# Kode R tugas
# 1. NEWTON-RAPHSON: f(x) = x^3 - x - 2
f <- function(x) x^3 - x - 2
df <- function(x) 3*x^2 - 1
newton_root <- function(x0, tol = 1e-10, maxit = 100) {
x <- x0
riwayat <- data.frame(iterasi = 0, x = x, f_x = f(x))
for (i in 1:maxit) {
x_baru <- x - f(x)/df(x)
riwayat <- rbind(
riwayat,
data.frame(iterasi = i, x = x_baru, f_x = f(x_baru))
)
if (abs(x_baru - x) < tol) break
x <- x_baru
}
list(akar = x_baru, iterasi = i, tabel = riwayat)
}
hasil_newton <- newton_root(1.5)
hasil_newton$tabel
## iterasi x f_x
## 1 0 1.500000 -1.250000e-01
## 2 1 1.521739 2.136928e-03
## 3 2 1.521380 5.893874e-07
## 4 3 1.521380 4.529710e-14
## 5 4 1.521380 0.000000e+00
# Bisection
bisection <- function(a, b, tol = 1e-10, maxit = 1000) {
if (f(a)*f(b) > 0) {
stop("f(a) dan f(b) harus berlainan tanda.")
}
for (i in 1:maxit) {
m <- (a+b)/2
if (abs(f(m)) < tol || abs(b-a)/2 < tol) break
if (f(a)*f(m) < 0) {
b <- m
} else {
a <- m
}
}
list(akar = m, iterasi = i)
}
hasil_bisect <- bisection(1, 2)
hasil_uniroot <- uniroot(f, interval = c(1, 2), tol = 1e-10)
perbandingan_akar <- data.frame(
metode = c("Newton-Raphson", "Bisection", "uniroot"),
akar = c(hasil_newton$akar, hasil_bisect$akar, hasil_uniroot$root),
iterasi = c(hasil_newton$iterasi, hasil_bisect$iterasi,
hasil_uniroot$iter)
)
perbandingan_akar
## metode akar iterasi
## 1 Newton-Raphson 1.52138 4
## 2 Bisection 1.52138 33
## 3 uniroot 1.52138 8
# 2. KUANTIL t: t(0.975), df = 9
# Fungsi kuantil t
df_t <- 9
p_target <- 0.975
ft <- function(x) {
pt(x, df = df_t) - p_target
}
dft <- function(x) {
dt(x, df = df_t)
}
# Newton-Raphson dengan pengaman
newton_t <- function(x0 = 10, tol = 1e-10, maxit = 100) {
a <- 0
b <- 10
x <- x0
tabel <- data.frame(
iterasi = 0,
x = x,
f_x = ft(x)
)
for (i in 1:maxit) {
fx <- ft(x)
dfx <- dft(x)
# Menghitung langkah Newton
x_baru <- x - fx/dfx
# Jika langkah Newton tidak valid atau keluar interval,
# gunakan Bisection
if (!is.finite(x_baru) || x_baru <= a || x_baru >= b) {
x_baru <- (a + b)/2
}
# Memperbarui interval akar
if (ft(x_baru) < 0) {
a <- x_baru
} else {
b <- x_baru
}
tabel <- rbind(
tabel,
data.frame(
iterasi = i,
x = x_baru,
f_x = ft(x_baru)
)
)
# Kriteria berhenti
if (abs(ft(x_baru)) < tol ||
abs(x_baru - x) < tol) {
break
}
x <- x_baru
}
return(list(
kuantil = x_baru,
iterasi = i,
tabel = tabel
))
}
# Menjalankan metode
hasil_t <- newton_t()
# Menampilkan tabel iterasi
hasil_t$tabel
## iterasi x f_x
## 1 0 10.000000 2.499821e-02
## 2 1 5.000000 2.463052e-02
## 3 2 2.500000 8.069086e-03
## 4 3 2.209537 -2.243173e-03
## 5 4 2.260009 -8.792330e-05
## 6 5 2.262153 -1.508562e-07
## 7 6 2.262157 -4.461986e-13
# Menampilkan kuantil hasil Newton
hasil_t$kuantil
## [1] 2.262157
# Membandingkan dengan fungsi qt()
qt(0.975, df = 9)
## [1] 2.262157
# 3. SECANT DAN NEWTON: cos(x) = x
fs <- function(x) cos(x)-x
dfs <- function(x) -sin(x)-1
secant_method <- function(x0 = 0, x1 = 1,
tol = 1e-10, maxit = 100) {
n_eval <- 2
tabel <- data.frame(iterasi = 0, x = x0, f_x = fs(x0))
tabel <- rbind(
tabel,
data.frame(iterasi = 1, x = x1, f_x = fs(x1))
)
for (i in 2:maxit) {
f0 <- fs(x0)
f1 <- fs(x1)
x2 <- x1 - f1*(x1-x0)/(f1-f0)
n_eval <- n_eval + 1
tabel <- rbind(
tabel,
data.frame(iterasi = i, x = x2, f_x = fs(x2))
)
if (abs(x2-x1) < tol) break
x0 <- x1
x1 <- x2
}
list(root = x2, iterasi = i, evaluasi_f = n_eval, tabel = tabel)
}
newton_method <- function(x0 = 1, tol = 1e-10, maxit = 100) {
n_eval_f <- 0
n_eval_df <- 0
