#Analisis Jalur
library(readxl)
df<- read_excel("C:/Users/ASUS/Downloads/kepuasan pelanggan (2).xlsx")
head(df)
## # A tibble: 6 × 5
## produk harga layanan kepuasan loyalitas
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 18 18 16 15 14
## 2 15 18 18 12 12
## 3 18 15 16 14 11
## 4 14 15 15 13 11
## 5 15 15 16 12 11
## 6 17 16 16 13 12
## vars n mean sd median trimmed mad min max range skew kurtosis
## produk 1 30 14.60 3.30 15.0 14.83 2.97 4 20 16 -0.97 1.56
## harga 2 30 15.07 2.12 15.0 15.04 2.22 11 19 8 0.02 -0.86
## layanan 3 30 15.47 2.57 16.0 15.67 1.48 8 21 13 -0.67 0.80
## kepuasan 4 30 12.57 1.87 13.0 12.71 1.48 8 15 7 -0.61 -0.51
## loyalitas 5 30 11.30 1.84 11.5 11.38 0.74 6 15 9 -0.59 0.76
## se
## produk 0.60
## harga 0.39
## layanan 0.47
## kepuasan 0.34
## loyalitas 0.34
## corrplot 0.92 loaded
specmod <- "kepuasan ~produk + harga + layanan "
int.model <- lm(specmod, data=df)
summary(int.model)
##
## Call:
## lm(formula = specmod, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9883 -1.1432 0.1984 0.8499 2.5063
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.33636 2.18443 2.443 0.0217 *
## produk 0.23871 0.10064 2.372 0.0254 *
## harga -0.02162 0.13057 -0.166 0.8698
## layanan 0.26320 0.13319 1.976 0.0588 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.417 on 26 degrees of freedom
## Multiple R-squared: 0.4848, Adjusted R-squared: 0.4254
## F-statistic: 8.157 on 3 and 26 DF, p-value: 0.0005436
library(QuantPsyc)
## Loading required package: boot
##
## Attaching package: 'boot'
## The following object is masked from 'package:psych':
##
## logit
## Loading required package: dplyr
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
## Loading required package: purrr
## Loading required package: MASS
##
## Attaching package: 'MASS'
## The following object is masked from 'package:dplyr':
##
## select
##
## Attaching package: 'QuantPsyc'
## The following object is masked from 'package:base':
##
## norm
lm.beta(int.model)
## produk harga layanan
## 0.4209403 -0.0244733 0.3617342
specmod <- "loyalitas ~ kepuasan"
bhv.model <- lm(specmod, data=df)
summary(bhv.model)
##
## Call:
## lm(formula = specmod, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4535 -0.7973 0.1522 0.7004 1.9504
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.2706 1.3846 0.918 0.367
## kepuasan 0.7981 0.1090 7.321 5.7e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.098 on 28 degrees of freedom
## Multiple R-squared: 0.6568, Adjusted R-squared: 0.6446
## F-statistic: 53.59 on 1 and 28 DF, p-value: 5.698e-08
lm.beta(bhv.model)
## kepuasan
## 0.8104462
sqrt(1-summary(int.model)$r.squared)
## [1] 0.7177415
sqrt(1-summary(bhv.model)$r.squared)
## [1] 0.5858131
library(lavaan)
## This is lavaan 0.6-12
## lavaan is FREE software! Please report any bugs.
##
## Attaching package: 'lavaan'
## The following object is masked from 'package:psych':
##
## cor2cov
specmod <- "
# Jalur langsung model A dan B (pada regresi) dianalisis bersamaan dengan kovariansnya juga
kepuasan ~produk + harga + layanan
loyalitas ~ kepuasan
# Kovarians (korelasi antar variabel eksogen)
produk ~~ harga + layanan
harga ~~ layanan
"
fitmod <- sem(specmod, data=df)
summary(fitmod, standardized = TRUE)
## lavaan 0.6-12 ended normally after 34 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 12
##
## Number of observations 30
##
## Model Test User Model:
##
## Test statistic 16.779
## Degrees of freedom 3
## P-value (Chi-square) 0.001
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## kepuasan ~
## produk 0.239 0.094 2.548 0.011 0.239 0.421
## harga -0.022 0.122 -0.178 0.859 -0.022 -0.024
## layanan 0.263 0.124 2.123 0.034 0.263 0.362
## loyalitas ~
## kepuasan 0.798 0.105 7.577 0.000 0.798 0.810
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## produk ~~
## harga 1.260 1.253 1.006 0.314 1.260 0.187
## layanan 4.987 1.750 2.849 0.004 4.987 0.609
## harga ~~
## layanan 1.602 1.003 1.597 0.110 1.602 0.305
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .kepuasan 1.741 0.449 3.873 0.000 1.741 0.515
## .loyalitas 1.124 0.290 3.873 0.000 1.124 0.343
## produk 10.507 2.713 3.873 0.000 10.507 1.000
## harga 4.329 1.118 3.873 0.000 4.329 1.000
## layanan 6.382 1.648 3.873 0.000 6.382 1.000
fitmeasures(fitmod)
## npar fmin chisq df
## 12.000 0.280 16.779 3.000
## pvalue baseline.chisq baseline.df baseline.pvalue
## 0.001 85.589 10.000 0.000
## cfi tli nnfi rfi
## 0.818 0.392 0.392 0.347
## nfi pnfi ifi rni
## 0.804 0.241 0.833 0.818
## logl unrestricted.logl aic bic
## -299.564 -291.174 623.127 639.942
## ntotal bic2 rmsea rmsea.ci.lower
## 30.000 602.579 0.391 0.223
## rmsea.ci.upper rmsea.pvalue rmr rmr_nomean
## 0.583 0.001 0.372 0.372
## srmr srmr_bentler srmr_bentler_nomean crmr
## 0.096 0.096 0.096 0.118
## crmr_nomean srmr_mplus srmr_mplus_nomean cn_05
## 0.118 0.096 0.096 14.973
## cn_01 gfi agfi pgfi
## 21.284 0.854 0.269 0.171
## mfi ecvi
## 0.795 1.359
library(semPlot)
semPaths(fitmod, "std", rotation=2, layout = "tree2", curvature = 2, nCharNodes = 0, nDigits = 3,
sizeMan = 10, sizeInt = 5, sizeLat = 5, edge.label.cex=1.2, exoVar = FALSE, fade=FALSE)
