Akaike (AIC) 7667.705
## Bayesian (BIC) 7699.463
## Sample-size adjusted Bayesian (SABIC) 7680.403
##
## 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 H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 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|) Std.lv Std.all
## SosialEkonomi =~
## MonthlyIncome 0.969 0.019 50.317 0.000 0.969 0.969
## JobLevel 0.980 0.019 51.447 0.000 0.980 0.981
## TotalWorkngYrs 0.797 0.022 36.766 0.000 0.797 0.798
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .MonthlyIncome 0.061 0.007 9.355 0.000 0.061 0.061
## .JobLevel 0.038 0.006 5.951 0.000 0.038 0.038
## .TotalWorkngYrs 0.364 0.014 25.902 0.000 0.364 0.364
## SosialEkonomi 1.000 1.000 1.000Hasil CFA pada konstruk SosialEkonomi menunjukkan bahwa seluruh indikator memiliki loading factor yang tinggi, yaitu MonthlyIncome sebesar 0.969, JobLevel sebesar 0.981, dan TotalWorkingYears sebesar 0.798. Seluruh nilai loading factor berada di atas 0.50 sehingga seluruh indikator dinyatakan valid dalam merepresentasikan konstruk SosialEkonomi.
8.2 CFA Y Stabilitas Karir Karyawan
model_cfa_y <- '
StabilitasKarir =~ YearsAtCompany + YearsInCurrentRole +
YearsSinceLastPromotion + YearsWithCurrManager
'
fit_y <- cfa(model_cfa_y, data = data_z, std.lv = TRUE)
summary(fit_y, fit.measures = TRUE, standardized = TRUE)## lavaan 0.6-21 ended normally after 20 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 8
##
## Number of observations 1470
##
## Model Test User Model:
##
## Test statistic 23.305
## Degrees of freedom 2
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 3474.113
## Degrees of freedom 6
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.994
## Tucker-Lewis Index (TLI) 0.982
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -6615.954
## Loglikelihood unrestricted model (H1) -6604.301
##
## Akaike (AIC) 13247.908
## Bayesian (BIC) 13290.252
## Sample-size adjusted Bayesian (SABIC) 13264.838
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.085
## 90 Percent confidence interval - lower 0.056
## 90 Percent confidence interval - upper 0.118
## P-value H_0: RMSEA <= 0.050 0.024
## P-value H_0: RMSEA >= 0.080 0.648
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.014
##
## 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
## StabilitasKarir =~
## YearsAtCompany 0.918 0.021 44.275 0.000 0.918 0.918
## YearsInCrrntRl 0.835 0.022 38.239 0.000 0.835 0.835
## YrsSncLstPrmtn 0.654 0.024 27.262 0.000 0.654 0.655
## YersWthCrrMngr 0.837 0.022 38.428 0.000 0.837 0.838
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .YearsAtCompany 0.157 0.012 12.595 0.000 0.157 0.157
## .YearsInCrrntRl 0.303 0.015 20.526 0.000 0.303 0.303
## .YrsSncLstPrmtn 0.571 0.023 25.152 0.000 0.571 0.572
## .YersWthCrrMngr 0.298 0.015 20.356 0.000 0.298 0.298
## StabilitasKarr 1.000 1.000 1.000Hasil CFA pada konstruk StabilitasKarir menunjukkan bahwa indikator YearsAtCompany memiliki loading factor sebesar 0.918, YearsInCurrentRole sebesar 0.835, YearsSinceLastPromotion sebesar 0.655, dan YearsWithCurrManager sebesar 0.838. Seluruh indikator memiliki nilai loading factor di atas 0.50 sehingga dinyatakan valid dalam membentuk konstruk StabilitasKarir.
9. Visualisasi CFA
9.1 Visualisasi CFA X
semPaths(fit_x,
what = "path", whatLabels = "std",
style = "ram", layout = "tree", rotation = 2,
sizeMan = 7, sizeLat = 9,
edge.label.cex = 1.2, label.cex = 1.1,
color = list(lat = "darkblue", man = "lightyellow"))
Visualisasi CFA pada konstruk SosialEkonomi menunjukkan bahwa seluruh indikator memiliki hubungan yang kuat dengan konstruk laten. Indikator JobLevel memiliki kontribusi terbesar terhadap konstruk SosialEkonomi karena memiliki loading factor tertinggi yaitu sebesar 0.981.
