Implementasi Principal Component Analysis (PCA) dan Factor Analysis (FA) pada Dataset Gen Z Mental Wellness
Nurlaila (205) & Lailil (036)
2026-03-02
1 Import data & libraries
1.1 Load libraries
# Load libraries
library(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, unionlibrary(psych)
library(tidyr)
library(factoextra)## Loading required package: ggplot2##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alpha## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBalibrary(knitr)
library(kableExtra)##
## Attaching package: 'kableExtra'## The following object is masked from 'package:dplyr':
##
## group_rows1.2 Import
data <- read.csv("genz_mental_wellness_synthetic_dataset.csv")
head(data)## Age Gender Country Student_Working_Status Daily_Social_Media_Hours
## 1 24 Male Canada Working 4.81
## 2 21 Male USA Student 4.16
## 3 25 Male Pakistan Student 3.07
## 4 22 Female Pakistan Student 4.41
## 5 24 Male Pakistan Student 2.97
## 6 20 Male Australia Both 6.06
## Screen_Time_Hours Night_Scrolling_Frequency Online_Gaming_Hours
## 1 6.93 2.61 2.07
## 2 7.94 1.85 3.58
## 3 7.45 2.96 2.85
## 4 7.34 4.51 3.37
## 5 5.76 2.36 1.77
## 6 8.75 4.60 0.61
## Content_Type_Preference Exercise_Frequency_per_Week Daily_Sleep_Hours
## 1 News 5.41 6.84
## 2 Gaming 3.41 7.88
## 3 Entertainment 3.40 6.39
## 4 Educational 2.19 7.92
## 5 Educational 4.93 5.97
## 6 Gaming 5.51 6.70
## Caffeine_Intake_Cups Study_Work_Hours_per_Day Overthinking_Score
## 1 1.52 11.42 4.95
## 2 2.23 6.98 5.91
## 3 0.53 7.79 4.06
## 4 0.58 6.61 6.10
## 5 1.64 4.81 5.22
## 6 0.00 6.44 6.19
## Anxiety_Score Mood_Stability_Score Social_Comparison_Index
## 1 4.13 5.74 4.67
## 2 3.63 5.75 5.38
## 3 5.67 6.03 2.41
## 4 4.78 4.85 5.86
## 5 4.23 5.05 5.54
## 6 4.29 3.21 5.99
## Sleep_Quality_Score Motivation_Level Emotional_Fatigue_Score Wellbeing_Index
## 1 6.27 6.13 6.45 4.28
## 2 7.37 6.27 3.74 5.23
## 3 6.48 4.82 6.69 3.72
## 4 7.27 5.17 5.96 3.97
## 5 6.34 5.72 2.22 4.63
## 6 7.55 4.88 6.35 3.44
## Burnout_Risk
## 1 Medium
## 2 Medium
## 3 High
## 4 High
## 5 Medium
## 6 High1.3 Cek karakteristik data
str(data)## 'data.frame': 10000 obs. of 22 variables:
## $ Age : int 24 21 25 22 24 20 24 25 22 21 ...
## $ Gender : chr "Male" "Male" "Male" "Female" ...
## $ Country : chr "Canada" "USA" "Pakistan" "Pakistan" ...
## $ Student_Working_Status : chr "Working" "Student" "Student" "Student" ...
## $ Daily_Social_Media_Hours : num 4.81 4.16 3.07 4.41 2.97 6.06 3.68 4.64 6.5 3.73 ...
## $ Screen_Time_Hours : num 6.93 7.94 7.45 7.34 5.76 8.75 6.15 6.7 9.61 5.97 ...
## $ Night_Scrolling_Frequency : num 2.61 1.85 2.96 4.51 2.36 4.6 1.68 4.24 4.33 4.26 ...
## $ Online_Gaming_Hours : num 2.07 3.58 2.85 3.37 1.77 0.61 1.65 1.66 0 0.98 ...
## $ Content_Type_Preference : chr "News" "Gaming" "Entertainment" "Educational" ...
## $ Exercise_Frequency_per_Week: num 5.41 3.41 3.4 2.19 4.93 5.51 3.61 2.21 1.41 1.94 ...
## $ Daily_Sleep_Hours : num 6.84 7.88 6.39 7.92 5.97 6.7 5.18 6.27 6.78 4.65 ...
## $ Caffeine_Intake_Cups : num 1.52 2.23 0.53 0.58 1.64 0 1.5 2.46 1.89 2.9 ...
## $ Study_Work_Hours_per_Day : num 11.42 6.98 7.79 6.61 4.81 ...
## $ Overthinking_Score : num 4.95 5.91 4.06 6.1 5.22 6.19 5.31 4.07 5.32 4.46 ...
## $ Anxiety_Score : num 4.13 3.63 5.67 4.78 4.23 4.29 5.29 4.36 5.26 4.67 ...
## $ Mood_Stability_Score : num 5.74 5.75 6.03 4.85 5.05 3.21 6.23 3.68 3.54 5.91 ...
## $ Social_Comparison_Index : num 4.67 5.38 2.41 5.86 5.54 5.99 3.07 4.16 5.15 4.63 ...
## $ Sleep_Quality_Score : num 6.27 7.37 6.48 7.27 6.34 7.55 4.79 7.18 7.17 4.61 ...
## $ Motivation_Level : num 6.13 6.27 4.82 5.17 5.72 4.88 5.51 2.8 4.51 6.06 ...
## $ Emotional_Fatigue_Score : num 6.45 3.74 6.69 5.96 2.22 6.35 5.87 6.03 5.59 5.38 ...
## $ Wellbeing_Index : num 4.28 5.23 3.72 3.97 4.63 3.44 3.65 2.82 3.27 3.85 ...
## $ Burnout_Risk : chr "Medium" "Medium" "High" "High" ...dim(data)## [1] 10000 22summary(data)## Age Gender Country Student_Working_Status
## Min. :18.00 Length:10000 Length:10000 Length:10000
## 1st Qu.:20.00 Class :character Class :character Class :character
## Median :22.00 Mode :character Mode :character Mode :character
## Mean :21.99
## 3rd Qu.:24.00
## Max. :26.00
## Daily_Social_Media_Hours Screen_Time_Hours Night_Scrolling_Frequency
## Min. : 0.500 Min. : 2.000 Min. :0.000
## 1st Qu.: 3.010 1st Qu.: 5.810 1st Qu.:2.188
## Median : 3.990 Median : 7.000 Median :2.980
## Mean : 4.006 Mean : 7.017 Mean :2.986
## 3rd Qu.: 4.982 3rd Qu.: 8.210 3rd Qu.:3.790
## Max. :10.000 Max. :14.000 Max. :7.000
## Online_Gaming_Hours Content_Type_Preference Exercise_Frequency_per_Week
## Min. :0.000 Length:10000 Min. :0.000
## 1st Qu.:0.470 Class :character 1st Qu.:1.960
## Median :1.460 Mode :character Median :3.010
## Mean :1.607 Mean :2.995
## 3rd Qu.:2.500 3rd Qu.:4.000
## Max. :6.000 Max. :7.000
## Daily_Sleep_Hours Caffeine_Intake_Cups Study_Work_Hours_per_Day
## Min. : 3.000 Min. :0.000 Min. : 1.000
## 1st Qu.: 5.710 1st Qu.:0.800 1st Qu.: 4.700
## Median : 6.520 Median :1.480 Median : 6.030
## Mean : 6.512 Mean :1.506 Mean : 6.031
## 3rd Qu.: 7.320 3rd Qu.:2.150 3rd Qu.: 7.340
## Max. :10.000 Max. :6.000 Max. :13.050
## Overthinking_Score Anxiety_Score Mood_Stability_Score
## Min. :1.000 Min. :1.000 Min. : 1.000
## 1st Qu.:4.240 1st Qu.:3.840 1st Qu.: 4.310
## Median :5.000 Median :4.740 Median : 5.170
## Mean :5.002 Mean :4.748 Mean : 5.161
## 3rd Qu.:5.760 3rd Qu.:5.630 3rd Qu.: 6.000
## Max. :9.510 Max. :9.690 Max. :10.000
## Social_Comparison_Index Sleep_Quality_Score Motivation_Level
## Min. :1.000 Min. : 1.020 Min. : 1.000
## 1st Qu.:3.470 1st Qu.: 5.550 