library(csv)
## Warning: package 'csv' was built under R version 4.5.2
library(ggplot2)
library(car)
## Loading required package: carData
library(lmtest)
## Warning: package 'lmtest' was built under R version 4.5.2
## Loading required package: zoo
## Warning: package 'zoo' was built under R version 4.5.2
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
data <- read.csv("~/Belajar kuliah lukas/Analisis Regresi/Data/admission.csv")
summary(data)
## gre_score toefl_score univ_ranking motiv_letter_strength
## Min. :290.0 Min. : 92.0 Min. :1.000 Min. :1.000
## 1st Qu.:308.0 1st Qu.:103.0 1st Qu.:2.000 1st Qu.:2.500
## Median :317.0 Median :107.0 Median :3.000 Median :3.500
## Mean :316.5 Mean :107.2 Mean :3.114 Mean :3.374
## 3rd Qu.:325.0 3rd Qu.:112.0 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :340.0 Max. :120.0 Max. :5.000 Max. :5.000
## recommendation_strength gpa research_exp admission_score
## Min. :1.000 Min. :6.800 Min. :0.00 Min. :34.00
## 1st Qu.:3.000 1st Qu.:8.127 1st Qu.:0.00 1st Qu.:63.00
## Median :3.500 Median :8.560 Median :1.00 Median :72.00
## Mean :3.484 Mean :8.576 Mean :0.56 Mean :72.14
## 3rd Qu.:4.000 3rd Qu.:9.040 3rd Qu.:1.00 3rd Qu.:82.00
## Max. :5.000 Max. :9.920 Max. :1.00 Max. :97.00
head(data)
## gre_score toefl_score univ_ranking motiv_letter_strength
## 1 337 118 4 4.5
## 2 324 107 4 4.0
## 3 316 104 3 3.0
## 4 322 110 3 3.5
## 5 314 103 2 2.0
## 6 330 115 5 4.5
## recommendation_strength gpa research_exp admission_score
## 1 4.5 9.65 1 92
## 2 4.5 8.87 1 76
## 3 3.5 8.00 1 72
## 4 2.5 8.67 1 80
## 5 3.0 8.21 0 65
## 6 3.0 9.34 1 90
tail(data)
## gre_score toefl_score univ_ranking motiv_letter_strength
## 495 301 99 3 2.5
## 496 332 108 5 4.5
## 497 337 117 5 5.0
## 498 330 120 5 4.5
## 499 312 103 4 4.0
## 500 327 113 4 4.5
## recommendation_strength gpa research_exp admission_score
## 495 2.0 8.45 1 68
## 496 4.0 9.02 1 87
## 497 5.0 9.87 1 96
## 498 5.0 9.56 1 93
## 499 5.0 8.43 0 73
## 500 4.5 9.04 0 84
ggplot(data, aes(x = gpa, y = admission_score)) +
geom_point(color = "blue", size = 3) +
labs(title = "Hubungan GPA dan Admission Score",
x = "GPA", y = "Admission Score") +
theme_minimal()
cor_test <- cor.test(data$gpa, data$admission_score)
print(paste("Korelasi Pearson:", round(cor_test$estimate, 4)))
## [1] "Korelasi Pearson: 0.8828"
print(paste("p-value korelasi:", round(cor_test$p.value, 4)))
## [1] "p-value korelasi: 0"
# 3. MEMBANGUN MODEL REGRESI
model <- lm(admission_score ~ gpa, data = data)
print("Ringkasan Model Regresi:")
## [1] "Ringkasan Model Regresi:"
summary(model)
##
## Call:
## lm(formula = admission_score ~ gpa, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -27.6247 -2.8559 0.6617 3.8753 17.7697
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -105.0275 4.2355 -24.80 <2e-16 ***
