LOAD DATASET
raw_data <- read_csv("airline_passenger_satisfaction.csv")
head(raw_data)
# A tibble: 6 × 24
ID Gender Age `Customer Type` `Type of Travel` Class `Flight Distance`
<dbl> <chr> <dbl> <chr> <chr> <chr> <dbl>
1 1 Male 48 First-time Business Business 821
2 2 Female 35 Returning Business Business 821
3 3 Male 41 Returning Business Business 853
4 4 Male 50 Returning Business Business 1905
5 5 Female 49 Returning Business Business 3470
6 6 Male 43 Returning Business Business 3788
# ℹ 17 more variables: `Departure Delay` <dbl>, `Arrival Delay` <dbl>,
# `Departure and Arrival Time Convenience` <dbl>,
# `Ease of Online Booking` <dbl>, `Check-in Service` <dbl>,
# `Online Boarding` <dbl>, `Gate Location` <dbl>, `On-board Service` <dbl>,
# `Seat Comfort` <dbl>, `Leg Room Service` <dbl>, Cleanliness <dbl>,
# `Food and Drink` <dbl>, `In-flight Service` <dbl>,
# `In-flight Wifi Service` <dbl>, `In-flight Entertainment` <dbl>, …
Exploratory Data
Analyst (EDA)
Statistika
Deskriptif
ID Gender Age Customer Type
Min. : 1 Length:129880 Min. : 7.00 Length:129880
1st Qu.: 32471 Class :character 1st Qu.:27.00 Class :character
Median : 64941 Mode :character Median :40.00 Mode :character
Mean : 64941 Mean :39.43
3rd Qu.: 97410 3rd Qu.:51.00
Max. :129880 Max. :85.00
Type of Travel Class Flight Distance Departure Delay
Length:129880 Length:129880 Min. : 31 Min. : 0.00
Class :character Class :character 1st Qu.: 414 1st Qu.: 0.00
Mode :character Mode :character Median : 844 Median : 0.00
Mean :1190 Mean : 14.71
3rd Qu.:1744 3rd Qu.: 12.00
Max. :4983 Max. :1592.00
Arrival Delay Departure and Arrival Time Convenience
Min. : 0.00 Min. :0.000
1st Qu.: 0.00 1st Qu.:2.000
Median : 0.00 Median :3.000
Mean : 15.09 Mean :3.058
3rd Qu.: 13.00 3rd Qu.:4.000
Max. :1584.00 Max. :5.000
NA's :393
Ease of Online Booking Check-in Service Online Boarding Gate Location
Min. :0.000 Min. :0.000 Min. :0.000 Min. :0.000
1st Qu.:2.000 1st Qu.:3.000 1st Qu.:2.000 1st Qu.:2.000
Median :3.000 Median :3.000 Median :3.000 Median :3.000
Mean :2.757 Mean :3.306 Mean :3.253 Mean :2.977
3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
On-board Service Seat Comfort Leg Room Service Cleanliness
Min. :0.000 Min. :0.000 Min. :0.000 Min. :0.000
1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000
Median :4.000 Median :4.000 Median :4.000 Median :3.000
Mean :3.383 Mean :3.441 Mean :3.351 Mean :3.286
3rd Qu.:4.000 3rd Qu.:5.000 3rd Qu.:4.000 3rd Qu.:4.000
Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
Food and Drink In-flight Service In-flight Wifi Service
Min. :0.000 Min. :0.000 Min. :0.000
1st Qu.:2.000 1st Qu.:3.000 1st Qu.:2.000
Median :3.000 Median :4.000 Median :3.000
Mean :3.205 Mean :3.642 Mean :2.729
3rd Qu.:4.000 3rd Qu.:5.000 3rd Qu.:4.000
Max. :5.000 Max. :5.000 Max. :5.000
In-flight Entertainment Baggage Handling Satisfaction
Min. :0.000 Min. :1.000 Length:129880
1st Qu.:2.000 1st Qu.:3.000 Class :character
Median :4.000 Median :4.000 Mode :character
Mean :3.358 Mean :3.632
3rd Qu.:4.000 3rd Qu.:5.000
Max. :5.000 Max. :5.000
Cek Missing
Value
missing_count <- colSums(is.na(raw_data))
missing_count[missing_count > 0]
Arrival Delay
393
gg_miss_var(raw_data) +
labs(title = "Visualisasi Missing Values pada Dataset",
