1. MEMUAT PACKAGE DAN DATA

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.5.2

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

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.5.2

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(car)

## Warning: package 'car' was built under R version 4.5.2

## Loading required package: carData

## Warning: package 'carData' was built under R version 4.5.2

## 
## Attaching package: 'car'

## The following object is masked from 'package:dplyr':
## 
##     recode

library(csv)

## Warning: package 'csv' was built under R version 4.5.2

# Import data CSV
df <- read.csv("C:/Users/MyBook Hype AMD/Downloads/Salary_dataset.csv")
data<- df[c("YearsExperience","Salary")]
# Lihat struktur data
head(data)

##   YearsExperience Salary
## 1             1.2  39344
## 2             1.4  46206
## 3             1.6  37732
## 4             2.1  43526
## 5             2.3  39892
## 6             3.0  56643

#2. M I S S I N G V A L U E S

total_missing<- sum (is.na(data))
total_missing

## [1] 0

3. ANALISIS DESKRIPTIF DAN VISUALISASI

print("Statistik Deskriptif:")

## [1] "Statistik Deskriptif:"

summary(data)

##  YearsExperience      Salary      
##  Min.   : 1.200   Min.   : 37732  
##  1st Qu.: 3.300   1st Qu.: 56722  
##  Median : 4.800   Median : 65238  
##  Mean   : 5.413   Mean   : 76004  
##  3rd Qu.: 7.800   3rd Qu.:100546  
##  Max.   :10.600   Max.   :122392

# Scatter plot
ggplot(data, aes(x = YearsExperience, y = Salary)) +
  geom_point(color = "blue", size = 3) +
  labs(title = "Hubungan tahun pengalaman dan gaji",
       x = "Tahun pengalaman", y = "Gaji") +
  theme_minimal()

# Korelasi
cor_test <- cor.test(data$YearsExperience,data$Salary)
print(paste("Korelasi Pearson:", round(cor_test$estimate, 4)))

## [1] "Korelasi Pearson: 0.9782"

print(paste("p-value korelasi:", round(cor_test$p.value, 4)))

## [1] "p-value korelasi: 0"

4. MEMBANGUN MODEL REGRESI

model <- lm(Salary ~ YearsExperience, data = data)
print("Ringkasan Model Regresi:")

## [1] "Ringkasan Model Regresi:"

summary(model)

## 
## Call:
## lm(formula = Salary ~ YearsExperience, data = data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -7958.0 -4088.5  -459.9  3372.6 11448.0 
## 
## Coefficients:
##                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      24848.2     2306.7   10.77 1.82e-11 ***
## YearsExperience   9450.0      378.8   24.95  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 5788 on 28 degrees of freedom
## Multiple R-squared:  0.957,  Adjusted R-squared:  0.9554 
## F-statistic: 622.5 on 1 and 28 DF,  p-value: < 2.2e-16

5. UJI ASUMSI REGRESI LINEAR

cat("\n=== UJI ASUMSI REGRESI LINEAR ===\n")

## 
## === UJI ASUMSI REGRESI LINEAR ===

# 5.1 Normalitas Residual
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 = 0.9523

cat("   p-value =", round(shapiro_test$p.value, 4), "\n")

##    p-value = 0.1952

if(shapiro_test$p.value > 0.05) {
  cat("   Keputusan: Residual berdistribusi normal\n")
} else {
  cat("   Keputusan: Residual tidak normal\n")
}

##    Keputusan: Residual berdistribusi normal

# Q-Q Plot
qqnorm(residuals(model), main = "Q-Q Plot Residual")
qqline(residuals(model), col = "red")

# 5.2 Homoskedastisitas
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 = 0.3991

cat("   p-value =", round(bp_test$p.value, 4), "\n")

##    p-value = 0.5276

if(bp_test$p.value > 0.05) {
  cat("   Keputusan: Varian residual homogen\n")
} else {
  cat("   Keputusan: Ada heteroskedastisitas\n")
}

##    Keputusan: Varian residual homogen

# 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)

# 5.3 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 = 1.648

cat("   p-value =", round(dw_test$p.value, 4), "\n")

##    p-value = 0.1178

if(dw_test$p.value > 0.05) {
  cat("   Keputusan: Tidak ada autokorelasi\n")
} else {
  cat("   Keputusan: Ada autokorelasi\n")
}

