Setup & Load Data
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.5.3
## Warning: package 'readr' was built under R version 4.5.3
## Warning: package 'forcats' was built under R version 4.5.3
## Warning: package 'lubridate' was built under R version 4.5.3
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.2.0 ✔ readr 2.2.0
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.2 ✔ tibble 3.3.1
## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2
## ✔ purrr 1.2.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(GGally)
## Warning: package 'GGally' was built under R version 4.5.3
anime <- read.csv("anime_clean.csv")
anime$type <- as.factor(anime$type)
head(anime)
Statistika Deskriptif
# Menghitung rata-rata untuk masing-masing grup (TV vs Movie)
ringkasan_data <- anime %>%
group_by(type) %>%
summarise(
Rata_Rating = mean(rating),
Rata_Log_Members = mean(log_members),
Rata_Episode = mean(episodes),
Total_Anime = n()
)
print(ringkasan_data)
## # A tibble: 2 × 5
## type Rata_Rating Rata_Log_Members Rata_Episode Total_Anime
## <fct> <dbl> <dbl> <dbl> <int>
## 1 Movie 6.32 6.71 1.10 2296
## 2 TV 6.93 8.54 36.0 3570
Membuat Correlogram
# Memilih hanya kolom-kolom yang relevan untuk di-plot
data_visual <- anime %>%
select(type, episodes, rating, log_members)
# Membuat Correlogram dengan membedakan warna berdasarkan 'type' (TV/Movie)
plot_korelasi <- ggpairs(
data_visual,
mapping = aes(color = type, alpha = 0.5),
title = "Correlogram: Episode, Rating, dan Popularitas (Log Members)",
lower = list(continuous = wrap("points", size = 0.5)) # Biar titiknya nggak terlalu besar
)
# Menampilkan plot ke layar
print(plot_korelasi)
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
Uji Asumsi Homogenitas Kemiringan Regresi
asumsi_kemiringan <- manova(cbind(rating, log_members) ~ type * episodes, data = anime)
summary(asumsi_kemiringan)
## Df Pillai approx F num Df den Df Pr(>F)
## type 1 0.124168 415.46 2 5861 < 2e-16 ***
## episodes 1 0.022888 68.65 2 5861 < 2e-16 ***
## type:episodes 1 0.000851 2.50 2 5861 0.08257 .
## Residuals 5862
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Uji Homogenitas Matriks Kovarians (Box’s M Test)
library(heplots)
## Warning: package 'heplots' was built under R version 4.5.3
## Loading required package: broom
## Warning: package 'broom' was built under R version 4.5.3
asumsi_boxM <- boxM(cbind(rating, log_members) ~ type, data = anime)
print(asumsi_boxM)
##
## Box's M-test for Homogeneity of Covariance Matrices
##
## data: anime
## Chi-Sq (approx.) = 718.4303, df = 3, p-value = < 2.2e-16
Uji Normalitas Multivariat (Mardia’s Test)
library(psych)
## Warning: package 'psych' was built under R version 4.5.3
##
## Attaching package: 'psych'
## The following objects are masked from 'package:ggplot2':
##
## %+%, alpha
data_dependen <- anime %>% select(rating, log_members)
uji_mardia_psych <- mardia(data_dependen)
print(uji_mardia_psych)
## Call: mardia(x = data_dependen)
##
## Mardia tests of multivariate skew and kurtosis
## Use describe(x) the to get univariate tests
## n.obs = 5866 num.vars = 2
## b1p = 0.99 skew = 964.23 with probability <= 2e-207
## small sample skew = 965.06 with probability <= 1.3e-207
## b2p = 9.21 kurtosis = 11.57 with probability <= 0
Menjalankan Model MANCOVA
model_mancova <- manova(cbind(rating, log_members) ~ episodes + type, data = anime)
hasil_mancova <- summary(model_mancova, test = "Pillai")
print(hasil_mancova)
## Df Pillai approx F num Df den Df Pr(>F)
## episodes 1 0.011242 33.32 2 5862 4.065e-15 ***
## type 1 0.133297 450.78 2 5862 < 2.2e-16 ***
## Residuals 5863
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Menghitung Effect Size (Partial Eta Squared)
library(effectsize)
## Warning: package 'effectsize' was built under R version 4.5.3
##
## Attaching package: 'effectsize'
## The following object is masked from 'package:psych':
##
## phi
eta_mancova <- eta_squared(model_mancova, partial = TRUE)
# Menampilkan hasil
print(eta_mancova)
## # Effect Size for ANOVA (Type I)
##
## Parameter | Eta2 (partial) | 95% CI
## -----------------------------------------
## episodes | 0.01 | [0.01, 1.00]
## type | 0.13 | [0.12, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].