Load Dataset
telecom <- read_csv("telecom dataset.csv")
head(telecom)
## # A tibble: 6 × 31
## PU1 PEOU1 TECH1 ORG1 ENV1 PU2 PEOU2 TECH2 ORG2 ENV2 PU3 PEOU3 TECH3
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 4.13 3.84 2.79 4.83 2.02 3.88 2.90 3.03 4.39 2.67 3.86 3.83 3.64
## 2 NA 3.64 3.76 3.25 3.72 3.63 4.06 3.16 2.91 3.87 3.22 4.03 2.43
## 3 4.48 4.25 3.22 3.58 3.67 3.86 3.73 4.58 3.68 3.66 4.34 4.04 3.84
## 4 4.24 3.98 3.90 3.88 4.99 4.45 3.05 3.47 3.51 4.74 4.41 NA 2.44
## 5 4.18 4.11 3.17 5 4.37 4.54 3.94 2.66 4.73 NA 5 4.08 2.80
## 6 5 3.09 3.62 3.94 4.35 NA NA 5 3.98 5 4.62 3.54 4.22
## # ℹ 18 more variables: ORG3 <dbl>, ENV3 <dbl>, INT1 <dbl>, INT2 <dbl>,
## # INT3 <dbl>, PERF1 <dbl>, CUST1 <dbl>, PERF2 <dbl>, CUST2 <dbl>,
## # PERF3 <dbl>, CUST3 <dbl>, Age <dbl>, Experience <dbl>, Department <chr>,
## # Gender <chr>, Random_Noise1 <dbl>, Random_Noise2 <dbl>,
## # Unused_Category <chr>
dim(telecom)
## [1] 2600 31
Data Cleaning
Menghapus Variabel yang Tidak Digunakan
telecom_clean <- telecom %>%
select(
-Age,
-Experience,
-Department,
-Gender,
-Random_Noise1,
-Random_Noise2,
-Unused_Category
)
dim(telecom_clean)
## [1] 2600 24
Menangani Missing Value
telecom_clean <- telecom_clean %>%
mutate(across(where(is.numeric),
~ ifelse(is.na(.), median(., na.rm = TRUE), .)
))
colSums(is.na(telecom_clean))
## PU1 PEOU1 TECH1 ORG1 ENV1 PU2 PEOU2 TECH2 ORG2 ENV2 PU3 PEOU3 TECH3
## 0 0 0 0 0 0 0 0 0 0 0 0 0
## ORG3 ENV3 INT1 INT2 INT3 PERF1 CUST1 PERF2 CUST2 PERF3 CUST3
## 0 0 0 0 0 0 0 0 0 0 0
Struktur dan Statistik Data
Struktur Dataset
str(telecom_clean)