y = "Jumlah Data Kosong")
Distribusi Variabel
Target
Pengecekan Matriks
Korelasi
preprocessing
Mengatasi Missing
Value
clean_data <- raw_data
median_delay <- median(clean_data$`Arrival Delay`, na.rm = TRUE)
clean_data$`Arrival Delay`[is.na(clean_data$`Arrival Delay`)] <- median_delay
cat("Total missing value setelah imputasi: ", sum(is.na(clean_data)), "\n")
Total missing value setelah imputasi: 0
Encoding Variabel
Target
clean_data <- clean_data %>%
mutate(Satisfaction_Num = ifelse(Satisfaction == "Satisfied", 1, 0))
table(clean_data$Satisfaction_Num)
0 1
73452 56428
Menyiapkan Dataset
Khusus untuk Pemodelan SEM-PLS
sem_data <- clean_data %>%
select(`In-flight Wifi Service`, `Departure and Arrival Time Convenience`,
`Ease of Online Booking`, `Gate Location`, `Food and Drink`,
`Online Boarding`, `Seat Comfort`, `In-flight Entertainment`,
`On-board Service`, `Leg Room Service`, `Baggage Handling`,
`Check-in Service`, `In-flight Service`, `Cleanliness`,
Satisfaction_Num)
head(sem_data)
# A tibble: 6 × 15
`In-flight Wifi Service` Departure and Arrival Time C…¹ Ease of Online Booki…²
<dbl> <dbl> <dbl>
1 3 3 3
2 2 2 2
3 4 4 4
4 2 2 2
5 3 3 3
6 4 4 4
# ℹ abbreviated names: ¹`Departure and Arrival Time Convenience`,
# ²`Ease of Online Booking`
# ℹ 12 more variables: `Gate Location` <dbl>, `Food and Drink` <dbl>,
# `Online Boarding` <dbl>, `Seat Comfort` <dbl>,
# `In-flight Entertainment` <dbl>, `On-board Service` <dbl>,
# `Leg Room Service` <dbl>, `Baggage Handling` <dbl>,
# `Check-in Service` <dbl>, `In-flight Service` <dbl>, Cleanliness <dbl>, …
Modeling SEM-PLS
Spesifikasi Outer
Model
measurement_model <- constructs(
composite(
"Layanan_Digital",
c(
"Ease of Online Booking",
"Online Boarding",
"In-flight Wifi Service"
),
weights = mode_A
),
composite(
"Layanan_Darat",
single_item("Check-in Service")
),
composite(
"Kenyamanan_Kabin",
c(
"Seat Comfort",
"Cleanliness",
"Food and Drink",
"In-flight Entertainment"
),
weights = mode_A
),
composite(
"Awak_Kabin",
c(
"On-board Service",
"In-flight Service",
"Baggage Handling"
),
weights = mode_A
),
composite(
"Kepuasan",
single_item("Satisfaction_Num")
)
)
Spesifikasi Inner
Model
structural_model <- relationships(
paths(
from = c(
"Layanan_Digital",
"Layanan_Darat",
"Kenyamanan_Kabin",
"Awak_Kabin"
),
to = "Kepuasan"
)
)
Estimasi Model
SEM-PLS
pls_model <- estimate_pls(
data = sem_data,
measurement_model = measurement_model,
structural_model = structural_model
)
summary_pls <- summary(pls_model)
summary_pls
Results from package seminr (2.4.2)
Path Coefficients:
Kepuasan
R^2 0.327
AdjR^2 0.327
Layanan_Digital 0.348
Layanan_Darat 0.094
Kenyamanan_Kabin 0.211
Awak_Kabin 0.198
Reliability:
alpha rhoA rhoC AVE
Layanan_Digital 0.769 0.932 0.846 0.649
Layanan_Darat 1.000 1.000 1.000 1.000
Kenyamanan_Kabin 0.877 0.907 0.914 0.727
Awak_Kabin 0.797 0.813 0.879 0.709
Kepuasan 1.000 1.000 1.000 1.000
Alpha, rhoA, and rhoC should exceed 0.7 while AVE should exceed 0.5
Hasil Awal
cat("Kekuatan Pengaruh Langsung (Path Coefficients):\n")
Kekuatan Pengaruh Langsung (Path Coefficients):
Kepuasan
R^2 0.327
AdjR^2 0.327
Layanan_Digital 0.348
Layanan_Darat 0.094
Kenyamanan_Kabin 0.211
Awak_Kabin 0.198
Evaluasi Model
Loading Factors
Layanan_Digital Layanan_Darat Kenyamanan_Kabin