1st Qu.: 4.200
## Median :4.400 Median : 6.530 Median : 5.080
## Mean :4.404 Mean : 6.514 Mean : 5.086
## 3rd Qu.:5.320 3rd Qu.: 7.490 3rd Qu.: 5.950
## Max. :9.420 Max. :10.000 Max. :10.000
## Emotional_Fatigue_Score Wellbeing_Index Burnout_Risk
## Min. : 1.000 Min. :1.00 Length:10000
## 1st Qu.: 4.620 1st Qu.:3.02 Class :character
## Median : 5.580 Median :3.87 Mode :character
## Mean : 5.582 Mean :3.87
## 3rd Qu.: 6.540 3rd Qu.:4.70
## Max. :10.000 Max. :8.86colnames(data)## [1] "Age" "Gender"
## [3] "Country" "Student_Working_Status"
## [5] "Daily_Social_Media_Hours" "Screen_Time_Hours"
## [7] "Night_Scrolling_Frequency" "Online_Gaming_Hours"
## [9] "Content_Type_Preference" "Exercise_Frequency_per_Week"
## [11] "Daily_Sleep_Hours" "Caffeine_Intake_Cups"
## [13] "Study_Work_Hours_per_Day" "Overthinking_Score"
## [15] "Anxiety_Score" "Mood_Stability_Score"
## [17] "Social_Comparison_Index" "Sleep_Quality_Score"
## [19] "Motivation_Level" "Emotional_Fatigue_Score"
## [21] "Wellbeing_Index" "Burnout_Risk"1.4 Cek type variabel
struktur_data <- data.frame(
Nama_Variabel = names(data),
Tipe_Data = sapply(data, class)
)
kable(struktur_data, caption = "Struktur Variabel Dataset") %>%
kable_styling(bootstrap_options = c("striped","hover","condensed"))| Nama_Variabel | Tipe_Data | |
|---|---|---|
| Age | Age | integer |
| Gender | Gender | character |
| Country | Country | character |
| Student_Working_Status | Student_Working_Status | character |
| Daily_Social_Media_Hours | Daily_Social_Media_Hours | numeric |
| Screen_Time_Hours | Screen_Time_Hours | numeric |
| Night_Scrolling_Frequency | Night_Scrolling_Frequency | numeric |
| Online_Gaming_Hours | Online_Gaming_Hours | numeric |
| Content_Type_Preference | Content_Type_Preference | character |
| Exercise_Frequency_per_Week | Exercise_Frequency_per_Week | numeric |
| Daily_Sleep_Hours | Daily_Sleep_Hours | numeric |
| Caffeine_Intake_Cups | Caffeine_Intake_Cups | numeric |
| Study_Work_Hours_per_Day | Study_Work_Hours_per_Day | numeric |
| Overthinking_Score | Overthinking_Score | numeric |
| Anxiety_Score | Anxiety_Score | numeric |
| Mood_Stability_Score | Mood_Stability_Score | numeric |
| Social_Comparison_Index | Social_Comparison_Index | numeric |
| Sleep_Quality_Score | Sleep_Quality_Score | numeric |
| Motivation_Level | Motivation_Level | numeric |
| Emotional_Fatigue_Score | Emotional_Fatigue_Score | numeric |
| Wellbeing_Index | Wellbeing_Index | numeric |
| Burnout_Risk | Burnout_Risk | character |
1.5 Pilah variabel
hanya memakai variabel numeric
data_pca <- data[, sapply(data, is.numeric)]
head(data_pca)## Age Daily_Social_Media_Hours Screen_Time_Hours Night_Scrolling_Frequency
## 1 24 4.81 6.93 2.61
## 2 21 4.16 7.94 1.85
## 3 25 3.07 7.45 2.96
## 4 22 4.41 7.34 4.51
## 5 24 2.97 5.76 2.36
## 6 20 6.06 8.75 4.60
## Online_Gaming_Hours Exercise_Frequency_per_Week Daily_Sleep_Hours
## 1 2.07 5.41 6.84
## 2 3.58 3.41 7.88
## 3 2.85 3.40 6.39
## 4 3.37 2.19 7.92
## 5 1.77 4.93 5.97
## 6 0.61 5.51 6.70
## Caffeine_Intake_Cups Study_Work_Hours_per_Day Overthinking_Score
## 1 1.52 11.42 4.95
## 2 2.23 6.98 5.91
## 3 0.53 7.79 4.06
## 4 0.58 6.61 6.10
## 5 1.64 4.81 5.22
## 6 0.00 6.44 6.19
## Anxiety_Score Mood_Stability_Score Social_Comparison_Index
## 1 4.13 5.74 4.67
## 2 3.63 5.75 5.38
## 3 5.67 6.03 2.41
## 4 4.78 4.85 5.86
## 5 4.23 5.05 5.54
## 6 4.29 3.21 5.99
## Sleep_Quality_Score Motivation_Level Emotional_Fatigue_Score Wellbeing_Index
## 1 6.27 6.13 6.45 4.28
## 2 7.37 6.27 3.74 5.23
## 3 6.48 4.82 6.69 3.72
## 4 7.27 5.17 5.96 3.97
## 5 6.34 5.72 2.22 4.63
## 6 7.55 4.88 6.35 3.441.6 Statistik deskriptif
data.frame(