##    Keputusan: Tidak ada autokorelasi

6. INTERPRETASI KOEFISIEN

cat("\n=== INTERPRETASI KOEFISIEN ===\n")

## 
## === INTERPRETASI KOEFISIEN ===

intercept <- coef(model)[1]
slope <- coef(model)[2]

cat("Persamaan Regresi: Salary =", round(intercept, 2), "+", round(slope, 2), "* YearsExperience\n")

## Persamaan Regresi: Salary = 24848.2 + 9449.96 * YearsExperience

cat("\nInterpretasi:\n")

## 
## Interpretasi:

cat("1. Intercept (β0 =", round(intercept, 2), "):\n")

## 1. Intercept (β0 = 24848.2 ):

cat("   Nilai gaji ketika tahun pengalam = 0 adalah", round(intercept, 2), "dolar\n")

##    Nilai gaji ketika tahun pengalam = 0 adalah 24848.2 dolar

cat("2. Slope (β1 =", round(slope, 2), "):\n")

## 2. Slope (β1 = 9449.96 ):

cat("   Setiap penambahan pengalaman 1 Tahun, nilai gaji meningkat", round(slope, 2), "dolar\n")

##    Setiap penambahan pengalaman 1 Tahun, nilai gaji meningkat 9449.96 dolar

7. 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: [20123.24, 29573.17]

cat("   Slope:     [", round(conf_int[2,1], 3), ", ", round(conf_int[2,2], 3), "]\n", sep = "")

##    Slope:     [8674.119, 10225.81]

# 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 = 0.957

cat("   Artinya:", round(r_squared * 100, 2), "% variasi nilai gaji dapat dijelaskan oleh pengalaman\n")

##    Artinya: 95.7 % variasi nilai gaji dapat dijelaskan oleh pengalaman

8. VISUALISASI MODEL

ggplot(data, aes(x =YearsExperience , y = Salary)) +
  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 = "Tahub pengalaman", y = "gaji") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

9. PREDIKSI

new_data <- data.frame(YearsExperience = c(3, 5))
prediction <- predict(model, newdata = new_data, interval = "confidence")
cat("\n=== PREDIKSI ===\n")

## 
## === PREDIKSI ===

cat("Untuk pengalaman 3 tahun, prediksi gaji =", round(prediction[1, "fit"], 2), "\n")

## Untuk pengalaman 3 tahun, prediksi gaji = 53198.09

cat("Untuk pengalaman 5 tahun , prediksi gaji =", round(prediction[2, "fit"], 2), "\n")

## Untuk pengalaman 5 tahun , prediksi gaji = 72098.02

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:Gaji = β0 + β1*YearsExperience + ε\n")

## 1. Model:Gaji = β0 + β1*YearsExperience + ε

cat("2. Estimasi: Y =", round(intercept, 3), "+", round(slope, 3), "* X\n")

## 2. Estimasi: Y = 24848.2 + 9449.962 * X

cat("3. R² =", round(r_squared, 4), "(", round(r_squared*100, 1), "%)\n")

## 3. R² = 0.957 ( 95.7 %)

cat("4. Uji F (model): p-value =", 
    round(summary_model$fstatistic[1], 4), "\n")

## 4. Uji F (model): p-value = 622.5072

cat("5. Asumsi:\n")

## 5. Asumsi:

cat("   - Normalitas: p =", round(shapiro_test$p.value, 4), "\n")

##    - Normalitas: p = 0.1952

cat("   - Homoskedastisitas: p =", round(bp_test$p.value, 4), "\n")

##    - Homoskedastisitas: p = 0.5276

cat("   - Autokorelasi: p =", round(dw_test$p.value, 4), "\n")

##    - Autokorelasi: p = 0.1178

# 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!"

anreg m3

sanah

2026-02-11

1. MEMUAT PACKAGE DAN DATA

3. ANALISIS DESKRIPTIF DAN VISUALISASI

4. MEMBANGUN MODEL REGRESI

5. UJI ASUMSI REGRESI LINEAR

6. INTERPRETASI KOEFISIEN

7. ESTIMASI PARAMETER DAN INFERENSI

7. KOEFISIEN DETERMINASI

8. VISUALISASI MODEL

9. PREDIKSI

10. DIAGNOSTIC PLOTS

11. RINGKASAN LENGKAP