## tibble [2,600 × 24] (S3: tbl_df/tbl/data.frame)
## $ PU1 : num [1:2600] 4.13 4.01 4.48 4.24 4.18 ...
## $ PEOU1: num [1:2600] 3.84 3.64 4.25 3.98 4.11 ...
## $ TECH1: num [1:2600] 2.79 3.76 3.22 3.9 3.17 ...
## $ ORG1 : num [1:2600] 4.83 3.25 3.58 3.88 5 ...
## $ ENV1 : num [1:2600] 2.02 3.72 3.67 4.99 4.37 ...
## $ PU2 : num [1:2600] 3.88 3.63 3.86 4.45 4.54 ...
## $ PEOU2: num [1:2600] 2.9 4.06 3.73 3.05 3.94 ...
## $ TECH2: num [1:2600] 3.03 3.16 4.58 3.47 2.66 ...
## $ ORG2 : num [1:2600] 4.39 2.91 3.68 3.51 4.73 ...
## $ ENV2 : num [1:2600] 2.67 3.87 3.66 4.74 3.58 ...
## $ PU3 : num [1:2600] 3.86 3.22 4.34 4.41 5 ...
## $ PEOU3: num [1:2600] 3.83 4.03 4.04 3.78 4.08 ...
## $ TECH3: num [1:2600] 3.64 2.43 3.84 2.44 2.8 ...
## $ ORG3 : num [1:2600] 4.13 3.62 4.84 3.27 4.2 ...
## $ ENV3 : num [1:2600] 2.48 2.85 3.25 5 4.15 ...
## $ INT1 : num [1:2600] 4.55 3.17 3.84 3.94 3.82 ...
## $ INT2 : num [1:2600] 4.11 3.51 4.63 4.45 3.82 ...
## $ INT3 : num [1:2600] 4.51 3.4 3.89 4.2 3.97 ...
## $ PERF1: num [1:2600] 2.51 2.34 1.83 2.38 2.66 ...
## $ CUST1: num [1:2600] 3.42 2.46 3.24 2.46 3.14 ...
## $ PERF2: num [1:2600] 2.37 2.44 1.81 2.47 2.35 ...
## $ CUST2: num [1:2600] 3.16 2.27 2.91 2.36 3.4 ...
## $ PERF3: num [1:2600] 1.64 2.59 1.71 2.77 2.55 ...
## $ CUST3: num [1:2600] 2.47 2.21 3.56 2.83 3.45 ...
Ringkasan Statistik
summary(telecom_clean)
## PU1 PEOU1 TECH1 ORG1
## Min. :1.939 Min. :1.508 Min. :1.000 Min. :1.000
## 1st Qu.:3.644 1st Qu.:3.374 1st Qu.:3.130 1st Qu.:3.421
## Median :4.012 Median :3.795 Median :3.678 Median :3.897
## Mean :4.001 Mean :3.801 Mean :3.646 Mean :3.866
## 3rd Qu.:4.378 3rd Qu.:4.242 3rd Qu.:4.174 3rd Qu.:4.364
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## ENV1 PU2 PEOU2 TECH2
## Min. :1.000 Min. :1.945 Min. :1.208 Min. :1.030
## 1st Qu.:3.052 1st Qu.:3.644 1st Qu.:3.323 1st Qu.:3.187
## Median :3.572 Median :4.013 Median :3.797 Median :3.695
## Mean :3.567 Mean :3.994 Mean :3.778 Mean :3.676
## 3rd Qu.:4.070 3rd Qu.:4.370 3rd Qu.:4.229 3rd Qu.:4.216
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## ORG2 ENV2 PU3 PEOU3
## Min. :1.435 Min. :1.000 Min. :1.884 Min. :1.433
## 1st Qu.:3.426 1st Qu.:3.058 1st Qu.:3.660 1st Qu.:3.346
## Median :3.887 Median :3.579 Median :4.011 Median :3.777
## Mean :3.863 Mean :3.570 Mean :4.006 Mean :3.772
## 3rd Qu.:4.332 3rd Qu.:4.091 3rd Qu.:4.384 3rd Qu.:4.201
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## TECH3 ORG3 ENV3 INT1
## Min. :1.055 Min. :1.441 Min. :1.000 Min. :1.923
## 1st Qu.:3.166 1st Qu.:3.456 1st Qu.:3.045 1st Qu.:3.502
## Median :3.688 Median :3.910 Median :3.594 Median :3.838
## Mean :3.669 Mean :3.888 Mean :3.571 Mean :3.824
## 3rd Qu.:4.198 3rd Qu.:4.354 3rd Qu.:4.101 3rd Qu.:4.158
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## INT2 INT3 PERF1 CUST1
## Min. :2.170 Min. :2.290 Min. :1.000 Min. :1.000
## 1st Qu.:3.513 1st Qu.:3.508 1st Qu.:1.937 1st Qu.:2.109
## Median :3.812 Median :3.831 Median :2.272 Median :2.462
## Mean :3.820 Mean :3.829 Mean :2.287 Mean :2.468
## 3rd Qu.:4.135 3rd Qu.:4.158 3rd Qu.:2.641 3rd Qu.:2.815
## Max. :5.000 Max. :5.000 Max. :4.090 Max. :4.514
## PERF2 CUST2 PERF3 CUST3
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:1.937 1st Qu.:2.115 1st Qu.:1.951 1st Qu.:2.110
## Median :2.278 Median :2.457 Median :2.291 Median :2.473
## Mean :2.287 Mean :2.470 Mean :2.294 Mean :2.465
## 3rd Qu.:2.630 3rd Qu.:2.820 3rd Qu.:2.654 3rd Qu.:2.817
## Max. :4.428 Max. :4.388 Max. :4.536 Max. :4.683
Statistik Deskriptif
psych::describe(telecom_clean)