Ease of Online Booking 0.725 0.000 0.000
Online Boarding 0.883 0.000 0.000
In-flight Wifi Service 0.800 0.000 0.000
Check-in Service 0.000 1.000 0.000
Seat Comfort 0.000 0.000 0.850
Cleanliness 0.000 0.000 0.883
Food and Drink 0.000 0.000 0.794
In-flight Entertainment 0.000 0.000 0.880
On-board Service 0.000 0.000 0.000
In-flight Service 0.000 0.000 0.000
Baggage Handling 0.000 0.000 0.000
Satisfaction_Num 0.000 0.000 0.000
Awak_Kabin Kepuasan
Ease of Online Booking 0.000 0.000
Online Boarding 0.000 0.000
In-flight Wifi Service 0.000 0.000
Check-in Service 0.000 0.000
Seat Comfort 0.000 0.000
Cleanliness 0.000 0.000
Food and Drink 0.000 0.000
In-flight Entertainment 0.000 0.000
On-board Service 0.853 0.000
In-flight Service 0.842 0.000
Baggage Handling 0.830 0.000
Satisfaction_Num 0.000 1.000
Reliabilitas Konstruk
alpha rhoA rhoC AVE
Layanan_Digital 0.769 0.932 0.846 0.649
Layanan_Darat 1.000 1.000 1.000 1.000
Kenyamanan_Kabin 0.877 0.907 0.914 0.727
Awak_Kabin 0.797 0.813 0.879 0.709
Kepuasan 1.000 1.000 1.000 1.000
Alpha, rhoA, and rhoC should exceed 0.7 while AVE should exceed 0.5
Validitas Diskriminan
Layanan_Digital Layanan_Darat Kenyamanan_Kabin Awak_Kabin
Layanan_Digital . . . .
Layanan_Darat 0.118 . . .
Kenyamanan_Kabin 0.284 0.179 . .
Awak_Kabin 0.158 0.317 0.265 .
Kepuasan 0.439 0.237 0.395 0.361
Kepuasan
Layanan_Digital .
Layanan_Darat .
Kenyamanan_Kabin .
Awak_Kabin .
Kepuasan .
Evaluasi Inner
# Path Coefficient
path_coefficient <- summary_pls$paths
path_coefficient
Kepuasan
R^2 0.327
AdjR^2 0.327
Layanan_Digital 0.348
Layanan_Darat 0.094
Kenyamanan_Kabin 0.211
Awak_Kabin 0.198
# R-Square
r_square <- summary_pls$r_squared
r_square
NULL
# f-square
summary_pls$fSquare
Layanan_Digital Layanan_Darat Kenyamanan_Kabin Awak_Kabin
Layanan_Digital 0.000 0.000 0.000 0.000
Layanan_Darat 0.000 0.000 0.000 0.000
Kenyamanan_Kabin 0.000 0.000 0.000 0.000
Awak_Kabin 0.000 0.000 0.000 0.000
Kepuasan 0.000 0.000 0.000 0.000
Kepuasan
Layanan_Digital 0.161
Layanan_Darat 0.012
Kenyamanan_Kabin 0.056
Awak_Kabin 0.051
Kepuasan 0.000
Pengujian
boot_model <- bootstrap_model(seminr_model = pls_model, nboot = 500)
summary_boot <- summary(boot_model)
cat("F-Square\n")
F-Square
print(summary_pls$fSquare)
Layanan_Digital Layanan_Darat Kenyamanan_Kabin Awak_Kabin
Layanan_Digital 0.000 0.000 0.000 0.000
Layanan_Darat 0.000 0.000 0.000 0.000
Kenyamanan_Kabin 0.000 0.000 0.000 0.000
Awak_Kabin 0.000 0.000 0.000 0.000
Kepuasan 0.000 0.000 0.000 0.000
Kepuasan
Layanan_Digital 0.161
Layanan_Darat 0.012
Kenyamanan_Kabin 0.056
Awak_Kabin 0.051
Kepuasan 0.000
cat("Hasil Uji Hipotesis\n")
Hasil Uji Hipotesis
print(summary_boot$bootstrapped_paths)
Original Est. Bootstrap Mean Bootstrap SD
Layanan_Digital -> Kepuasan 0.348 0.348 0.002
Layanan_Darat -> Kepuasan 0.094 0.094 0.002
Kenyamanan_Kabin -> Kepuasan 0.211 0.211 0.002
Awak_Kabin -> Kepuasan 0.198 0.198 0.002
T Stat. 2.5% CI 97.5% CI Bootstrap P Val
Layanan_Digital -> Kepuasan 150.532 0.343 0.352 0.000
Layanan_Darat -> Kepuasan 40.495 0.089 0.098 0.000
Kenyamanan_Kabin -> Kepuasan 90.119 0.206 0.216 0.000
Awak_Kabin -> Kepuasan 81.539 0.194 0.203 0.000
Visualisasi Diagram
Model SEM PLS
plot(
pls_model,
title = "PLS-SEM Airline Satisfaction"
)