Analisis regresi Minggu 2
Ade Saputra
2026-02-04
library(csv)## Warning: package 'csv' was built under R version 4.5.2library(outliers)## Warning: package 'outliers' was built under R version 4.5.2library(tidyverse)## Warning: package 'tidyverse' was built under R version 4.5.2## Warning: package 'ggplot2' was built under R version 4.5.2## Warning: package 'tibble' was built under R version 4.5.2## Warning: package 'tidyr' was built under R version 4.5.2## Warning: package 'readr' was built under R version 4.5.2## Warning: package 'purrr' was built under R version 4.5.2## Warning: package 'dplyr' was built under R version 4.5.2## Warning: package 'stringr' was built under R version 4.5.2## Warning: package 'forcats' was built under R version 4.5.2## Warning: package 'lubridate' was built under R version 4.5.2## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.6
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.1 ✔ tibble 3.3.1
## ✔ lubridate 1.9.4 ✔ 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 errorslibrary(VIM)## Warning: package 'VIM' was built under R version 4.5.2## Loading required package: colorspace## Warning: package 'colorspace' was built under R version 4.5.2## Loading required package: grid
## VIM is ready to use.
##
## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues
##
## Attaching package: 'VIM'
##
## The following object is masked from 'package:datasets':
##
## sleeplibrary(naniar)## Warning: package 'naniar' was built under R version 4.5.2library(outliers)
library(ggplot2)
library(mice)## Warning: package 'mice' was built under R version 4.5.2##
## Attaching package: 'mice'
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following objects are masked from 'package:base':
##
## cbind, rbinddata <- read.csv("~/datania1k.csv")
df<- data[,c("Age","Annual_Premium")]
head(df)## Age Annual_Premium
## 1 22 36513
## 2 24 2630
## 3 22 35832
## 4 72 36685
## 5 66 2630
## 6 42 31226tail(df)## Age Annual_Premium
## 995 48 47533
## 996 47 29384
## 997 56 47479
## 998 22 29000
## 999 48 45107
## 1000 33 43068#Missing Value
total_missing <- sum(is.na(df))
total_missing## [1] 0#Mencari Outlier
# 3. Deteksi outlier
detect_outliers <- function(df) {
cat("\n=== DETEKSI OUTLIER ===\n\n")
outlier_report <- list()
for(var in names(df)[sapply(df, is.numeric)]) {
cat("Analisis outlier untuk variabel:", var, "\n")
# Statistik deskriptif
stats <- summary(df[[var]])
iqr_val <- IQR(df[[var]], na.rm = TRUE)
q1 <- quantile(df[[var]], 0.25, na.rm = TRUE)
q3 <- quantile(df[[var]], 0.75, na.rm = TRUE)
lower_bound <- q1 - 1.5 * iqr_val
upper_bound <- q3 + 1.5 * iqr_val
# Deteksi outlier dengan metode IQR
outliers_iqr <- data[[var]][df[[var]] < lower_bound | df[[var]] > upper_bound]
# Deteksi outlier dengan metode Z-score
z_scores <- scale(df[[var]])
outliers_z <- df[[var]][abs(z_scores) > 3]
# Deteksi outlier dengan metode Grubbs (uji statistik)
if(length(na.omit(df[[var]])) > 6) {
tryCatch({
grubbs_test <- grubbs.test(na.omit(df[[var]]))
grubbs_outlier <- ifelse(grubbs_test$p.value < 0.05, "Terdeteksi", "Tidak terdeteksi")
}, error = function(e) {
grubbs_outlier <- "Tidak dapat dihitung"
})
} else {
grubbs_outlier <- "Data tidak cukup"
}
# Ringkasan
outlier_report[[var]] <- list(
n_outliers_iqr = length(outliers_iqr),
n_outliers_z = length(outliers_z),
grubbs_result = grubbs_outlier,
lower_bound = lower_bound,
upper_bound = upper_bound,
outlier_values = unique(round(outliers_iqr, 2))
)
cat(" - Outlier (IQR method):", length(outliers_iqr), "\n")
cat(" - Outlier (Z-score > 3):", length(outliers_z), "\n")
cat(" - Uji Grubbs:", grubbs_outlier, "\n")
cat(" - Batas bawah:", round(lower_bound, 2), "\n")
cat(" - Batas atas:", round(upper_bound, 2), "\n")