tabel <- data.frame(iterasi = 0, x = x0, f_x = fs(x0))
n_eval_f <- n_eval_f + 1
x <- x0
for (i in 1:maxit) {
fx <- fs(x)
dfx <- dfs(x)
n_eval_f <- n_eval_f + 1
n_eval_df <- n_eval_df + 1
x_baru <- x - fx/dfx
tabel <- rbind(
tabel,
data.frame(iterasi = i, x = x_baru, f_x = fs(x_baru))
)
n_eval_f <- n_eval_f + 1
if (abs(x_baru-x) < tol) break
x <- x_baru
}
list(
root = x_baru,
iterasi = i,
evaluasi_f = n_eval_f,
evaluasi_df = n_eval_df,
tabel = tabel
)
}
hasil_secant <- secant_method()
hasil_newton_cos <- newton_method()
hasil_secant$tabel
## iterasi x f_x
## 1 0 0.0000000 1.000000e+00
## 2 1 1.0000000 -4.596977e-01
## 3 2 0.6850734 8.929928e-02
## 4 3 0.7362990 4.660039e-03
## 5 4 0.7391194 -5.728599e-05
## 6 5 0.7390851 3.529262e-08
## 7 6 0.7390851 2.667866e-13
## 8 7 0.7390851 0.000000e+00
hasil_newton_cos$tabel
## iterasi x f_x
## 1 0 1.0000000 -4.596977e-01
## 2 1 0.7503639 -1.892307e-02
## 3 2 0.7391129 -4.645590e-05
## 4 3 0.7390851 -2.847206e-10
## 5 4 0.7390851 0.000000e+00
## 6 5 0.7390851 0.000000e+00
data.frame(
metode = c("Secant", "Newton"),
akar = c(hasil_secant$root, hasil_newton_cos$root),
iterasi = c(hasil_secant$iterasi, hasil_newton_cos$iterasi),
evaluasi_f = c(hasil_secant$evaluasi_f,
hasil_newton_cos$evaluasi_f),
evaluasi_turunan = c(NA, hasil_newton_cos$evaluasi_df)
)
## metode akar iterasi evaluasi_f evaluasi_turunan
## 1 Secant 0.7390851 7 8 NA
## 2 Newton 0.7390851 5 11 5
# 4. MLE PARAMETER GAMMA DENGAN NEWTON-RAPHSON
# Data contoh; ganti dengan data pengamatan Anda
set.seed(2026)
x <- rgamma(100, shape = 3.5, scale = 2)
n <- length(x)
xbar <- mean(x)
s <- sd(x)
C <- log(xbar) - mean(log(x))
g <- function(alpha) {
log(alpha) - digamma(alpha) - C
}
dg <- function(alpha) {
1/alpha - trigamma(alpha)
}
alpha0 <- 1/(2*s)
newton_gamma <- function(alpha0, tol = 1e-10, maxit = 100) {
alpha <- alpha0
tabel <- data.frame(
iterasi = 0,
alpha = alpha,
f_alpha = g(alpha)
)
for (i in 1:maxit) {
alpha_baru <- alpha - g(alpha)/dg(alpha)
if (!is.finite(alpha_baru) || alpha_baru <= 0) {
stop("Iterasi menghasilkan alpha tidak positif; coba nilai awal lain.")
}
tabel <- rbind(
tabel,
data.frame(
iterasi = i,
alpha = alpha_baru,
f_alpha = g(alpha_baru)
)
)
if (abs(alpha_baru-alpha) < tol) break
alpha <- alpha_baru
}
list(alpha = alpha_baru, iterasi = i, tabel = tabel)
}
hasil_gamma <- newton_gamma(alpha0)
hasil_gamma$tabel
## iterasi alpha f_alpha
## 1 0 0.1567648 4.753995e+00
## 2 1 0.2901283 2.272524e+00
## 3 2 0.5273550 1.077377e+00
## 4 3 0.9397992 5.015186e-01
## 5 4 1.6190406 2.223261e-01
## 6 5 2.5959366 8.756114e-02
## 7 6 3.6450014 2.615932e-02
## 8 7 4.2826326 4.028572e-03
## 9 8 4.4198410 1.293084e-04
## 10 9 4.4245421 1.420654e-07
## 11 10 4.4245473 1.716405e-13
## 12 11 4.4245473 2.220446e-16
# Estimasi parameter skala
theta_newton <- xbar/hasil_gamma$alpha
theta_newton
## [1] 1.53058
# Pembanding dengan MASS::fitdistr()
if (!requireNamespace("MASS", quietly = TRUE)) {
install.packages("MASS")
}
fit_gamma <- MASS::fitdistr(x, densfun = "gamma")
hasil_perbandingan_gamma <- data.frame(
metode = c("Newton (alpha)", "MASS::fitdistr (alpha)"),
alpha = c(
hasil_gamma$alpha,
unname(fit_gamma$estimate["shape"])
),
scale = c(
theta_newton,
1/unname(fit_gamma$estimate["rate"])
)
)
hasil_perbandingan_gamma
## metode alpha scale
## 1 Newton (alpha) 4.424547 1.530580
## 2 MASS::fitdistr (alpha) 4.424583 1.530568
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)
## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.