## vars n mean sd median trimmed mad min max range skew kurtosis
## PU1 1 2600 4.00 0.53 4.01 4.01 0.54 1.94 5.00 3.06 -0.22 -0.22
## PEOU1 2 2600 3.80 0.64 3.79 3.81 0.65 1.51 5.00 3.49 -0.14 -0.31
## TECH1 3 2600 3.65 0.76 3.68 3.67 0.78 1.00 5.00 4.00 -0.28 -0.15
## ORG1 4 2600 3.87 0.67 3.90 3.89 0.70 1.00 5.00 4.00 -0.29 -0.33
## ENV1 5 2600 3.57 0.75 3.57 3.58 0.76 1.00 5.00 4.00 -0.14 -0.27
## PU2 6 2600 3.99 0.54 4.01 4.01 0.54 1.95 5.00 3.05 -0.28 -0.11
## PEOU2 7 2600 3.78 0.65 3.80 3.79 0.67 1.21 5.00 3.79 -0.18 -0.23
## TECH2 8 2600 3.68 0.76 3.70 3.69 0.76 1.03 5.00 3.97 -0.25 -0.28
## ORG2 9 2600 3.86 0.66 3.89 3.88 0.67 1.43 5.00 3.57 -0.27 -0.26
## ENV2 10 2600 3.57 0.75 3.58 3.58 0.77 1.00 5.00 4.00 -0.19 -0.17
## PU3 11 2600 4.01 0.54 4.01 4.02 0.54 1.88 5.00 3.12 -0.21 -0.24
## PEOU3 12 2600 3.77 0.64 3.78 3.78 0.64 1.43 5.00 3.57 -0.15 -0.17
## TECH3 13 2600 3.67 0.75 3.69 3.69 0.76 1.06 5.00 3.94 -0.28 -0.17
## ORG3 14 2600 3.89 0.66 3.91 3.91 0.66 1.44 5.00 3.56 -0.33 -0.19
## ENV3 15 2600 3.57 0.77 3.59 3.58 0.79 1.00 5.00 4.00 -0.18 -0.32
## INT1 16 2600 3.82 0.50 3.84 3.83 0.48 1.92 5.00 3.08 -0.17 0.14
## INT2 17 2600 3.82 0.48 3.81 3.82 0.46 2.17 5.00 2.83 -0.03 -0.07
## INT3 18 2600 3.83 0.49 3.83 3.83 0.48 2.29 5.00 2.71 -0.05 -0.09
## PERF1 19 2600 2.29 0.53 2.27 2.28 0.52 1.00 4.09 3.09 0.08 -0.12
## CUST1 20 2600 2.47 0.54 2.46 2.46 0.52 1.00 4.51 3.51 0.10 0.07
## PERF2 21 2600 2.29 0.53 2.28 2.28 0.51 1.00 4.43 3.43 0.12 0.04
## CUST2 22 2600 2.47 0.54 2.46 2.47 0.52 1.00 4.39 3.39 0.10 0.10
## PERF3 23 2600 2.29 0.54 2.29 2.29 0.52 1.00 4.54 3.54 0.10 0.18
## CUST3 24 2600 2.47 0.54 2.47 2.47 0.53 1.00 4.68 3.68 0.01 0.09
## se
## PU1 0.01
## PEOU1 0.01
## TECH1 0.01
## ORG1 0.01
## ENV1 0.01
## PU2 0.01
## PEOU2 0.01
## TECH2 0.01
## ORG2 0.01
## ENV2 0.01
## PU3 0.01
## PEOU3 0.01
## TECH3 0.01
## ORG3 0.01
## ENV3 0.02
## INT1 0.01
## INT2 0.01
## INT3 0.01
## PERF1 0.01
## CUST1 0.01
## PERF2 0.01
## CUST2 0.01
## PERF3 0.01
## CUST3 0.01
Exploratory Data Analysis (EDA)
Membuat Variabel Konstruk
telecom_clean$INT <- rowMeans(
telecom_clean[, c("INT1", "INT2", "INT3")],
na.rm = TRUE
)
telecom_clean$PERF <- rowMeans(
telecom_clean[, c("PERF1", "PERF2", "PERF3")],
na.rm = TRUE
)
Histogram Variabel Intention
ggplot(telecom_clean, aes(x = INT)) +
geom_histogram(bins = 30, fill = "skyblue", color = "black") +
theme_minimal() +
labs(title = "Histogram Intention", x = "INT", y = "Frekuensi")
Boxplot Seluruh Variabel
telecom_long <- telecom_clean %>%
pivot_longer(cols = everything(),
names_to = "Variabel",
values_to = "Nilai")
ggplot(telecom_long, aes(x = Variabel, y = Nilai)) +
geom_boxplot(fill = "lightgreen") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90)) +
labs(title = "Boxplot Semua Variabel")
Heatmap Korelasi
cor_matrix <- cor(
select(telecom_clean, where(is.numeric)),
use = "complete.obs"
)
corrplot(
cor_matrix,
method = "color",
type = "upper",
tl.col = "black",
tl.cex = 0.7,
addCoef.col = "black",
number.cex = 0.3
)
Rata-rata Tiap Konstruk
construct_mean <- data.frame(
Konstruk = c("PU","PEOU","TECH","ORG","ENV","INT","PERF","CUST"),
Mean = c(
mean(rowMeans(telecom_clean[, c("PU1","PU2","PU3")])),
mean(rowMeans(telecom_clean[, c("PEOU1","PEOU2","PEOU3")])),
mean(rowMeans(telecom_clean[, c("TECH1","TECH2","TECH3")])),
mean(rowMeans(telecom_clean[, c("ORG1","ORG2","ORG3")])),
mean(rowMeans(telecom_clean[, c("ENV1","ENV2","ENV3")])),
mean(rowMeans(telecom_clean[, c("INT1","INT2","INT3")])),
mean(rowMeans(telecom_clean[, c("PERF1","PERF2","PERF3")])),
mean(rowMeans(telecom_clean[, c("CUST1","CUST2","CUST3")]))
)
)
ggplot(construct_mean, aes(x = Konstruk, y = Mean)) +
geom_bar(stat = "identity", fill = "steelblue") +
theme_minimal() +
labs(title = "Rata-rata Konstruk")
Model Inner PLS-SEM
inner <- matrix(c(
# PU
0,0,0,0,0,0,0,0,
# PEOU
0,0,0,0,0,0,0,0,
# TECH
0,0,0,0,0,0,0,0,
# ORG
0,0,0,0,0,0,0,0,
# ENV
0,0,0,0,0,0,0,0,
# INT
1,1,1,1,1,0,0,0,