Variabel = colnames(data_pca),
Minimum = apply(data_pca, 2, min),
Maksimum = apply(data_pca, 2, max),
Mean = apply(data_pca, 2, mean),
SD = apply(data_pca, 2, sd)
)## Variabel Minimum Maksimum
## Age Age 18.00 26.00
## Daily_Social_Media_Hours Daily_Social_Media_Hours 0.50 10.00
## Screen_Time_Hours Screen_Time_Hours 2.00 14.00
## Night_Scrolling_Frequency Night_Scrolling_Frequency 0.00 7.00
## Online_Gaming_Hours Online_Gaming_Hours 0.00 6.00
## Exercise_Frequency_per_Week Exercise_Frequency_per_Week 0.00 7.00
## Daily_Sleep_Hours Daily_Sleep_Hours 3.00 10.00
## Caffeine_Intake_Cups Caffeine_Intake_Cups 0.00 6.00
## Study_Work_Hours_per_Day Study_Work_Hours_per_Day 1.00 13.05
## Overthinking_Score Overthinking_Score 1.00 9.51
## Anxiety_Score Anxiety_Score 1.00 9.69
## Mood_Stability_Score Mood_Stability_Score 1.00 10.00
## Social_Comparison_Index Social_Comparison_Index 1.00 9.42
## Sleep_Quality_Score Sleep_Quality_Score 1.02 10.00
## Motivation_Level Motivation_Level 1.00 10.00
## Emotional_Fatigue_Score Emotional_Fatigue_Score 1.00 10.00
## Wellbeing_Index Wellbeing_Index 1.00 8.86
## Mean SD
## Age 21.992900 2.5893088
## Daily_Social_Media_Hours 4.005883 1.4805089
## Screen_Time_Hours 7.016991 1.7925289
## Night_Scrolling_Frequency 2.986009 1.1970353
## Online_Gaming_Hours 1.607241 1.3000446
## Exercise_Frequency_per_Week 2.994855 1.4782478
## Daily_Sleep_Hours 6.512031 1.1941936
## Caffeine_Intake_Cups 1.505871 0.9340687
## Study_Work_Hours_per_Day 6.030983 1.9753370
## Overthinking_Score 5.001868 1.1431790
## Anxiety_Score 4.747556 1.3055925
## Mood_Stability_Score 5.161021 1.2570548
## Social_Comparison_Index 4.403556 1.3364786
## Sleep_Quality_Score 6.514447 1.4278061
## Motivation_Level 5.086132 1.3083508
## Emotional_Fatigue_Score 5.582222 1.4165579
## Wellbeing_Index 3.870213 1.2389397data_pca <- as.data.frame(data_pca)
data_long <- tidyr::pivot_longer(data_pca,
cols = everything(),
names_to = "variable",
values_to = "value")
ggplot(data_long, aes(variable, value)) +
geom_boxplot(fill = "lightblue") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
labs(title = "Boxplot 17 Variabel Numerik (EDA)")
1.7 Cek missing value
missing_jumlah <- colSums(is.na(data_pca))
tabel_missing <- data.frame(
Nama_Variabel = names(missing_jumlah),
Jumlah_Missing = missing_jumlah
)
tabel_missing## Nama_Variabel Jumlah_Missing
## Age Age 0
## Daily_Social_Media_Hours Daily_Social_Media_Hours 0
## Screen_Time_Hours Screen_Time_Hours 0
## Night_Scrolling_Frequency Night_Scrolling_Frequency 0
## Online_Gaming_Hours Online_Gaming_Hours 0
## Exercise_Frequency_per_Week Exercise_Frequency_per_Week 0
## Daily_Sleep_Hours Daily_Sleep_Hours 0
## Caffeine_Intake_Cups Caffeine_Intake_Cups 0
## Study_Work_Hours_per_Day Study_Work_Hours_per_Day 0
## Overthinking_Score Overthinking_Score 0
## Anxiety_Score Anxiety_Score 0
## Mood_Stability_Score Mood_Stability_Score 0
## Social_Comparison_Index Social_Comparison_Index 0
## Sleep_Quality_Score Sleep_Quality_Score 0
## Motivation_Level Motivation_Level 0
## Emotional_Fatigue_Score Emotional_Fatigue_Score 0
## Wellbeing_Index Wellbeing_Index 01.8 Standarisasi
## Standarisasi
data_scaled <- scale(data_pca)
data_scaled_df <- as.data.frame(data_scaled)