## gpa 20.6572 0.4926 41.93 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6.656 on 498 degrees of freedom
## Multiple R-squared: 0.7793, Adjusted R-squared: 0.7788
## F-statistic: 1758 on 1 and 498 DF, p-value: < 2.2e-16
cat("\n=== UJI ASUMSI REGRESI LINEAR ===\n")
##
## === UJI ASUMSI REGRESI LINEAR ===
shapiro_test <- shapiro.test(residuals(model))
cat("1. UJI NORMALITAS (Shapiro-Wilk):\n")
## 1. UJI NORMALITAS (Shapiro-Wilk):
cat(" Statistik W =", round(shapiro_test$statistic, 4), "\n")
## Statistik W = 0.9507
cat(" p-value =", round(shapiro_test$p.value, 4), "\n")
## p-value = 0
if(shapiro_test$p.value > 0.05) {
cat(" Keputusan: Residual berdistribusi normal\n")
} else {
cat(" Keputusan: Residual tidak normal\n")
}
## Keputusan: Residual tidak normal
qqnorm(residuals(model), main = "Q-Q Plot Residual")
qqline(residuals(model), col = "red")
bp_test <- bptest(model)
cat("\n2. UJI HOMOSKEDASTISITAS (Breusch-Pagan):\n")
##
## 2. UJI HOMOSKEDASTISITAS (Breusch-Pagan):
cat(" Statistik LM =", round(bp_test$statistic, 4), "\n")
## Statistik LM = 20.6523
cat(" p-value =", round(bp_test$p.value, 4), "\n")
## p-value = 0
if(bp_test$p.value > 0.05) {
cat(" Keputusan: Varian residual homogen\n")
} else {
cat(" Keputusan: Ada heteroskedastisitas\n")
}
## Keputusan: Ada heteroskedastisitas
# Plot Residual vs Fitted
plot(fitted(model), residuals(model),
main = "Residual vs Fitted Values",
xlab = "Fitted Values", ylab = "Residuals",
pch = 19, col = "blue")
abline(h = 0, col = "red", lty = 2)
# 4.3 Tidak ada Autokorelasi
dw_test <- dwtest(model)
cat("\n3. UJI AUTOKORELASI (Durbin-Watson):\n")
##
## 3. UJI AUTOKORELASI (Durbin-Watson):
cat(" Statistik DW =", round(dw_test$statistic, 4), "\n")
## Statistik DW = 0.9726
cat(" p-value =", round(dw_test$p.value, 4), "\n")
## p-value = 0
if(dw_test$p.value > 0.05) {
cat(" Keputusan: Tidak ada autokorelasi\n")
} else {
cat(" Keputusan: Ada autokorelasi\n")
}
## Keputusan: Ada autokorelasi
# 5. INTERPRETASI KOEFISIEN
cat("\n=== INTERPRETASI KOEFISIEN ===\n")
##
## === INTERPRETASI KOEFISIEN ===
intercept <- coef(model)[1]
slope <- coef(model)[2]
cat("Persamaan Regresi:\n")
## Persamaan Regresi:
cat("Admission Score =", round(intercept, 2), "+", round(slope, 2), "* GPA\n")
## Admission Score = -105.03 + 20.66 * GPA
# 6. ESTIMASI PARAMETER DAN INFERENSI
cat("\n=== ESTIMASI PARAMETER ===\n")
##
## === ESTIMASI PARAMETER ===
conf_int <- confint(model, level = 0.95)
cat("Interval Kepercayaan 95%:\n")
## Interval Kepercayaan 95%:
cat(" Intercept: [", round(conf_int[1,1], 3), ", ", round(conf_int[1,2], 3), "]\n", sep = "")
## Intercept: [-113.349, -96.706]
cat(" Slope: [", round(conf_int[2,1], 3), ", ", round(conf_int[2,2], 3), "]\n", sep = "")
## Slope: [19.689, 21.625]
# Uji hipotesis untuk slope
cat("\nUji Hipotesis untuk Slope (β1):\n")
##
## Uji Hipotesis untuk Slope (β1):
cat(" H0: β1 = 0 (tidak ada hubungan linear)\n")
## H0: β1 = 0 (tidak ada hubungan linear)
cat(" H1: β1 ≠ 0 (ada hubungan linear)\n")