# PERF
0,0,0,0,0,1,0,0,
# CUST
0,0,0,0,0,1,0,0
), nrow = 8, byrow = TRUE)
colnames(inner) <- rownames(inner) <- c(
"PU","PEOU","TECH","ORG","ENV","INT","PERF","CUST"
)
inner
## PU PEOU TECH ORG ENV INT PERF CUST
## PU 0 0 0 0 0 0 0 0
## PEOU 0 0 0 0 0 0 0 0
## TECH 0 0 0 0 0 0 0 0
## ORG 0 0 0 0 0 0 0 0
## ENV 0 0 0 0 0 0 0 0
## INT 1 1 1 1 1 0 0 0
## PERF 0 0 0 0 0 1 0 0
## CUST 0 0 0 0 0 1 0 0
Model Outer PLS-SEM
outer <- list(
c("PU1","PU2","PU3"),
c("PEOU1","PEOU2","PEOU3"),
c("TECH1","TECH2","TECH3"),
c("ORG1","ORG2","ORG3"),
c("ENV1","ENV2","ENV3"),
c("INT1","INT2","INT3"),
c("PERF1","PERF2","PERF3"),
c("CUST1","CUST2","CUST3")
)
outer
## [[1]]
## [1] "PU1" "PU2" "PU3"
##
## [[2]]
## [1] "PEOU1" "PEOU2" "PEOU3"
##
## [[3]]
## [1] "TECH1" "TECH2" "TECH3"
##
## [[4]]
## [1] "ORG1" "ORG2" "ORG3"
##
## [[5]]
## [1] "ENV1" "ENV2" "ENV3"
##
## [[6]]
## [1] "INT1" "INT2" "INT3"
##
## [[7]]
## [1] "PERF1" "PERF2" "PERF3"
##
## [[8]]
## [1] "CUST1" "CUST2" "CUST3"
Menentukan Measurement Mode
modes <- rep("A", 8)
modes
## [1] "A" "A" "A" "A" "A" "A" "A" "A"
Menjalankan Model PLS-SEM
pls_model <- plspm(
telecom_clean,
inner,
outer,
modes = modes
)
Hasil Model PLS-SEM
Ringkasan Model
summary(pls_model)
## PARTIAL LEAST SQUARES PATH MODELING (PLS-PM)
##
## ----------------------------------------------------------
## MODEL SPECIFICATION
## 1 Number of Cases 2600
## 2 Latent Variables 8
## 3 Manifest Variables 24
## 4 Scale of Data Standardized Data
## 5 Non-Metric PLS FALSE
## 6 Weighting Scheme centroid
## 7 Tolerance Crit 1e-06
## 8 Max Num Iters 100
## 9 Convergence Iters 3
## 10 Bootstrapping FALSE
## 11 Bootstrap samples NULL
##
## ----------------------------------------------------------
## BLOCKS DEFINITION
## Block Type Size Mode
## 1 PU Exogenous 3 A
## 2 PEOU Exogenous 3 A
## 3 TECH Exogenous 3 A
## 4 ORG Exogenous 3 A
## 5 ENV Exogenous 3 A
## 6 INT Endogenous 3 A
## 7 PERF Endogenous 3 A
## 8 CUST Endogenous 3 A
##
## ----------------------------------------------------------
## BLOCKS UNIDIMENSIONALITY
## Mode MVs C.alpha DG.rho eig.1st eig.2nd
## PU A 3 0.865 0.917 2.36 0.324
## PEOU A 3 0.901 0.938 2.50 0.254
## TECH A 3 0.881 0.926 2.42 0.297
## ORG A 3 0.851 0.909 2.31 0.348
## ENV A 3 0.883 0.928 2.43 0.298
## INT A 3 0.824 0.895 2.22 0.405
## PERF A 3 0.856 0.913 2.33 0.347
## CUST A 3 0.867 0.918 2.37 0.324
##
## ----------------------------------------------------------
## OUTER MODEL
## weight loading communality redundancy
## PU
## 1 PU1 0.368 0.884 0.781 0.000
## 1 PU2 0.377 0.887 0.787 0.000
## 1 PU3 0.382 0.891 0.794 0.000
## PEOU
## 2 PEOU1 0.366 0.916 0.838 0.000
## 2 PEOU2 0.370 0.913 0.834 0.000
## 2 PEOU3 0.358 0.912 0.831 0.000
## TECH
## 3 TECH1 0.395 0.903 0.816 0.000
## 3 TECH2 0.363 0.895 0.801 0.000
## 3 TECH3 0.355 0.897 0.805 0.000
## ORG
## 4 ORG1 0.377 0.876 0.767 0.000
## 4 ORG2 0.374 0.877 0.768 0.000
## 4 ORG3 0.389 0.880 0.774 0.000
## ENV
## 5 ENV1 0.392 0.902 0.813 0.000
## 5 ENV2 0.338 0.894 0.800 0.000
## 5 ENV3 0.380 0.904 0.818 0.000
## INT
## 6 INT1 0.384 0.865 0.748 0.261
## 6 INT2 0.389 0.857 0.734 0.256
## 6 INT3 0.389 0.859 0.738 0.257
## PERF
## 7 PERF1 0.377 0.877 0.769 0.160
## 7 PERF2 0.372 0.880 0.775 0.161
## 7 PERF3 0.385 0.887 0.788 0.164
## CUST
## 8 CUST1 0.378 0.886 0.786 0.180
## 8 CUST2 0.377 0.891 0.794 0.181
## 8 CUST3 0.371 0.888 0.789 0.180
##
## ----------------------------------------------------------
## CROSSLOADINGS
## PU PEOU TECH ORG ENV INT PERF
## PU
## 1 PU1 0.88382 -0.00356 -0.01635 0.03607 0.00899 0.271 0.1629
## 1 PU2 0.88698 0.00299 -0.00333 0.02645 0.02637 0.278 0.1606
## 1 PU3 0.89114 0.01439 0.00497 0.02784 0.03239 0.282 0.1501
## PEOU
## 2 PEOU1 0.00457 0.91570 -0.00931 0.01033 -0.00567 0.308 0.1929
## 