knitr::opts_chunk$set(echo = TRUE, warning = FALSE, message = FALSE)
Import Library
& Membaca Dataset
library(readr)
library(dplyr)
library(psych)
library(factoextra)
library(corrplot)
data <- read.csv("WHR2024.csv")
Menampilkan
Dataset
head(data)
## Country.name Ladder.score upperwhisker lowerwhisker
## 1 Finland 7.741 7.815 7.667
## 2 Denmark 7.583 7.665 7.500
## 3 Iceland 7.525 7.618 7.433
## 4 Sweden 7.344 7.422 7.267
## 5 Israel 7.341 7.405 7.277
## 6 Netherlands 7.319 7.383 7.256
## Explained.by..Log.GDP.per.capita Explained.by..Social.support
## 1 1.844 1.572
## 2 1.908 1.520
## 3 1.881 1.617
## 4 1.878 1.501
## 5 1.803 1.513
## 6 1.901 1.462
## Explained.by..Healthy.life.expectancy
## 1 0.695
## 2 0.699
## 3 0.718
## 4 0.724
## 5 0.740
## 6 0.706
## Explained.by..Freedom.to.make.life.choices Explained.by..Generosity
## 1 0.859 0.142
## 2 0.823 0.204
## 3 0.819 0.258
## 4 0.838 0.221
## 5 0.641 0.153
## 6 0.725 0.247
## Explained.by..Perceptions.of.corruption Dystopia...residual
## 1 0.546 2.082
## 2 0.548 1.881
## 3 0.182 2.050
## 4 0.524 1.658
## 5 0.193 2.298
## 6 0.372 1.906
Cek Struktur
Dataset
str(data)
## 'data.frame': 143 obs. of 11 variables:
## $ Country.name : chr "Finland" "Denmark" "Iceland" "Sweden" ...
## $ Ladder.score : num 7.74 7.58 7.53 7.34 7.34 ...
## $ upperwhisker : num 7.82 7.67 7.62 7.42 7.41 ...
## $ lowerwhisker : num 7.67 7.5 7.43 7.27 7.28 ...
## $ Explained.by..Log.GDP.per.capita : num 1.84 1.91 1.88 1.88 1.8 ...
## $ Explained.by..Social.support : num 1.57 1.52 1.62 1.5 1.51 ...
## $ Explained.by..Healthy.life.expectancy : num 0.695 0.699 0.718 0.724 0.74 0.706 0.704 0.708 0.747 0.692 ...
## $ Explained.by..Freedom.to.make.life.choices: num 0.859 0.823 0.819 0.838 0.641 0.725 0.835 0.801 0.759 0.756 ...
## $ Explained.by..Generosity : num 0.142 0.204 0.258 0.221 0.153 0.247 0.224 0.146 0.173 0.225 ...
## $ Explained.by..Perceptions.of.corruption : num 0.546 0.548 0.182 0.524 0.193 0.372 0.484 0.432 0.498 0.323 ...
## $ Dystopia...residual : num 2.08 1.88 2.05 1.66 2.3 ...
Pembentukan
Variabel Baru dan Seleksi Variabel Penelitian
data <- data %>%
mutate(
GDP_social_interaction =
Explained.by..Log.GDP.per.capita *
Explained.by..Social.support,
health_freedom_index =
Explained.by..Healthy.life.expectancy *
Explained.by..Freedom.to.make.life.choices,
corruption_inverse =
1 / (Explained.by..Perceptions.of.corruption + 0.001)
)
data_selected <- data %>%
select(
Explained.by..Log.GDP.per.capita,
Explained.by..Social.support,
Explained.by..Healthy.life.expectancy,
Explained.by..Freedom.to.make.life.choices,
Explained.by..Generosity,
Explained.by..Perceptions.of.corruption,
Dystopia...residual,
GDP_social_interaction,
health_freedom_index,
corruption_inverse
) %>%
na.omit()
dim(data_selected)
## [1] 140 10
Standarisasi
Data dan Uji Kelayakan Analisis Faktor
data_scaled <- scale(data_selected)
KMO(data_scaled)
## Kaiser-Meyer-Olkin factor adequacy
## Call: KMO(r = data_scaled)
## Overall MSA = 0.57
## MSA for each item =
## Explained.by..Log.GDP.per.capita
## 0.58
## Explained.by..Social.support
## 0.56
## Explained.by..Healthy.life.expectancy
## 0.57
## Explained.by..Freedom.to.make.life.choices
## 0.42
## Explained.by..Generosity
## 0.47
## Explained.by..Perceptions.of.corruption
## 0.78
## Dystopia...residual
## 0.48
## GDP_social_interaction
## 0.59
## health_freedom_index
## 0.60
## corruption_inverse
## 0.42
Uji Kelayakan
Analisis Faktor
cor_matrix <- cor(data_selected)
cortest.bartlett(cor_matrix, n = nrow(data_selected))
## $chisq
## [1] 1502.535
##
## $p.value
## [1] 1.561919e-285
##
## $df
## [1] 45
Menampilkan
Deskripsi Data yang dipilih
describe(data_selected)