9.2 Visualisasi CFA Y
semPaths(fit_y,
what = "path", whatLabels = "std",
style = "ram", layout = "tree", rotation = 2,
sizeMan = 7, sizeLat = 9,
edge.label.cex = 1.2, label.cex = 1.1,
color = list(lat = "darkgreen", man = "lightyellow"))
Visualisasi CFA pada konstruk StabilitasKarir menunjukkan bahwa indikator YearsAtCompany memiliki kontribusi paling besar terhadap konstruk laten dengan loading factor sebesar 0.918. Hal ini menunjukkan bahwa lama bekerja di perusahaan menjadi indikator utama dalam membentuk stabilitas karir karyawan.
10. Fit Indeks CFA
cfa_fits <- data.frame(
Konstruk = c("SosialEkonomi (x)", "StabilitasKarir (Y)"),
CFI = c(fitMeasures(fit_x, "cfi"),
fitMeasures(fit_y, "cfi")),
TLI = c(fitMeasures(fit_x, "tli"),
fitMeasures(fit_y, "tli")),
RMSEA = c(fitMeasures(fit_x, "rmsea"),
fitMeasures(fit_y, "rmsea")),
SRMR = c(fitMeasures(fit_x, "srmr"),
fitMeasures(fit_y, "srmr")),
ChiSquare = c(fitMeasures(fit_x, "chisq"),
fitMeasures(fit_y, "chisq")),
p_value = c(fitMeasures(fit_x, "pvalue"),
fitMeasures(fit_y, "pvalue"))
)
cfa_fits[, -1] <- round(cfa_fits[, -1], 4)
print(cfa_fits)## Konstruk CFI TLI RMSEA SRMR ChiSquare p_value
## 1 SosialEkonomi (x) 1.0000 1.0000 0.0000 0.0000 0.0000 NA
## 2 StabilitasKarir (Y) 0.9939 0.9816 0.0851 0.0143 23.3048 0Hasil evaluasi fit indeks menunjukkan bahwa konstruk SosialEkonomi memiliki nilai CFI dan TLI sebesar 1.000 serta RMSEA dan SRMR sebesar 0.000, yang menunjukkan model memiliki kecocokan yang sangat baik. Sementara itu, konstruk StabilitasKarir memiliki nilai CFI sebesar 0.994 dan TLI sebesar 0.982 yang menunjukkan model sudah baik, meskipun nilai RMSEA sebesar 0.085 sedikit berada di atas batas ideal 0.08.
11. Evaluasi Outer Model
11.1 AVE dan CR
hitung_AVE <- function(fit) {
std <- standardizedSolution(fit)
lambda <- std$est[std$op == "=~"]
AVE <- sum(lambda^2) / length(lambda)
return(round(AVE, 4))
}
hitung_CR <- function(fit) {
std <- standardizedSolution(fit)
lambda <- std$est[std$op == "=~"]
theta <- 1 - lambda^2
CR <- sum(lambda)^2 / (sum(lambda)^2 + sum(theta))
return(round(CR, 4))
}Hasil evaluasi outer model menunjukkan bahwa konstruk SosialEkonomi memiliki nilai AVE sebesar 0.8456 dan CR sebesar 0.9422, sedangkan konstruk StabilitasKarir memiliki nilai AVE sebesar 0.6674 dan CR sebesar 0.8878. Karena seluruh nilai AVE > 0.50 dan CR > 0.70, maka kedua konstruk dinyatakan valid dan reliabel.
11.2 Tabel AVE dan CR
hasil_validitas <- data.frame(
Konstruk = c("SosialEkonomi (X)", "StabilitasKarir (Y)"),
AVE = c(hitung_AVE(fit_x), hitung_AVE(fit_y)),
CR = c(hitung_CR(fit_x), hitung_CR(fit_y))
)
print(hasil_validitas)## Konstruk AVE CR
## 1 SosialEkonomi (X) 0.8456 0.9422
## 2 StabilitasKarir (Y) 0.6674 0.8878Hasil uji reliabilitas menunjukkan bahwa konstruk SosialEkonomi memiliki nilai Cronbach Alpha sebesar 0.938 dan StabilitasKarir sebesar 0.883. Nilai tersebut berada di atas 0.70 sehingga kedua konstruk memiliki tingkat reliabilitas yang sangat baik.
