1. Trapezoidal dan Simpson
f1 <- function(x) sin(x)
eksak1 <- 2
trapezoidal <- function(f, a, b, n) {
h <- (b - a) / n
x <- seq(a, b, length.out = n + 1)
y <- f(x)
tengah <- if (n > 1) 2 * sum(y[2:n]) else 0
(h / 2) * (y[1] + tengah + y[n + 1])
}
simpson <- function(f, a, b, n) {
if (n %% 2 != 0) stop("n harus genap")
h <- (b - a) / n
x <- seq(a, b, length.out = n + 1)
y <- f(x)
idx_ganjil <- seq(2, n, by = 2)
sum_genap <- if (n > 2) 2 * sum(y[seq(3, n - 1, by = 2)]) else 0
(h / 3) * (y[1] + 4 * sum(y[idx_ganjil]) + sum_genap + y[n + 1])
}
n_vals <- c(4, 8, 16, 32)
galat_trap <- sapply(n_vals, function(n) abs(trapezoidal(f1, 0, pi, n) - eksak1))
galat_simp <- sapply(n_vals, function(n) abs(simpson(f1, 0, pi, n) - eksak1))
rasio_trap <- c(NA, galat_trap[1:3] / galat_trap[2:4])
rasio_simp <- c(NA, galat_simp[1:3] / galat_simp[2:4])
data.frame(
n = n_vals,
Galat_Trapezoidal = galat_trap,
Rasio_Trapezoidal = rasio_trap,
Galat_Simpson = galat_simp,
Rasio_Simpson = rasio_simp
)
## n Galat_Trapezoidal Rasio_Trapezoidal Galat_Simpson Rasio_Simpson
## 1 4 0.103881102 NA 4.559755e-03 NA
## 2 8 0.025768398 4.031337 2.691699e-04 16.94006
## 3 16 0.006429656 4.007741 1.659105e-05 16.22381
## 4 32 0.001606639 4.001930 1.033369e-06 16.05529
2. Nilai Harapan
f2 <- function(x) x * dgamma(x, shape = 3, rate = 2)
simpson_tol <- function(f, a, b, tol = 1e-8) {
n <- 2
prev <- simpson(f, a, b, n)
repeat {
n <- n * 2
curr <- simpson(f, a, b, n)
if (abs(curr - prev) < tol) {
return(list(nilai = curr, n_akhir = n))
}
prev <- curr
}
}
res_simp2 <- simpson_tol(f2, 0, 20, tol = 1e-8)
res_int2 <- integrate(f2, lower = 0, upper = Inf)
cat("Nilai Simpson :", res_simp2[["nilai"]], "(n =", res_simp2[["n_akhir"]], ")\n")
## Nilai Simpson : 1.5 (n = 4096 )
cat("Nilai integrate() :", res_int2[["value"]], "\n")
## Nilai integrate() : 1.5
cat("Nilai Eksak (3/2) :", 1.5, "\n")
## Nilai Eksak (3/2) : 1.5
cat("Selisih vs Eksak :", abs(res_simp2[["nilai"]] - 1.5), "\n")
## Selisih vs Eksak : 7.585599e-11
3. Memilih n
f3 <- function(x) 5 * x^4
eksak3 <- 1
k_vals <- 2:16
eps_vals <- 2^(-k_vals)
n_T <- numeric(length(eps_vals))
n_S <- numeric(length(eps_vals))
for (i in seq_along(eps_vals)) {
eps <- eps_vals[i]
n <- 1
while (abs(trapezoidal(f3, 0, 1, n) - eksak3) > eps) {
n <- n + 1
}
n_T[i] <- n
n <- 2
while (abs(simpson(f3, 0, 1, n) - eksak3) > eps) {
n <- n + 2
}
n_S[i] <- n
}
hasil_n <- data.frame(k = k_vals, epsilon = eps_vals, n_Trapezoidal = n_T, n_Simpson = n_S)
print(hasil_n)
## k epsilon n_Trapezoidal n_Simpson
## 1 2 2.500000e-01 3 2
## 2 3 1.250000e-01 4 2
## 3 4 6.250000e-02 6 2
## 4 5 3.125000e-02 8 4
## 5 6 1.562500e-02 11 4
## 6 7 7.812500e-03 15 4
## 7 8 3.906250e-03 21 4
## 8 9 1.953125e-03 30 6
## 9 10 9.765625e-04 42 6
## 10 11 4.882812e-04 59 8
## 11 12 2.441406e-04 83 8
## 12 13 1.220703e-04 117 10
## 13 14 6.103516e-05 166 12
## 14 15 3.051758e-05 234 14
## 15 16 1.525879e-05 331 16
plot(eps_vals, n_T, log = "xy", type = "b", pch = 16, col = "blue",
ylim = range(c(n_T, n_S)),
xlab = "Toleransi Galat (epsilon, skala log)",
ylab = "Jumlah Subinterval Minimum (n, skala log)",
main = "Perbandingan n Minimum: Trapezoidal vs Simpson")
lines(eps_vals, n_S, type = "b", pch = 17, col = "red")
legend("topright", legend = c("Trapezoidal (n_T)", "Simpson (n_S)"),
col = c("blue", "red"), pch = c(16, 17), lty = 1)

4. Proyek Mini: AUC ROC
set.seed(2026)
skor_pos <- rnorm(100, mean = 1, sd = 1)
skor_neg <- rnorm(100, mean = 0, sd = 1)
thresholds <- sort(unique(c(-Inf, skor_pos, skor_neg, Inf)), decreasing = TRUE)
tpr <- sapply(thresholds, function(t) mean(skor_pos >= t))
fpr <- sapply(thresholds, function(t) mean(skor_neg >= t))
ord <- order(fpr, tpr)
fpr_sorted <- fpr[ord]
tpr_sorted <- tpr[ord]
auc_trap <- sum(diff(fpr_sorted) * (tpr_sorted[-1] + tpr_sorted[-length(tpr_sorted)]) / 2)
prob_empiris <- mean(outer(skor_pos, skor_neg, ">")) + 0.5 * mean(outer(skor_pos, skor_neg, "=="))
prob_teoretis <- pnorm(1 / sqrt(2))
cat("AUC Metode Trapezoidal :", auc_trap, "\n")
## AUC Metode Trapezoidal : 0.7127
cat("P(skor+ > skor-) Empiris:", prob_empiris, "\n")
## P(skor+ > skor-) Empiris: 0.7127
cat("P(skor+ > skor-) Teori :", prob_teoretis, "\n")
## P(skor+ > skor-) Teori : 0.7602499