## vars n mean sd median trimmed
## Explained.by..Log.GDP.per.capita 1 140 1.38 0.43 1.43 1.40
## Explained.by..Social.support 2 140 1.13 0.33 1.24 1.17
## Explained.by..Healthy.life.expectancy 3 140 0.52 0.16 0.55 0.53
## Explained.by..Freedom.to.make.life.choices 4 140 0.62 0.16 0.64 0.64
## Explained.by..Generosity 5 140 0.15 0.07 0.14 0.14
## Explained.by..Perceptions.of.corruption 6 140 0.15 0.13 0.12 0.13
## Dystopia...residual 7 140 1.58 0.54 1.64 1.60
## GDP_social_interaction 8 140 1.67 0.83 1.72 1.69
## health_freedom_index 9 140 0.33 0.15 0.36 0.34
## corruption_inverse 10 140 20.51 85.47 8.23 9.93
## mad min max range skew
## Explained.by..Log.GDP.per.capita 0.50 0.00 2.14 2.14 -0.50
## Explained.by..Social.support 0.30 0.00 1.62 1.62 -0.97
## Explained.by..Healthy.life.expectancy 0.17 0.00 0.86 0.86 -0.53
## Explained.by..Freedom.to.make.life.choices 0.15 0.00 0.86 0.86 -1.00
## Explained.by..Generosity 0.07 0.00 0.40 0.40 0.65
## Explained.by..Perceptions.of.corruption 0.09 0.00 0.58 0.58 1.49
## Dystopia...residual 0.39 -0.07 3.00 3.07 -0.59
## GDP_social_interaction 1.09 0.00 3.04 3.04 -0.21
## health_freedom_index 0.18 0.00 0.61 0.61 -0.23
## corruption_inverse 6.35 1.74 1000.00 998.26 10.79
## kurtosis se
## Explained.by..Log.GDP.per.capita -0.42 0.04
## Explained.by..Social.support 0.40 0.03
## Explained.by..Healthy.life.expectancy -0.44 0.01
## Explained.by..Freedom.to.make.life.choices 1.16 0.01
## Explained.by..Generosity 0.72 0.01
## Explained.by..Perceptions.of.corruption 1.83 0.01
## Dystopia...residual 0.68 0.05
## GDP_social_interaction -1.18 0.07
## health_freedom_index -1.01 0.01
## corruption_inverse 120.28 7.22
Menampilkan
Corrplot Data yang dipilih
cor_matrix <- cor(data_selected)
corrplot(cor_matrix, method="color")
Ringkasan
Hasil PCA
pca_result <- prcomp(data_scaled, center = TRUE, scale. = TRUE)
summary(pca_result)
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7
## Standard deviation 2.2062 1.1241 1.0711 1.0100 0.77885 0.76270 0.56002
## Proportion of Variance 0.4868 0.1264 0.1147 0.1020 0.06066 0.05817 0.03136
## Cumulative Proportion 0.4868 0.6131 0.7278 0.8298 0.89051 0.94868 0.98004
## PC8 PC9 PC10
## Standard deviation 0.42021 0.12997 0.07803
## Proportion of Variance 0.01766 0.00169 0.00061
## Cumulative Proportion 0.99770 0.99939 1.00000
Grafik Scree
Plot Hasil PCA
fviz_eig(pca_result)
Histogram Data
yang dipilih
par(mfrow=c(2,3))
for(i in 1:min(6, ncol(data_selected))){
hist(data_selected[,i],
main=names(data_selected)[i],
col="skyblue")
}
Boxplot Data
yang dipilih
par(mfrow=c(2,3))
for(i in 1:min(6, ncol(data_selected))){
boxplot(data_selected[,i],
main=names(data_selected)[i],
col="orange")
}
Interpretasi
Loading pada Komponen Utama
pca_result$rotation
## PC1 PC2
## Explained.by..Log.GDP.per.capita -0.40703256 -0.276297245
## Explained.by..Social.support -0.38546615 -0.066014205
## Explained.by..Healthy.life.expectancy -0.40106553 -0.182043592
## Explained.by..Freedom.to.make.life.choices -0.30288969 0.433869741
## Explained.by..Generosity -0.05133338 0.622377796
## Explained.by..Perceptions.of.corruption -0.24491330 0.136178022
## Dystopia...residual -0.06480643 0.493200739
## GDP_social_interaction -0.42826162 -0.175426386
## health_freedom_index -0.42768775 0.134147175
## corruption_inverse 0.00150799 0.001926501
## PC3 PC4
## Explained.by..Log.GDP.per.capita 0.001675601 0.038672062
## Explained.by..Social.support 0.192936790 -0.075947040
## Explained.by..Healthy.life.expectancy 0.043493163 0.013535451
## Explained.by..Freedom.to.make.life.choices -0.011729703 -0.079705159
## Explained.by..Generosity 0.009716100 0.581302526
## Explained.by..Perceptions.of.corruption -0.514571451 0.215622361
## Dystopia...residual 0.205045433 -0.703959650
## GDP_social_interaction 0.065007913 0.001693138
## health_freedom_index -0.007786302 -0.011724262
## corruption_inverse 0.805937269 0.325722665
## PC5 PC6 PC7
## Explained.by..Log.GDP.per.capita -0.008278696 -0.11064795 0.01887290
## Explained.by..Social.support -0.376349737 -0.06653277 -0.53059071
## Explained.by..Healthy.life.expectancy -0.031855498 -0.11675031 0.67141017
## Explained.by..Freedom.to.make.life.choices 0.180997781 0.68903474 -0.16130740
## Explained.by..Generosity -0.432884440 -0.23578813 0.11551111
## Explained.by..Perceptions.of.corruption 0.604062195 -0.38936838 -0.24111559
## Dystopia...residual 0.067468730 -0.43807251 0.07609362
## GDP_social_interaction -0.157219069 -0.15128889 -0.25260363
## health_freedom_index 0.103714160 0.25561049 0.31027022
## corruption_inverse 0.481882561 -0.08714683 -0.06292558
## PC8 PC9
## Explained.by..Log.GDP.per.capita -0.69735586 -0.2829291050
## Explained.by..Social.support 0.50335627 -0.1915922993
## Explained.by..Healthy.life.expectancy 0.33560026 -0.3878613111
## Explained.by..Freedom.to.make.life.choices -0.11892621 -0.3353325071
## Explained.by..Generosity -0.12231489 -0.0245353685
## Explained.by..Perceptions.of.corruption 0.17780794 -0.0623206866
## Dystopia...residual -0.11085863 -0.0141794860
## GDP_social_interaction -0.23229983 0.4215941469
## health_freedom_index 0.14188191 0.6617625717
## corruption_inverse 0.02442088 -0.0009946777
## PC10
## Explained.by..Log.GDP.per.capita -0.421265033
## Explained.by..Social.support -0.293935429
## Explained.by..Healthy.life.expectancy 0.274646594
## Explained.by..Freedom.to.make.life.choices 0.231049580
## Explained.by..Generosity -0.010630996
## Explained.by..Perceptions.of.corruption -0.007817490
## Dystopia...residual -0.014486339
## GDP_social_interaction 0.662169979
## health_freedom_index -0.410449143
## corruption_inverse 0.001229062
Hasil
FA
fa_result <- fa(data_scaled, nfactors=3, rotate="varimax")
print(fa_result, cut=0.4)
## Factor Analysis using method = minres
## Call: fa(r = data_scaled, nfactors = 3, rotate = "varimax")
## Standardized loadings (pattern matrix) based upon correlation matrix
## MR1 MR3 MR2 h2 u2 com
## Explained.by..Log.GDP.per.capita 0.95 0.915 0.085 1.0
## Explained.by..Social.support 0.81 0.721 0.279 1.2
## Explained.by..Healthy.life.expectancy 0.87 0.767 0.233 1.0
## Explained.by..Freedom.to.make.life.choices 0.41 0.79 0.800 0.200 1.5
## Explained.by..Generosity 0.092 0.908 1.3
## Explained.by..Perceptions.of.corruption 0.91 0.997 0.003 1.4
## Dystopia...residual 0.097 0.903 1.2
## GDP_social_interaction 0.99 0.984 0.016 1.0
## health_freedom_index 0.80 0.56 0.972 0.028 1.9
## corruption_inverse 0.051 0.949 1.0
##
## MR1 MR3 MR2
## SS loadings 4.23 1.21 0.96
## Proportion Var 0.42 0.12 0.10
## Cumulative Var 0.42 0.54 0.64
## Proportion Explained 0.66 0.19 0.15
## Cumulative Proportion 0.66 0.85 1.00
##
## Mean item complexity = 1.3
## Test of the hypothesis that 3 factors are sufficient.
##
## df null model = 45 with the objective function = 11.14 with Chi Square = 1502.54
## df of the model are 18 and the objective function was 3.54
##
## The root mean square of the residuals (RMSR) is 0.03
## The df corrected root mean square of the residuals is 0.05
##
## The harmonic n.obs is 140 with the empirical chi square 7.16 with prob < 0.99
## The total n.obs was 140 with Likelihood Chi Square = 469.77 with prob < 2.3e-88
##
## Tucker Lewis Index of factoring reliability = 0.213
## RMSEA index = 0.423 and the 90 % confidence intervals are 0.392 0.459
## BIC = 380.82
## Fit based upon off diagonal values = 0.99
## Measures of factor score adequacy
## MR1 MR3 MR2
## Correlation of (regression) scores with factors 0.99 0.95 1.00
## Multiple R square of scores with factors 0.98 0.90 0.99
## Minimum correlation of possible factor scores 0.97 0.81 0.99