2 PEOU2 0.01581 0.91329 0.01708 0.01069 -0.01112 0.311 0.1814
## 2 PEOU3 -0.00617 0.91163 0.01016 0.00258 -0.00806 0.301 0.1822
## TECH
## 3 TECH1 -0.00577 0.03158 0.90326 0.00996 -0.01091 0.281 0.1372
## 3 TECH2 -0.00314 -0.01901 0.89521 0.02029 -0.01899 0.259 0.1063
## 3 TECH3 -0.00551 0.00280 0.89704 -0.00168 -0.03287 0.253 0.1119
## ORG
## 4 ORG1 0.03239 0.01812 0.00397 0.87587 -0.02067 0.170 0.0956
## 4 ORG2 0.03195 0.00743 0.01510 0.87654 -0.00255 0.169 0.1004
## 4 ORG3 0.02500 -0.00242 0.00916 0.87977 0.00279 0.176 0.1066
## ENV
## 5 ENV1 0.03125 -0.00846 -0.00964 -0.00218 0.90174 0.135 0.0929
## 5 ENV2 0.00440 -0.00811 -0.03489 -0.00819 0.89443 0.116 0.0767
## 5 ENV3 0.03127 -0.00794 -0.01917 -0.01062 0.90422 0.131 0.0857
## INT
## 6 INT1 0.26465 0.28966 0.25451 0.14768 0.12416 0.865 0.3954
## 6 INT2 0.26272 0.29918 0.25379 0.18497 0.10943 0.857 0.3967
## 6 INT3 0.27817 0.27764 0.25250 0.17158 0.13263 0.859 0.3840
## PERF
## 7 PERF1 0.14881 0.17466 0.12664 0.09744 0.08073 0.400 0.8767
## 7 PERF2 0.16134 0.18047 0.10298 0.10030 0.08207 0.395 0.8801
## 7 PERF3 0.16010 0.18172 0.12048 0.10641 0.08832 0.409 0.8875
## CUST
## 8 CUST1 0.14896 0.14860 0.13634 0.08047 0.08111 0.428 0.2125
## 8 CUST2 0.14726 0.16307 0.13256 0.10754 0.06670 0.427 0.2075
## 8 CUST3 0.13741 0.14338 0.13890 0.11279 0.06622 0.420 0.2403
## CUST
## PU
## 1 PU1 0.1447
## 1 PU2 0.1455
## 1 PU3 0.1430
## PEOU
## 2 PEOU1 0.1718
## 2 PEOU2 0.1471
## 2 PEOU3 0.1490
## TECH
## 3 TECH1 0.1486
## 3 TECH2 0.1296
## 3 TECH3 0.1331
## ORG
## 4 ORG1 0.1144
## 4 ORG2 0.0911
## 4 ORG3 0.0915
## ENV
## 5 ENV1 0.0644
## 5 ENV2 0.0752
## 5 ENV3 0.0779
## INT
## 6 INT1 0.4133
## 6 INT2 0.4038
## 6 INT3 0.4163
## PERF
## 7 PERF1 0.2359
## 7 PERF2 0.2043
## 7 PERF3 0.2144
## CUST
## 8 CUST1 0.8865
## 8 CUST2 0.8910
## 8 CUST3 0.8884
##
## ----------------------------------------------------------
## INNER MODEL
## $INT
## Estimate Std. Error t value Pr(>|t|)
## Intercept 5.05e-17 0.0158 3.19e-15 1.00e+00
## PU 3.02e-01 0.0159 1.91e+01 7.45e-76
## PEOU 3.32e-01 0.0158 2.09e+01 3.66e-90
## TECH 2.96e-01 0.0158 1.87e+01 5.71e-73
## ORG 1.80e-01 0.0159 1.14e+01 2.79e-29
## ENV 1.45e-01 0.0159 9.17e+00 9.75e-20
##
## $PERF
## Estimate Std. Error t value Pr(>|t|)
## Intercept 3.43e-16 0.0175 1.97e-14 1.00e+00
## INT 4.56e-01 0.0175 2.61e+01 1.59e-133
##
## $CUST
## Estimate Std. Error t value Pr(>|t|)
## Intercept 3.33e-16 0.0172 1.93e-14 1.00e+00
## INT 4.78e-01 0.0172 2.77e+01 1.63e-148
##
## ----------------------------------------------------------
## CORRELATIONS BETWEEN LVs
## PU PEOU TECH ORG ENV INT PERF CUST
## PU 1.0000 0.0053 -0.0054 0.0339 0.0256 0.312 0.178 0.1627
## PEOU 0.0053 1.0000 0.0065 0.0087 -0.0091 0.336 0.203 0.1707
## TECH -0.0054 0.0065 1.0000 0.0107 -0.0229 0.295 0.133 0.1530
## ORG 0.0339 0.0087 0.0107 1.0000 -0.0077 0.196 0.115 0.1127
## ENV 0.0256 -0.0091 -0.0229 -0.0077 1.0000 0.142 0.095 0.0803
## INT 0.3122 0.3358 0.2948 0.1955 0.1419 1.000 0.456 0.4779
## PERF 0.1778 0.2030 0.1325 0.1151 0.0950 0.456 1.000 0.2475
## CUST 0.1627 0.1707 0.1530 0.1127 0.0803 0.478 0.247 1.0000
##
## ----------------------------------------------------------
## SUMMARY INNER MODEL
## Type R2 Block_Communality Mean_Redundancy AVE
## PU Exogenous 0.000 0.787 0.000 0.787
## PEOU Exogenous 0.000 0.835 0.000 0.835
## TECH Exogenous 0.000 0.807 0.000 0.807
## ORG Exogenous 0.000 0.770 0.000 0.770
## ENV Exogenous 0.000 0.810 0.000 0.810
## INT Endogenous 0.349 0.740 0.258 0.740
## PERF Endogenous 0.208 0.777 0.161 0.777
## CUST Endogenous 0.228 0.790 0.180 0.790
##
## ----------------------------------------------------------
## GOODNESS-OF-FIT
## [1] 0.4545
##
## ----------------------------------------------------------
## TOTAL