head(data_scaled_df) %>%
kable(caption = "Data Setelah Standarisasi (6 Observasi Pertama)") %>%
kable_styling(
bootstrap_options = c("striped","hover","condensed"),
full_width = FALSE
)| Age | Daily_Social_Media_Hours | Screen_Time_Hours | Night_Scrolling_Frequency | Online_Gaming_Hours | Exercise_Frequency_per_Week | Daily_Sleep_Hours | Caffeine_Intake_Cups | Study_Work_Hours_per_Day | Overthinking_Score | Anxiety_Score | Mood_Stability_Score | Social_Comparison_Index | Sleep_Quality_Score | Motivation_Level | Emotional_Fatigue_Score | Wellbeing_Index |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.7751490 | 0.5431355 | -0.0485298 | -0.3141169 | 0.3559563 | 1.6337890 | 0.2746364 | 0.0151263 | 2.7281506 | -0.0453717 | -0.4730082 | 0.4605837 | 0.1993627 | -0.1712046 | 0.7978502 | 0.6125962 | 0.3307562 |
| -0.3834614 | 0.1040973 | 0.5149200 | -0.9490188 | 1.5174549 | 0.2808359 | 1.1455169 | 0.7752417 | 0.4804330 | 0.7943918 | -0.8559761 | 0.4685388 | 0.7306095 | 0.5992081 | 0.9048552 | -1.3004919 | 1.0975409 |
| 1.1613524 | -0.6321360 | 0.2415632 | -0.0217278 | 0.9559357 | 0.2740711 | -0.1021869 | -1.0447529 | 0.8904896 | -0.8239025 | 0.7065328 | 0.6912817 | -1.4916483 | -0.0241258 | -0.2034103 | 0.7820210 | -0.1212432 |
| 0.0027420 | 0.2729582 | 0.1801974 | 1.2731379 | 1.3559220 | -0.5444655 | 1.1790123 | -0.9912237 | 0.2931231 | 0.9605950 | 0.0248500 | -0.2474204 | 1.0897623 | 0.5291706 | 0.0641021 | 0.2666873 | 0.0805423 |
| 0.7751490 | -0.6996803 | -0.7012389 | -0.5229662 | 0.1251949 | 1.3090802 | -0.4538887 | 0.1435965 | -0.6181138 | 0.1908118 | -0.3964146 | -0.0883183 | 0.8503271 | -0.1221784 | 0.4844786 | -2.3735154 | 0.6132558 |
| -0.7696649 | 1.3874398 | 0.9667956 | 1.3483237 | -0.7670822 | 1.7014366 | 0.1574024 | -1.6121630 | 0.2070619 | 1.0393228 | -0.3504585 | -1.5520572 | 1.1870328 | 0.7252756 | -0.1575510 | 0.5420026 | -0.3472429 |
1.9 Cek korelasi
cor_matrix <- cor(data_scaled)
round(cor_matrix, 2)## Age Daily_Social_Media_Hours Screen_Time_Hours
## Age 1.00 0.00 0.00
## Daily_Social_Media_Hours 0.00 1.00 0.83
## Screen_Time_Hours 0.00 0.83 1.00
## Night_Scrolling_Frequency 0.00 -0.01 -0.01
## Online_Gaming_Hours 0.00 0.00 -0.01
## Exercise_Frequency_per_Week -0.01 0.00 0.00
## Daily_Sleep_Hours 0.02 -0.01 -0.01
## Caffeine_Intake_Cups 0.00 0.00 0.00
## Study_Work_Hours_per_Day 0.01 0.01 0.00
## Overthinking_Score 0.00 0.26 0.21
## Anxiety_Score -0.01 0.11 0.10
## Mood_Stability_Score 0.00 -0.08 -0.07
## Social_Comparison_Index 0.00 0.66 0.56
## Sleep_Quality_Score 0.02 -0.01 -0.02
## Motivation_Level 0.01 -0.04 -0.03
## Emotional_Fatigue_Score 0.02 0.38 0.44
## Wellbeing_Index 0.01 -0.13 -0.14
## Night_Scrolling_Frequency Online_Gaming_Hours
## Age 0.00 0.00
## Daily_Social_Media_Hours -0.01 0.00
## Screen_Time_Hours -0.01 -0.01
## Night_Scrolling_Frequency 1.00 0.01
## Online_Gaming_Hours 0.01 1.00
## Exercise_Frequency_per_Week -0.01 0.00
## Daily_Sleep_Hours 0.00 -0.01
## Caffeine_Intake_Cups 0.00 -0.01
## Study_Work_Hours_per_Day 0.01 0.01
## Overthinking_Score 0.42 -0.02
## Anxiety_Score 0.20 0.00
## Mood_Stability_Score -0.12 0.01
## Social_Comparison_Index -0.01 -0.01
## Sleep_Quality_Score 0.00 0.00
## Motivation_Level -0.07 -0.01
## Emotional_Fatigue_Score 0.10 0.00
## Wellbeing_Index -0.12 0.00
## Exercise_Frequency_per_Week Daily_Sleep_Hours
## Age -0.01 0.02
## Daily_Social_Media_Hours 0.00 -0.01
## Screen_Time_Hours 0.00 -0.01
## Night_Scrolling_Frequency -0.01 0.00
## Online_Gaming_Hours 0.00 -0.01
## Exercise_Frequency_per_Week 1.00 0.00
## Daily_Sleep_Hours 0.00 1.00
## Caffeine_Intake_Cups 0.00 -0.01
## Study_Work_Hours_per_Day 0.00 -0.01
## Overthinking_Score -0.01 0.00
## Anxiety_Score 0.00 -0.45
## Mood_Stability_Score 0.01 0.28
## Social_Comparison_Index -0.02 -0.01
## Sleep_Quality_Score 0.00 0.83
## Motivation_Level 0.34 0.50
## Emotional_Fatigue_Score -0.31 -0.22
## Wellbeing_Index 0.18 0.70
## Caffeine_Intake_Cups Study_Work_Hours_per_Day
## Age 0.00 0.01
## Daily_Social_Media_Hours 0.00 0.01
## Screen_Time_Hours 0.00 0.00
## Night_Scrolling_Frequency 0.00 0.01
## Online_Gaming_Hours -0.01 0.01
## Exercise_Frequency_per_Week 0.00 0.00
## Daily_Sleep_Hours -0.01 -0.01
## Caffeine_Intake_Cups 1.00 -0.01
## Study_Work_Hours_per_Day -0.01 1.00
## Overthinking_Score -0.01 0.01
## Anxiety_Score 0.00 0.02
## Mood_Stability_Score -0.01 -0.01
## Social_Comparison_Index -0.01 0.00
## Sleep_Quality_Score -0.01 -0.02
## Motivation_Level 0.00 -0.01
## Emotional_Fatigue_Score 0.01 0.01
## Wellbeing_Index -0.01 -0.02
## Overthinking_Score Anxiety_Score
## Age 0.00 -0.01
## Daily_Social_Media_Hours 0.26 0.11
## Screen_Time_Hours 0.21 0.10
## Night_Scrolling_Frequency 0.42 0.20
## Online_Gaming_Hours -0.02 0.00
## Exercise_Frequency_per_Week -0.01 0.00
## Daily_Sleep_Hours 0.00 -0.45
## Caffeine_Intake_Cups -0.01 0.00
## Study_Work_Hours_per_Day 0.01 0.02
## Overthinking_Score 1.00 0.44
## Anxiety_Score 0.44 1.00
## Mood_Stability_Score -0.27 -0.62
## Social_Comparison_Index 0.16 0.08
## Sleep_Quality_Score 0.00 -0.37
## Motivation_Level -0.15 -0.46
## Emotional_Fatigue_Score 0.29 0.50
## Wellbeing_Index -0.28 -0.78
## Mood_Stability_Score Social_Comparison_Index
## Age 0.00 0.00
## Daily_Social_Media_Hours -0.08 0.66
## Screen_Time_Hours -0.07 0.56
## Night_Scrolling_Frequency -0.12 -0.01
## Online_Gaming_Hours 0.01 -0.01
## Exercise_Frequency_per_Week 0.01 -0.02
## Daily_Sleep_Hours 0.28 -0.01
## Caffeine_Intake_Cups -0.01 -0.01
## Study_Work_Hours_per_Day -0.01 0.00
## Overthinking_Score -0.27 0.16
## Anxiety_Score -0.62 0.08
## Mood_Stability_Score 1.00 -0.06
## Social_Comparison_Index -0.06 1.00
## Sleep_Quality_Score 0.23 -0.02
## Motivation_Level 0.29 -0.03
## Emotional_Fatigue_Score -0.31 0.26
## Wellbeing_Index 0.69 -0.10
## Sleep_Quality_Score Motivation_Level
## Age 0.02 0.01
## Daily_Social_Media_Hours -0.01 -0.04
## Screen_Time_Hours -0.02 -0.03
## Night_Scrolling_Frequency 0.00 -0.07
## Online_Gaming_Hours 0.00 -0.01
## Exercise_Frequency_per_Week 0.00 0.34
## Daily_Sleep_Hours 0.83 0.50
## Caffeine_Intake_Cups -0.01 0.00
## Study_Work_Hours_per_Day -0.02 -0.01
## Overthinking_Score 0.00 -0.15
## Anxiety_Score -0.37 -0.46
## Mood_Stability_Score 0.23 0.29
## Social_Comparison_Index -0.02 -0.03
## Sleep_Quality_Score 1.00 0.40
## Motivation_Level 0.40 1.00
## Emotional_Fatigue_Score -0.19 -0.34
## Wellbeing_Index 0.70 0.74
## Emotional_Fatigue_Score Wellbeing_Index
## Age 0.02 0.01
## Daily_Social_Media_Hours 0.38 -0.13
## Screen_Time_Hours 0.44 -0.14
## Night_Scrolling_Frequency 0.10 -0.12
## Online_Gaming_Hours 0.00 0.00
## Exercise_Frequency_per_Week -0.31 0.18
## Daily_Sleep_Hours -0.22 0.70
## Caffeine_Intake_Cups 0.01 -0.01
## Study_Work_Hours_per_Day 0.01 -0.02
## Overthinking_Score 0.29 -0.28
## Anxiety_Score 0.50 -0.78
## Mood_Stability_Score -0.31 0.69
## Social_Comparison_Index 0.26 -0.10
## Sleep_Quality_Score -0.19 0.70
## Motivation_Level -0.34 0.74
## Emotional_Fatigue_Score 1.00 -0.57
## Wellbeing_Index -0.57 1.00library(corrplot)## corrplot 0.95 loadedcorrplot(cor_matrix, method = "color", type = "upper")
# Uji kelayakan PCA
1.10 Uji KMO