11.3 Cronbach Alpha
reliability(fit_x)## Warning in reliability(fit_x):
## The reliability() function was deprecated in 2022 and will cease to be included in future versions of semTools. See help('semTools-deprecated) for details.
##
## It is replaced by the compRelSEM() function, which can estimate alpha and model-based reliability in an even wider variety of models and data types, with greater control in specifying the desired type of reliability coefficient (i.e., more explicitly choosing assumptions).
##
## The average variance extracted should never have been included because it is not a reliability coefficient. It is now available from the AVE() function.## SosialEkonomi
## alpha 0.9382585
## omega 0.9421928
## omega2 0.9421928
## omega3 0.9421928
## avevar 0.8456392reliability(fit_y)## Warning in reliability(fit_y):
## The reliability() function was deprecated in 2022 and will cease to be included in future versions of semTools. See help('semTools-deprecated) for details.
##
## It is replaced by the compRelSEM() function, which can estimate alpha and model-based reliability in an even wider variety of models and data types, with greater control in specifying the desired type of reliability coefficient (i.e., more explicitly choosing assumptions).
##
## The average variance extracted should never have been included because it is not a reliability coefficient. It is now available from the AVE() function.## StabilitasKarir
## alpha 0.8828083
## omega 0.8878276
## omega2 0.8878276
## omega3 0.8894817
## avevar 0.6674061Hasil validitas diskriminan menggunakan HTMT menunjukkan nilai sebesar 0.578. Karena nilai HTMT berada di bawah 0.90, maka kedua konstruk dapat dibedakan dengan baik dan memenuhi validitas diskriminan.
11.4 Validitas Diskriminan
model_cfa_gabungan <- '
SosialEkonomi =~ MonthlyIncome + JobLevel + TotalWorkingYears
StabilitasKarir =~ YearsAtCompany + YearsInCurrentRole +
YearsSinceLastPromotion + YearsWithCurrManager
'
fit_gabungan <- cfa(model_cfa_gabungan, data = data_z, std.lv = TRUE)
summary(fit_gabungan, fit.measures = TRUE, standardized = TRUE)## lavaan 0.6-21 ended normally after 27 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 15
##
## Number of observations 1470
##
## Model Test User Model:
##
## Test statistic 346.688
## Degrees of freedom 13
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 9105.958
## Degrees of freedom 21
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.963
## Tucker-Lewis Index (TLI) 0.941
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -10217.741
## Loglikelihood unrestricted model (H1) -10044.398
##
## Akaike (AIC) 20465.483
## Bayesian (BIC) 20544.878
## Sample-size adjusted Bayesian (SABIC) 20497.228
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.132
## 90 Percent confidence interval - lower 0.120
## 90 Percent confidence interval - upper 0.144
## P-value H_0: RMSEA <= 0.050 0.000
## P-value H_0: RMSEA >= 0.080 1.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.061
##
## 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
## SosialEkonomi =~
## MonthlyIncome 0.967 0.019 50.295 0.000 0.967 0.968
## JobLevel 0.981 0.019 51.648 0.000 0.981 0.981
## TotalWorkngYrs 0.801 0.022 36.997 0.000 0.801 0.801
## StabilitasKarir =~
## YearsAtCompany 0.939 0.020 46.296 0.000 0.939 0.939
## YearsInCrrntRl 0.818 0.022 37.307 0.000 0.818 0.819
## YrsSncLstPrmtn 0.654 0.024 27.383 0.000 0.654 0.654
## YersWthCrrMngr 0.821 0.022 37.512 0.000 0.821 0.822
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## SosialEkonomi ~~
