1. Simulasi Data

Data disimulasikan dengan hubungan non-linier (kuadratik) antara x dan y.

set.seed(123)
n <- 100
x <- seq(0, 10, length.out = n)
y <- 5 + 2*x - 0.3*x^2 + rnorm(n, mean = 0, sd = 2)
data <- data.frame(x = x, y = y)

head(data)
##           x        y
## 1 0.0000000 3.879049
## 2 0.1010101 4.738604
## 3 0.2020202 8.509213
## 4 0.3030303 5.719529
## 5 0.4040404 6.017682
## 6 0.5050505 9.363708

2. Pencocokan Model

Tiga model dicocokkan sebagai pembanding: linier, polinomial derajat 2, dan derajat 3.

model_linier <- lm(y ~ x, data = data)
model_poli2  <- lm(y ~ poly(x, 2, raw = TRUE), data = data)
model_poli3  <- lm(y ~ poly(x, 3, raw = TRUE), data = data)

summary(model_poli2)
## 
## Call:
## lm(formula = y ~ poly(x, 2, raw = TRUE), data = data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.8136 -1.1977 -0.0533  1.3549  4.3891 
## 
## Coefficients:
##                         Estimate Std. Error t value Pr(>|t|)    
## (Intercept)              5.33982    0.53777   9.929   <2e-16 ***
## poly(x, 2, raw = TRUE)1  1.80266    0.24855   7.253    1e-10 ***
## poly(x, 2, raw = TRUE)2 -0.27529    0.02405 -11.447   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.829 on 97 degrees of freedom
## Multiple R-squared:  0.788,  Adjusted R-squared:  0.7837 
## F-statistic: 180.3 on 2 and 97 DF,  p-value: < 2.2e-16

3. Perbandingan Model

3.1 Uji ANOVA Bertingkat

anova(model_linier, model_poli2, model_poli3)
## Analysis of Variance Table
## 
## Model 1: y ~ x
## Model 2: y ~ poly(x, 2, raw = TRUE)
## Model 3: y ~ poly(x, 3, raw = TRUE)
##   Res.Df    RSS Df Sum of Sq        F Pr(>F)    
## 1     98 762.42                                 
## 2     97 324.33  1    438.09 129.6931 <2e-16 ***
## 3     96 324.28  1      0.05   0.0155 0.9012    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

3.2 Perbandingan AIC

AIC(model_linier, model_poli2, model_poli3)
##              df      AIC
## model_linier  3 492.9204
## model_poli2   4 409.4469
## model_poli3   5 411.4307

4. Visualisasi Perbandingan Model

data$pred_linier <- predict(model_linier)
data$pred_poli2  <- predict(model_poli2)
data$pred_poli3  <- predict(model_poli3)

ggplot(data, aes(x = x, y = y)) +
  geom_point(alpha = 0.5) +
  geom_line(aes(y = pred_linier, color = "Linier"), linewidth = 1) +
  geom_line(aes(y = pred_poli2, color = "Polinomial derajat 2"), linewidth = 1) +
  geom_line(aes(y = pred_poli3, color = "Polinomial derajat 3"), linewidth = 1) +
  labs(title = "Perbandingan Regresi Linier vs Polinomial",
       x = "X", y = "Y", color = "Model") +
  theme_minimal()

5. Evaluasi dengan RMSE

rmse <- function(actual, predicted) sqrt(mean((actual - predicted)^2))

data.frame(
  Model = c("Linier", "Polinomial derajat 2", "Polinomial derajat 3"),
  RMSE  = c(rmse(data$y, data$pred_linier),
            rmse(data$y, data$pred_poli2),
            rmse(data$y, data$pred_poli3))
)
##                  Model     RMSE
## 1               Linier 2.761195
## 2 Polinomial derajat 2 1.800917
## 3 Polinomial derajat 3 1.800772

6. Pemilihan Derajat Optimal via Cross-Validation

Skema 10-fold cross-validation diulang 5 kali untuk menguji derajat polinomial 1 sampai 6.