kmo_result <- KMO(data_scaled)
kmo_per_var <- data.frame(
Variabel = names(kmo_result$MSAi),
MSA = round(kmo_result$MSAi, 4)
)
kable(kmo_per_var, caption = "Nilai MSA Setiap Variabel") %>%
kable_styling(
bootstrap_options = c("striped","hover","condensed"),
full_width = FALSE
)| Variabel | MSA | |
|---|---|---|
| Age | Age | 0.7771 |
| Daily_Social_Media_Hours | Daily_Social_Media_Hours | 0.6649 |
| Screen_Time_Hours | Screen_Time_Hours | 0.7141 |
| Night_Scrolling_Frequency | Night_Scrolling_Frequency | 0.6272 |
| Online_Gaming_Hours | Online_Gaming_Hours | 0.3616 |
| Exercise_Frequency_per_Week | Exercise_Frequency_per_Week | 0.8097 |
| Daily_Sleep_Hours | Daily_Sleep_Hours | 0.9635 |
| Caffeine_Intake_Cups | Caffeine_Intake_Cups | 0.4511 |
| Study_Work_Hours_per_Day | Study_Work_Hours_per_Day | 0.6613 |
| Overthinking_Score | Overthinking_Score | 0.7841 |
| Anxiety_Score | Anxiety_Score | 0.3570 |
| Mood_Stability_Score | Mood_Stability_Score | 0.2268 |
| Social_Comparison_Index | Social_Comparison_Index | 0.8204 |
| Sleep_Quality_Score | Sleep_Quality_Score | 0.2612 |
| Motivation_Level | Motivation_Level | 0.2567 |
| Emotional_Fatigue_Score | Emotional_Fatigue_Score | 0.2658 |
| Wellbeing_Index | Wellbeing_Index | 0.4049 |
# Ambil nama variabel dengan MSA >= 0.5
variabel_lolos <- names(kmo_result$MSAi[kmo_result$MSAi >= 0.5])
variabel_lolos## [1] "Age" "Daily_Social_Media_Hours"
## [3] "Screen_Time_Hours" "Night_Scrolling_Frequency"
## [5] "Exercise_Frequency_per_Week" "Daily_Sleep_Hours"
## [7] "Study_Work_Hours_per_Day" "Overthinking_Score"
## [9] "Social_Comparison_Index"data_reduced <- data_scaled[, variabel_lolos]
kmo_result2 <- KMO(data_reduced)
kmo_result2$MSA # ini nilai KMO overall## [1] 0.65110461.11 Uji Bartlett
cortest.bartlett(data_reduced)## R was not square, finding R from data## $chisq
## [1] 20178.46
##
## $p.value
## [1] 0
##
## $df
## [1] 362 Uji PCA
pca_awal <- principal(data_reduced, nfactors = ncol(data_reduced), rotate = "none")
pca_awal$values## [1] 2.4693112 1.3638372 1.0232638 1.0108038 0.9946897 0.9713043 0.5508143
## [8] 0.4603357 0.15564012.1 Cek eigeen value
eigen_values <- pca_awal$values
tabel_eigen <- data.frame(
Komponen = paste0("PC", 1:length(eigen_values)),
Eigenvalue = round(eigen_values, 4),
Keputusan = ifelse(eigen_values > 1, "Dipertahankan", "Tidak")
)
kable(tabel_eigen, caption = "Eigenvalue dan Keputusan Jumlah Komponen") %>%
kable_styling(
bootstrap_options = c("striped","hover","condensed"),
full_width = FALSE
)| Komponen | Eigenvalue | Keputusan |
|---|---|---|
| PC1 | 2.4693 | Dipertahankan |
| PC2 | 1.3638 | Dipertahankan |
| PC3 | 1.0233 | Dipertahankan |
| PC4 | 1.0108 | Dipertahankan |
| PC5 | 0.9947 | Tidak |
| PC6 | 0.9713 | Tidak |
| PC7 | 0.5508 | Tidak |
| PC8 | 0.4603 | Tidak |
| PC9 | 0.1556 | Tidak |
2.2 Cek scree plot
library(factoextra)
pca_model <- prcomp(data_reduced, scale. = TRUE)
fviz_eig(
pca_model,
addlabels = TRUE,
ylim = c(0, 30),
barfill = "steelblue",
barcolor = "black",
linecolor = "red"
) +
theme_minimal() +
labs(
title = "Scree Plot PCA",
x = "Principal Component",
y = "Percentage of Variance"
)## Warning in geom_bar(stat = "identity", fill = barfill, color = barcolor, :