## StabilitasKarr 0.547 0.020 27.799 0.000 0.547 0.547
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .MonthlyIncome 0.064 0.006 10.607 0.000 0.064 0.064
## .JobLevel 0.037 0.006 6.285 0.000 0.037 0.037
## .TotalWorkngYrs 0.358 0.014 25.886 0.000 0.358 0.358
## .YearsAtCompany 0.117 0.011 10.294 0.000 0.117 0.118
## .YearsInCrrntRl 0.330 0.015 21.938 0.000 0.330 0.330
## .YrsSncLstPrmtn 0.572 0.022 25.420 0.000 0.572 0.572
## .YersWthCrrMngr 0.325 0.015 21.796 0.000 0.325 0.325
## SosialEkonomi 1.000 1.000 1.000
## StabilitasKarr 1.000 1.000 1.000inspect(fit_gabungan, "cor.lv")## SslEkn StbltK
## SosialEkonomi 1.000
## StabilitasKarir 0.547 1.000htmt(model_cfa_gabungan, data = data_z)## SslEkn StbltK
## SosialEkonomi 1.000
## StabilitasKarir 0.578 1.00012. Structural Equation Modeling (SEM)
model_sem <- '
SosialEkonomi =~ MonthlyIncome + JobLevel + TotalWorkingYears
StabilitasKarir =~ YearsAtCompany + YearsInCurrentRole +
YearsSinceLastPromotion + YearsWithCurrManager
StabilitasKarir ~ SosialEkonomi
'
fit_sem <- sem(model_sem, data = data_z, std.lv = TRUE)
summary(fit_sem, fit.measures = TRUE, standardized = TRUE)## lavaan 0.6-21 ended normally after 28 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 15
##
## Number of observations 1470
##
## Model Test User Model:
##
## Test statistic 346.688
## Degrees of freedom 13
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 9105.958
## Degrees of freedom 21
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.963
## Tucker-Lewis Index (TLI) 0.941
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -10217.741
## Loglikelihood unrestricted model (H1) -10044.398
##
## Akaike (AIC) 20465.483
## Bayesian (BIC) 20544.878
## Sample-size adjusted Bayesian (SABIC) 20497.228
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.132
## 90 Percent confidence interval - lower 0.120
## 90 Percent confidence interval - upper 0.144
## P-value H_0: RMSEA <= 0.050 0.000
## P-value H_0: RMSEA >= 0.080 1.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.061
##
## 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
## SosialEkonomi =~
## MonthlyIncome 0.967 0.019 50.295 0.000 0.967 0.968
## JobLevel 0.981 0.019 51.648 0.000 0.981 0.981
## TotalWorkngYrs 0.801 0.022 36.998 0.000 0.801 0.801
## StabilitasKarir =~
## YearsAtCompany 0.786 0.018 44.220 0.000 0.939 0.939
## YearsInCrrntRl 0.685 0.019 36.564 0.000 0.818 0.819
## YrsSncLstPrmtn 0.547 0.020 27.078 0.000 0.654 0.654
## YersWthCrrMngr 0.687 0.019 36.758 0.000 0.821 0.822
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## StabilitasKarir ~
## SosialEkonomi 0.654 0.034 19.477 0.000 0.547 0.547
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .MonthlyIncome 0.064 0.006 10.607 0.000 0.064 0.064
## .JobLevel 0.037 0.006 6.285 0.000 0.037 0.037
## .TotalWorkngYrs 0.358 0.014 25.886 0.000 0.358 0.358
## .YearsAtCompany 0.117 0.011 10.294 0.000 0.117 0.118
## .YearsInCrrntRl 0.330 0.015 21.938 0.000 0.330 0.330
## .YrsSncLstPrmtn 0.572 0.022 25.420 0.000 0.572 0.572
## .YersWthCrrMngr 0.325 0.015 21.796 0.000 0.325 0.325
## SosialEkonomi 1.000 1.000 1.000
## .StabilitasKarr 1.000 0.701 0.701Hasil SEM menunjukkan bahwa seluruh indikator tetap memiliki loading factor yang baik terhadap konstruk laten masing-masing. Konstruk SosialEkonomi memiliki hubungan positif terhadap StabilitasKarir dengan standardized coefficient sebesar 0.547, yang menunjukkan bahwa peningkatan kondisi sosial ekonomi akan meningkatkan stabilitas karir karyawan.