EFFECTS
## relationships direct indirect total
## 1 PU -> PEOU 0.000 0.0000 0.0000
## 2 PU -> TECH 0.000 0.0000 0.0000
## 3 PU -> ORG 0.000 0.0000 0.0000
## 4 PU -> ENV 0.000 0.0000 0.0000
## 5 PU -> INT 0.302 0.0000 0.3022
## 6 PU -> PERF 0.000 0.1377 0.1377
## 7 PU -> CUST 0.000 0.1444 0.1444
## 8 PEOU -> TECH 0.000 0.0000 0.0000
## 9 PEOU -> ORG 0.000 0.0000 0.0000
## 10 PEOU -> ENV 0.000 0.0000 0.0000
## 11 PEOU -> INT 0.332 0.0000 0.3320
## 12 PEOU -> PERF 0.000 0.1513 0.1513
## 13 PEOU -> CUST 0.000 0.1587 0.1587
## 14 TECH -> ORG 0.000 0.0000 0.0000
## 15 TECH -> ENV 0.000 0.0000 0.0000
## 16 TECH -> INT 0.296 0.0000 0.2956
## 17 TECH -> PERF 0.000 0.1347 0.1347
## 18 TECH -> CUST 0.000 0.1413 0.1413
## 19 ORG -> ENV 0.000 0.0000 0.0000
## 20 ORG -> INT 0.180 0.0000 0.1803
## 21 ORG -> PERF 0.000 0.0822 0.0822
## 22 ORG -> CUST 0.000 0.0862 0.0862
## 23 ENV -> INT 0.145 0.0000 0.1453
## 24 ENV -> PERF 0.000 0.0662 0.0662
## 25 ENV -> CUST 0.000 0.0695 0.0695
## 26 INT -> PERF 0.456 0.0000 0.4557
## 27 INT -> CUST 0.478 0.0000 0.4779
## 28 PERF -> CUST 0.000 0.0000 0.0000
pls_model$path_coefs
## PU PEOU TECH ORG ENV INT PERF CUST
## PU 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0 0
## PEOU 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0 0
## TECH 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0 0
## ORG 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0 0
## ENV 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0 0
## INT 0.3021579 0.3319686 0.2956496 0.1803163 0.1453163 0.0000000 0 0
## PERF 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.4557301 0 0
## CUST 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.4779471 0 0
pls_model$outer_model
## name block weight loading communality redundancy
## 1 PU1 PU 0.3678134 0.8838158 0.7811303 0.0000000
## 2 PU2 PU 0.3771189 0.8869764 0.7867271 0.0000000
## 3 PU3 PU 0.3820098 0.8911424 0.7941347 0.0000000
## 4 PEOU1 PEOU 0.3662120 0.9156955 0.8384982 0.0000000
## 5 PEOU2 PEOU 0.3701854 0.9132918 0.8341019 0.0000000
## 6 PEOU3 PEOU 0.3582316 0.9116282 0.8310660 0.0000000
## 7 TECH1 TECH 0.3947032 0.9032633 0.8158846 0.0000000
## 8 TECH2 TECH 0.3632635 0.8952065 0.8013946 0.0000000
## 9 TECH3 TECH 0.3548141 0.8970421 0.8046845 0.0000000
## 10 ORG1 ORG 0.3767908 0.8758676 0.7671440 0.0000000
## 11 ORG2 ORG 0.3740470 0.8765390 0.7683206 0.0000000
## 12 ORG3 ORG 0.3888700 0.8797655 0.7739873 0.0000000
## 13 ENV1 ENV 0.3924939 0.9017400 0.8131351 0.0000000
## 14 ENV2 ENV 0.3383847 0.8944295 0.8000042 0.0000000
## 15 ENV3 ENV 0.3797887 0.9042166 0.8176076 0.0000000
## 16 INT1 INT 0.3844727 0.8648929 0.7480397 0.2609258
## 17 INT2 INT 0.3887935 0.8567794 0.7340710 0.2560533
## 18 INT3 INT 0.3892404 0.8590116 0.7379009 0.2573893
## 19 PERF1 PERF 0.3767288 0.8766908 0.7685868 0.1596278
## 20 PERF2 PERF 0.3722648 0.8801155 0.7746032 0.1608773
## 21 PERF3 PERF 0.3854646 0.8874727 0.7876077 0.1635782
## 22 CUST1 CUST 0.3776614 0.8864696 0.7858283 0.1795095
## 23 CUST2 CUST 0.3768294 0.8909544 0.7937997 0.1813304
## 24 CUST3 CUST 0.3708848 0.8883537 0.7891722 0.1802733
pls_model$inner_model
## $INT
## Estimate Std. Error t value Pr(>|t|)
## Intercept 5.053337e-17 0.01584411 3.189410e-15 1.000000e+00
## PU 3.021579e-01 0.01585897 1.905281e+01 7.451150e-76
## PEOU 3.319686e-01 0.01584588 2.094983e+01 3.661433e-90
## TECH 2.956496e-01 0.01584966 1.865337e+01 5.710302e-73
## ORG 1.803163e-01 0.01585525 1.137266e+01 2.791275e-29
## ENV 1.453163e-01 0.01585460 9.165556e+00 9.745823e-20
##
## $PERF
## Estimate Std. Error t value Pr(>|t|)
## Intercept 3.432012e-16 0.01746337 1.965263e-14 1.000000e+00
## INT 4.557301e-01 0.01746337 2.609635e+01 1.585066e-133
##
## $CUST
## Estimate Std. Error t value Pr(>|t|)
## Intercept 3.330035e-16 0.01723325 1.932332e-14 1.00000e+00
## INT 4.779471e-01 0.01723325 2.773401e+01 1.63192e-148
pls_model$gof