## Ignoring empty aesthetic: `width`.
2.3 Cumulative variance
eig_val <- get_eigenvalue(pca_model)
kable(round(eig_val, 3),
caption = "Eigenvalue dan Proporsi Variansi PCA") %>%
kable_styling(
bootstrap_options = c("striped","hover","condensed"),
full_width = FALSE
)| eigenvalue | variance.percent | cumulative.variance.percent | |
|---|---|---|---|
| Dim.1 | 2.469 | 27.437 | 27.437 |
| Dim.2 | 1.364 | 15.154 | 42.591 |
| Dim.3 | 1.023 | 11.370 | 53.960 |
| Dim.4 | 1.011 | 11.231 | 65.191 |
| Dim.5 | 0.995 | 11.052 | 76.243 |
| Dim.6 | 0.971 | 10.792 | 87.036 |
| Dim.7 | 0.551 | 6.120 | 93.156 |
| Dim.8 | 0.460 | 5.115 | 98.271 |
| Dim.9 | 0.156 | 1.729 | 100.000 |
loading <- pca_model$rotation[,1:4]
loading## PC1 PC2 PC3
## Age 0.0003516554 -0.002559084 -0.7198557484
## Daily_Social_Media_Hours 0.5928556718 0.114126095 0.0001264989
## Screen_Time_Hours 0.5642778660 0.125276370 0.0086941392
## Night_Scrolling_Frequency 0.0639021037 -0.739363548 0.0065503297
## Exercise_Frequency_per_Week -0.0072737169 0.016179127 0.4843262920
## Daily_Sleep_Hours -0.0138699487 0.004154051 -0.4526934299
## Study_Work_Hours_per_Day 0.0082282156 -0.015008150 -0.2046220840
## Overthinking_Score 0.2570161068 -0.635494524 0.0076237693
## Social_Comparison_Index 0.5095672427 0.142332379 -0.0160490767
## PC4
## Age 0.0852073844
## Daily_Social_Media_Hours -0.0059975704
## Screen_Time_Hours -0.0119615490
## Night_Scrolling_Frequency -0.0076557108
## Exercise_Frequency_per_Week -0.1345373910
## Daily_Sleep_Hours -0.6252621428
## Study_Work_Hours_per_Day 0.7635662380
## Overthinking_Score -0.0203854508
## Social_Comparison_Index 0.00013785072.4 Score PCA
pca_scores <- as.data.frame(pca_model$x[,1:4])
head(pca_scores)## PC1 PC2 PC3 PC4
## 1 0.3714989 0.3300081 -0.4552307 1.7583269
## 2 0.8539818 0.3802883 -0.2122179 -0.4354741
## 3 -1.2045371 0.2731325 -0.8196846 0.8235825
## 4 1.1370782 -1.3512476 -0.8596091 -0.4728595
## 5 -0.3696210 0.2453183 0.3861757 -0.2854278
## 6 2.3131235 -1.1819287 1.2707594 -0.28603183 Factor Analysis (FA)
fa.parallel(data_reduced, fa = "fa")
## Parallel analysis suggests that the number of factors = 2 and the number of components = NAfa_model <- fa(data_reduced,
nfactors = 2,
rotate = "varimax")
print(fa_model$loadings, cutoff = 0.3)##
## Loadings:
## MR1 MR2
## Age
## Daily_Social_Media_Hours 0.987
## Screen_Time_Hours 0.829
## Night_Scrolling_Frequency 0.533
## Exercise_Frequency_per_Week
## Daily_Sleep_Hours
## Study_Work_Hours_per_Day
## Overthinking_Score 0.806
## Social_Comparison_Index 0.665
##
## MR1 MR2
## SS loadings 2.135 0.959
## Proportion Var 0.237 0.107
## Cumulative Var 0.237 0.344fa_model <- fa(data_reduced,
nfactors = 2,
rotate = "varimax",
scores = "regression")
factor_scores <- as.data.frame(fa_model$scores)
head(factor_scores)## MR1 MR2
## 1 0.52007986 -0.13458932
## 2 0.08223927 0.34668203
## 3 -0.56168220 -0.55596760
## 4 0.17138731 0.96503814
## 5 -0.69278318 0.05565477
## 6 1.26567748 0.96352466