names(data)
## [1] "x"           "y"           "pred_linier" "pred_poli2"  "pred_poli3"
library(caret)

set.seed(42)

kontrol <- trainControl(
  method = "repeatedcv",
  number = 10,
  repeats = 5
)

derajat_max <- 6

hasil_cv <- data.frame(
  derajat = integer(),
  RMSE = numeric()
)

for (d in 1:derajat_max) {
  
  data_cv <- data
  
  # Membuat variabel polynomial
  if (d == 1) {
    data_cv$x_poly <- data_cv$x
  } else {
    poly_x <- poly(data_cv$x, degree = d, raw = TRUE)
    
    data_cv$x_poly <- poly_x[, 1]
    
    for (j in 2:d) {
      data_cv[[paste0("x_poly", j)]] <- poly_x[, j]
    }
  }
  
  # Formula sesuai derajat
  if (d == 1) {
    formula_model <- y ~ x_poly
  } else {
    variabel <- paste0("x_poly", 2:d)
    formula_model <- as.formula(
      paste("y ~ x_poly +", paste(variabel, collapse = " + "))
    )
  }
  
  model_cv <- train(
    formula_model,
    data = data_cv,
    method = "lm",
    trControl = kontrol
  )
  
  hasil_cv <- rbind(
    hasil_cv,
    data.frame(
      derajat = d,
      RMSE = min(model_cv$results$RMSE)
    )
  )
}

hasil_cv
##   derajat     RMSE
## 1       1 2.757805
## 2       2 1.825068
## 3       3 1.859968
## 4       4 1.877628
## 5       5 1.871701
## 6       6 1.880719
derajat_optimal <- hasil_cv$derajat[which.min(hasil_cv$RMSE)]
cat("Derajat optimal berdasarkan CV:", derajat_optimal, "\n")
## Derajat optimal berdasarkan CV: 2
ggplot(hasil_cv, aes(x = derajat, y = RMSE)) +
  geom_line(
    color = "steelblue",
    linewidth = 1
  ) +
  geom_point(
    size = 3,
    color = "steelblue"
  ) +
  geom_vline(
    xintercept = derajat_optimal,
    linetype = "dashed",
    color = "firebrick"
  ) +
  scale_x_continuous(
    breaks = 1:derajat_max
  ) +
  labs(
    title = "Pemilihan Derajat Optimal via 10-Fold Cross-Validation",
    x = "Derajat Polinomial",
    y = "RMSE Rata-rata (Validasi Silang)"
  ) +
  theme_minimal()

7. Model Final

model_final <- lm(y ~ poly(x, derajat_optimal, raw = TRUE), data = data)
summary(model_final)
## 
## Call:
## lm(formula = y ~ poly(x, derajat_optimal, raw = TRUE), data = data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.8136 -1.1977 -0.0533  1.3549  4.3891 
## 
## Coefficients:
##                                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                            5.33982    0.53777   9.929   <2e-16 ***
## poly(x, derajat_optimal, raw = TRUE)1  1.80266    0.24855   7.253    1e-10 ***
## poly(x, derajat_optimal, raw = TRUE)2 -0.27529    0.02405 -11.447   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.829 on 97 degrees of freedom
## Multiple R-squared:  0.788,  Adjusted R-squared:  0.7837 
## F-statistic: 180.3 on 2 and 97 DF,  p-value: < 2.2e-16

8. Y Asli, Y Topi, dan Residual

data$y_topi <- predict(model_final)
data$residual <- residuals(model_final)

head(data[, c("y", "y_topi", "residual")], 10)
##           y   y_topi     residual
## 1  3.879049 5.339823 -1.460774162
## 2  4.738604 5.519101 -0.780496476
## 3  8.509213 5.692761  2.816452348
## 4  5.719529 5.860804 -0.141274434
## 5  6.017682 6.023229 -0.005546837
## 6  9.363708 6.180036  3.183672422
## 7  7.023761 6.331225  0.692535462
## 8  3.734034 6.476797 -2.742762972
## 9  5.046558 6.616751 -1.570193912
## 10 5.678924 6.751088 -1.072164008

Catatan

  • poly(x, derajat, raw = TRUE) digunakan agar koefisien dapat diinterpretasi langsung sebagai \(\beta_1 x + \beta_2 x^2 + \dots\)
  • Untuk derajat tinggi (\(\geq 4\)), sebaiknya x distandardisasi terlebih dahulu (scale(x)) agar model lebih stabil secara numerik.
  • Pertimbangkan aturan one-standard-error rule: pilih derajat terkecil dengan RMSE \(\leq\) (RMSE minimum + 1 SD) untuk model yang lebih sederhana namun performanya setara.