## [1] 0.4544918
Evaluasi Outer Model
pls_model$outer_model
## name block weight loading communality redundancy
## 1 PU1 PU 0.3678134 0.8838158 0.7811303 0.0000000
## 2 PU2 PU 0.3771189 0.8869764 0.7867271 0.0000000
## 3 PU3 PU 0.3820098 0.8911424 0.7941347 0.0000000
## 4 PEOU1 PEOU 0.3662120 0.9156955 0.8384982 0.0000000
## 5 PEOU2 PEOU 0.3701854 0.9132918 0.8341019 0.0000000
## 6 PEOU3 PEOU 0.3582316 0.9116282 0.8310660 0.0000000
## 7 TECH1 TECH 0.3947032 0.9032633 0.8158846 0.0000000
## 8 TECH2 TECH 0.3632635 0.8952065 0.8013946 0.0000000
## 9 TECH3 TECH 0.3548141 0.8970421 0.8046845 0.0000000
## 10 ORG1 ORG 0.3767908 0.8758676 0.7671440 0.0000000
## 11 ORG2 ORG 0.3740470 0.8765390 0.7683206 0.0000000
## 12 ORG3 ORG 0.3888700 0.8797655 0.7739873 0.0000000
## 13 ENV1 ENV 0.3924939 0.9017400 0.8131351 0.0000000
## 14 ENV2 ENV 0.3383847 0.8944295 0.8000042 0.0000000
## 15 ENV3 ENV 0.3797887 0.9042166 0.8176076 0.0000000
## 16 INT1 INT 0.3844727 0.8648929 0.7480397 0.2609258
## 17 INT2 INT 0.3887935 0.8567794 0.7340710 0.2560533
## 18 INT3 INT 0.3892404 0.8590116 0.7379009 0.2573893
## 19 PERF1 PERF 0.3767288 0.8766908 0.7685868 0.1596278
## 20 PERF2 PERF 0.3722648 0.8801155 0.7746032 0.1608773
## 21 PERF3 PERF 0.3854646 0.8874727 0.7876077 0.1635782
## 22 CUST1 CUST 0.3776614 0.8864696 0.7858283 0.1795095
## 23 CUST2 CUST 0.3768294 0.8909544 0.7937997 0.1813304
## 24 CUST3 CUST 0.3708848 0.8883537 0.7891722 0.1802733
pls_model$crossloadings
## name block PU PEOU TECH ORG ENV
## 1 PU1 PU 0.883815754 -0.003559818 -0.016349578 0.036071928 0.008987715
## 2 PU2 PU 0.886976388 0.002994031 -0.003334236 0.026447643 0.026372975
## 3 PU3 PU 0.891142367 0.014387298 0.004973240 0.027840817 0.032394889
## 4 PEOU1 PEOU 0.004569672 0.915695476 -0.009314985 0.010329974 -0.005674426
## 5 PEOU2 PEOU 0.015813920 0.913291770 0.017076723 0.010691550 -0.011123703
## 6 PEOU3 PEOU -0.006173951 0.911628213 0.010156554 0.002583188 -0.008056079
## 7 TECH1 TECH -0.005771895 0.031575213 0.903263283 0.009962473 -0.010913980
## 8 TECH2 TECH -0.003136649 -0.019012079 0.895206455 0.020285872 -0.018989485
## 9 TECH3 TECH -0.005505856 0.002796533 0.897042092 -0.001679915 -0.032866166
## 10 ORG1 ORG 0.032389411 0.018115824 0.003966421 0.875867575 -0.020667791
## 11 ORG2 ORG 0.031949306 0.007432147 0.015099751 0.876538976 -0.002552035
## 12 ORG3 ORG 0.025002026 -0.002416365 0.009161810 0.879765497 0.002789542
## 13 ENV1 ENV 0.031245248 -0.008458043 -0.009635312 -0.002175307 0.901740045
## 14 ENV2 ENV 0.004396054 -0.008114373 -0.034888128 -0.008190188 0.894429538
## 15 ENV3 ENV 0.031268935 -0.007942066 -0.019168398 -0.010616471 0.904216593
## 16 INT1 INT 0.264646333 0.289656537 0.254509951 0.147678937 0.124159237
## 17 INT2 INT 0.262717403 0.299181790 0.253788750 0.184974483 0.109426409
## 18 INT3 INT 0.278170306 0.277640434 0.252503056 0.171581223 0.132625367
## 19 PERF1 PERF 0.148807218 0.174663864 0.126638447 0.097438251 0.080730805
## 20 PERF2 PERF 0.161336674 0.180468914 0.102981182 0.100303010 0.082065589
## 21 PERF3 PERF 0.160098501 0.181721135 0.120482884 0.106407356 0.088315949
## 22 CUST1 CUST 0.148963101 0.148595208 0.136337280 0.080469202 0.081107853
## 23 CUST2 CUST 0.147257727 0.163067229 0.132557389 0.107536082 0.066695902
## 24 CUST3 CUST 0.137406728 0.143377440 0.138899313 0.112790590 0.066220877
## INT PERF CUST
## 1 0.2711604 0.16293162 0.14472225
## 2 0.2780206 0.16056050 0.14547013
## 3 0.2816262 0.15013593 0.14298165
## 4 0.3077942 0.19285224 0.17181240
## 5 0.3111336 0.18139888 0.14710938
## 6 0.3010868 0.18215639 0.14897122
## 7 0.2813086 0.13723127 0.14863625
## 8 0.2589013 0.10631847 