## H1: β1 ≠ 0 (ada hubungan linear)
summary_model <- summary(model)
slope_pvalue <- summary_model$coefficients[2, 4]
cat(" p-value =", round(slope_pvalue, 6), "\n")
## p-value = 0
if(slope_pvalue < 0.05) {
cat(" Keputusan: Tolak H0, ada hubungan linear signifikan\n")
} else {
cat(" Keputusan: Gagal tolak H0, tidak ada hubungan linear signifikan\n")
}
## Keputusan: Tolak H0, ada hubungan linear signifikan
# 7. KOEFISIEN DETERMINASI
r_squared <- summary_model$r.squared
cat("\nKoefisien Determinasi (R²):\n")
##
## Koefisien Determinasi (R²):
cat(" R² =", round(r_squared, 4), "\n")
## R² = 0.7793
cat(" Artinya:", round(r_squared * 100, 2), "% variasi admission score dapat dijelaskan oleh gpa\n")
## Artinya: 77.93 % variasi admission score dapat dijelaskan oleh gpa
# 8. VISUALISASI MODEL
ggplot(data, aes(x = gpa, y = admission_score)) +
geom_point(color = "blue", size = 3) +
geom_smooth(method = "lm", se = TRUE, color = "red", fill = "pink") +
labs(title = "Garis Regresi Linear",
subtitle = paste("Y =", round(intercept, 2), "+", round(slope, 2), "X"),
x = "gpa", y = "admission score") +
theme_minimal()
## `geom_smooth()` using formula = 'y ~ x'
# 9. PREDIKSI
new_data <- data.frame(gpa = 8.5)
prediction <- predict(model, newdata = new_data, interval = "confidence")
cat("\n=== Prediksi Admission Score ===\n")
##
## === Prediksi Admission Score ===
cat("Untuk gpa 8.5, prediksi admission score =", round(prediction[1, "fit"], 2), "\n")
## Untuk gpa 8.5, prediksi admission score = 70.56
print(cbind(new_data, prediction))
## gpa fit lwr upr
## 1 8.5 70.55896 69.96949 71.14843
# 10. DIAGNOSTIC PLOTS
par(mfrow = c(2, 2))
plot(model, which = 1:4)
par(mfrow = c(1, 1))
# 11. RINGKASAN LENGKAP
cat("\n=== RINGKASAN ANALISIS ===\n")
##
## === RINGKASAN ANALISIS ===
cat("1. Model: admission score = β0 + β1*gpa + ε\n")
## 1. Model: admission score = β0 + β1*gpa + ε
cat("2. Estimasi: Y =", round(intercept, 3), "+", round(slope, 3), "* X\n")
## 2. Estimasi: Y = -105.027 + 20.657 * X
cat("3. R² =", round(r_squared, 4), "(", round(r_squared*100, 1), "%)\n")
## 3. R² = 0.7793 ( 77.9 %)
cat("4. Uji F (model): p-value =",
round(summary_model$fstatistic[1], 4), "\n")
## 4. Uji F (model): p-value = 1758.324
cat("5. Asumsi:\n")
## 5. Asumsi:
cat(" - Normalitas: p =", round(shapiro_test$p.value, 4), "\n")
## - Normalitas: p = 0
cat(" - Homoskedastisitas: p =", round(bp_test$p.value, 4), "\n")
## - Homoskedastisitas: p = 0
cat(" - Autokorelasi: p =", round(dw_test$p.value, 4), "\n")
## - Autokorelasi: p = 0
# Simpan hasil
hasil <- list(
model = model,
coefficients = coef(model),
r_squared = r_squared,
assumptions = list(
normality = shapiro_test$p.value,
homoscedasticity = bp_test$p.value,
autocorrelation = dw_test$p.value
),
confidence_intervals = conf_int
)
print("Analisis regresi linear sederhana selesai!")
## [1] "Analisis regresi linear sederhana selesai!"
```