13. Evaluasi Inner Model SEM
fit_indices <- data.frame(
Indeks = c("Chi-Square", "df", "p-value", "CFI",
"TLI", "RMSEA", "SRMR", "GFI"),
Nilai = round(c(
fitMeasures(fit_sem, "chisq"),
fitMeasures(fit_sem, "df"),
fitMeasures(fit_sem, "pvalue"),
fitMeasures(fit_sem, "cfi"),
fitMeasures(fit_sem, "tli"),
fitMeasures(fit_sem, "rmsea"),
fitMeasures(fit_sem, "srmr"),
fitMeasures(fit_sem, "gfi")
), 4),
Threshold = c("> 0.05", "—", "> 0.05", ">= 0.90",
">= 0.90", "< 0.08", "< 0.05", ">= 0.90")
)
print(fit_indices)## Indeks Nilai Threshold
## chisq Chi-Square 346.6877 > 0.05
## df df 13.0000 —
## pvalue p-value 0.0000 > 0.05
## cfi CFI 0.9633 >= 0.90
## tli TLI 0.9407 >= 0.90
## rmsea RMSEA 0.1321 < 0.08
## srmr SRMR 0.0612 < 0.05
## gfi GFI 0.9398 >= 0.90Hasil evaluasi model SEM menunjukkan nilai CFI sebesar 0.963, TLI sebesar 0.941, dan GFI sebesar 0.940 yang menunjukkan model memiliki goodness of fit yang baik. Nilai SRMR sebesar 0.061 masih berada dalam kategori acceptable fit, meskipun nilai RMSEA sebesar 0.132 menunjukkan model belum sepenuhnya optimal.
14. Uji Hipotesis dan Koefisien Jalur
hasil_sem <- parameterEstimates(fit_sem, standardized = TRUE)
path_coef <- hasil_sem[hasil_sem$op == "~",
c("lhs", "rhs", "est", "se", "z", "pvalue", "std.all")]
colnames(path_coef) <- c("Endogen", "Eksogen", "Estimasi",
"Std.Error", "z-value", "p-value", "Std.Koef")
path_coef[, 3:7] <- round(path_coef[, 3:7], 4)
print(path_coef)## Endogen Eksogen Estimasi Std.Error z.value p.value Std.Koef
## 8 StabilitasKarir SosialEkonomi 0.654 0.034 19.477 0 0.547for (i in 1:nrow(path_coef)) {
status <- ifelse(path_coef$`p-value`[i] < 0.05, "SIGNIFIKAN", "TIDAK SIGNIFIKAN")
arah <- ifelse(path_coef$Estimasi[i] > 0, "POSITIF (+)", "NEGATIF (-)")
cat(sprintf("H%d: %s -> %s | p = %.4f | Arah: %s | %s\n",
i,
path_coef$Eksogen[i],
path_coef$Endogen[i],
path_coef$`p-value`[i],
arah,
status))
}## H1: SosialEkonomi -> StabilitasKarir | p = 0.0000 | Arah: POSITIF (+) | SIGNIFIKANHasil pengujian hipotesis menunjukkan bahwa hubungan SosialEkonomi terhadap StabilitasKarir memiliki nilai estimasi sebesar 0.654 dengan z-value sebesar 19.477 dan p-value sebesar 0.000. Nilai tersebut menunjukkan bahwa SosialEkonomi berpengaruh positif dan signifikan terhadap StabilitasKarir, sehingga hipotesis penelitian diterima.
15. Visualisasi SEM
semPaths(fit_sem,
what = "path",
whatLabels = "std",
style = "ram",
layout = "tree2",
rotation = 2,
sizeMan = 5,
sizeLat = 8,
edge.label.cex = 0.9,
label.cex = 0.9,
color = list(lat = "darkblue", man = "lightyellow"),
edge.color = "gray40")
Visualisasi SEM menunjukkan adanya hubungan positif antara konstruk SosialEkonomi dan StabilitasKarir. Jalur hubungan antar konstruk memiliki koefisien standar sebesar 0.547 yang menunjukkan pengaruh dalam kategori sedang hingga kuat. Seluruh indikator juga terlihat memiliki hubungan yang kuat terhadap konstruk laten masing-masing.