if(length(outliers_iqr) > 0) {
cat(" - Nilai outlier:", paste(head(unique(round(outliers_iqr, 2)), 5), collapse = ", "), "\n")
}
cat("\n")
}
return(outlier_report)
}
# Deteksi outlier
outlier_analysis <- detect_outliers(df)##
## === DETEKSI OUTLIER ===
##
## Analisis outlier untuk variabel: Age
## - Outlier (IQR method): 0
## - Outlier (Z-score > 3): 0
## - Uji Grubbs: Tidak terdeteksi
## - Batas bawah: -12.88
## - Batas atas: 88.12
##
## Analisis outlier untuk variabel: Annual_Premium
## - Outlier (IQR method): 26
## - Outlier (Z-score > 3): 5
## - Uji Grubbs: Terdeteksi
## - Batas bawah: 1704.5
## - Batas atas: 62266.5
## - Nilai outlier: 81192, 100278, 63273, 70452, 71918#Statistika Deskriptif
summary(df$Age, df$Annual_Premium)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 20.00 25.00 38.00 39.65 50.25 85.00#Analisis Regresi
# ============================
# ANALISIS REGRESI LINEAR
# Age (X) → Annual_Premium (Y)
# ============================
# Membuat model regresi
model <- lm(Annual_Premium ~ Age, data = df)
cat("\n1. RINGKASAN MODEL:\n")##
## 1. RINGKASAN MODEL:summary_model <- summary(model)
print(summary_model)##
## Call:
## lm(formula = Annual_Premium ~ Age, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -32960 -5971 1517 9265 72308
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 24662.40 1386.17 17.792 < 2e-16 ***
## Age 143.79 32.48 4.427 1.06e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 16200 on 998 degrees of freedom
## Multiple R-squared: 0.01926, Adjusted R-squared: 0.01827
## F-statistic: 19.59 on 1 and 998 DF, p-value: 1.063e-05# ====================================================
# RINGKASAN UTAMA REGRESI (3 KOMPONEN)
# ====================================================
# 1. Signifikansi (p-value)
p_value <- summary_model$coefficients[2, 4]
# 2. Besarnya Pengaruh (Slope)
slope <- coef(model)[2]
# 3. Kualitas Model (R-squared)
r_squared <- summary_model$r.squared
cat("\n=== TIGA KOMPONEN UTAMA REGRESI ===\n")##
## === TIGA KOMPONEN UTAMA REGRESI ===# 1. SIGNIFIKANSI HUBUNGAN
cat("\n1. SIGNIFIKANSI HUBUNGAN (p-value slope):\n")##
## 1. SIGNIFIKANSI HUBUNGAN (p-value slope):cat("p-value =", round(p_value, 6), "\n")## p-value = 1.1e-05if (p_value < 0.05) {
cat("Interpretasi: Terdapat hubungan signifikan antara Age dan Annual_Premium.\n")
} else {
cat("Interpretasi: Tidak ada hubungan signifikan antara Age dan Annual_Premium.\n")
}## Interpretasi: Terdapat hubungan signifikan antara Age dan Annual_Premium.# 2. BESARNYA PENGARUH (SLOPE)
cat("\n2. BESARNYA PENGARUH (slope regresi):\n")##
## 2. BESARNYA PENGARUH (slope regresi):cat("Slope =", round(slope, 4), "\n")## Slope = 143.7899cat("Artinya: Setiap kenaikan 1 tahun usia mengubah nilai Annual_Premium sebesar",
round(slope, 2), "unit.\n")## Artinya: Setiap kenaikan 1 tahun usia mengubah nilai Annual_Premium sebesar 143.79 unit.# 3. KEKUATAN MODEL (R-SQUARED)
cat("\n3. KEKUATAN MODEL (R-squared):\n")##
## 3. KEKUATAN MODEL (R-squared):cat("R-squared =", round(r_squared, 4), "\n")## R-squared = 0.0193cat("Artinya:", round(r_squared * 100, 2),
"% variasi Annual_Premium dijelaskan oleh Age.\n")## Artinya: 1.93 % variasi Annual_Premium dijelaskan oleh Age.cat("\n=== SELESAI ANALISIS REGRESI ===\n")##
## === SELESAI ANALISIS REGRESI ===# ====================================================
# GRAFIK REGRESI (Scatter + Line)
# ====================================================
library(ggplot2)
ggplot(df, aes(x = Age, y = Annual_Premium)) +
geom_point(alpha = 0.5) +
geom_smooth(method = "lm", color = "blue", se = TRUE) +
labs(title = "Regresi Linear: Usia vs Premi Tahunan",
x = "Age",
y = "Annual Premium")## `geom_smooth()` using formula = 'y ~ x'