0.12960597
## 9 0.2528793 0.11188748 0.13305040
## 10 0.1700654 0.09559228 0.11435409
## 11 0.1688270 0.10044978 0.09105687
## 12 0.1755174 0.10664777 0.09154234
## 13 0.1349245 0.09292922 0.06442124
## 14 0.1163238 0.07674458 0.07521122
## 15 0.1305569 0.08573999 0.07790997
## 16 0.8648929 0.39538294 0.41334559
## 17 0.8567794 0.39670523 0.40381892
## 18 0.8590116 0.38402946 0.41625899
## 19 0.4001194 0.87669084 0.23589759
## 20 0.3953782 0.88011547 0.20429373
## 21 0.4093976 0.88747266 0.21435929
## 22 0.4275438 0.21247977 0.88646959
## 23 0.4266019 0.20748363 0.89095436
## 24 0.4198721 0.24028315 0.88835367
ave <- aggregate(
pls_model$outer_model$communality,
by = list(pls_model$outer_model$block),
mean
)
ave
## Group.1 x
## 1 PU 0.7873307
## 2 PEOU 0.8345554
## 3 TECH 0.8073212
## 4 ORG 0.7698173
## 5 ENV 0.8102490
## 6 INT 0.7400039
## 7 PERF 0.7769326
## 8 CUST 0.7896001
Evaluasi Inner Model
pls_model$path_coefs
## PU PEOU TECH ORG ENV INT PERF CUST
## PU 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0 0
## PEOU 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0 0
## TECH 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0 0
## ORG 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0 0
## ENV 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0 0
## INT 0.3021579 0.3319686 0.2956496 0.1803163 0.1453163 0.0000000 0 0
## PERF 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.4557301 0 0
## CUST 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.4779471 0 0
pls_model$inner_summary
## Type R2 Block_Communality Mean_Redundancy AVE
## PU Exogenous 0.0000000 0.7873307 0.0000000 0.7873307
## PEOU Exogenous 0.0000000 0.8345554 0.0000000 0.8345554
## TECH Exogenous 0.0000000 0.8073212 0.0000000 0.8073212
## ORG Exogenous 0.0000000 0.7698173 0.0000000 0.7698173
## ENV Exogenous 0.0000000 0.8102490 0.0000000 0.8102490
## INT Endogenous 0.3488128 0.7400039 0.2581228 0.7400039
## PERF Endogenous 0.2076900 0.7769326 0.1613611 0.7769326
## CUST Endogenous 0.2284334 0.7896001 0.1803710 0.7896001
Bootstrapping PLS-SEM
boot_model <- plspm(
telecom_clean,
inner,
outer,
modes = modes,
boot.val = TRUE,
br = 200
)
Hasil Bootstrap
boot_model$boot$paths
## Original Mean.Boot Std.Error perc.025 perc.975
## PU -> INT 0.3021579 0.3013111 0.01519760 0.2712260 0.3288432
## PEOU -> INT 0.3319686 0.3344326 0.01545446 0.3021877 0.3620884
## TECH -> INT 0.2956496 0.2964979 0.01595385 0.2653705 0.3269921
## ORG -> INT 0.1803163 0.1803065 0.01473995 0.1494047 0.2061088
## ENV -> INT 0.1453163 0.1447927 0.01371822 0.1182949 0.1722344
## INT -> PERF 0.4557301 0.4556916 0.01518599 0.4250613 0.4820933
## INT -> CUST 0.4779471 0.4773767 0.01326678 0.4542773 0.5059886
boot_model$boot$rsq
## Original Mean.Boot Std.Error perc.025 perc.975
## INT 0.3488128 0.3522385 0.01456854 0.3226351 0.3803506
## PERF 0.2076900 0.2078843 0.01379037 0.1806771 0.2324140
## CUST 0.2284334 0.2280636 0.01268940 0.2063679 0.2560244
boot_model$inner_model
## $INT
## Estimate Std. Error t value Pr(>|t|)
## Intercept 5.053337e-17 0.01584411 3.189410e-15 1.000000e+00
## PU 3.021579e-01 0.01585897 1.905281e+01 7.451150e-76
## PEOU 3.319686e-01 0.01584588 2.094983e+01 3.661433e-90
## TECH 2.956496e-01 0.01584966 1.865337e+01 5.710302e-73
## ORG 1.803163e-01 0.01585525 1.137266e+01 2.791275e-29
## ENV 1.453163e-01 0.01585460 9.165556e+00 9.745823e-20
##
## $PERF
## Estimate Std. Error t value Pr(>|t|)
## Intercept 3.432012e-16 0.01746337 1.965263e-14 1.000000e+00
## INT 4.557301e-01 0.01746337 2.609635e+01 1.585066e-133
##
## $CUST
## Estimate Std. Error t value Pr(>|t|)
## Intercept 3.330035e-16 0.01723325 1.932332e-14 1.00000e+00
## INT 4.779471e-01 0.01723325 2.773401e+01 1.63192e-148
Visualisasi Model
plot(pls_model)
