library(readxl)
library(dplyr)
library(tidyr)
library(plm)
library(lmtest)
library(car)
library(tseries)
library(sandwich)
library(knitr)
library(ggplot2)
Ubah bagian ini sesuai data Anda. File ini otomatis mendeteksi data format wide (tahun sebagai kolom, misalnya 2001, 2002, …, 2025) dan mengubahnya ke format panel long. Jika
NULL, kolom negara dan kolom indikator dideteksi otomatis, dan indikator pertama dijadikan Y. Sebaiknya isiy_vardanx_varssecara manual setelah melihat daftar indikator yang tercetak.
file_path <- "C:/Users/valem/Downloads/DATA_15_NEGARA_CLEANED.xlsx"
sheet_no <- 1
# Nama kolom persis seperti di Excel (isi hanya jika deteksi otomatis salah)
kol_negara <- NULL # contoh: "Country Name"
kol_indikator <- NULL # contoh: "Series Name" (kolom berisi nama variabel: GDP, FDI, dst.)
# Variabel regresi (isi sesuai nama indikator; spasi akan menjadi titik)
# contoh: y_var <- "GDP"; x_vars <- c("FDI", "INF", "TO")
y_var <- NULL
x_vars <- NULL
# Opsi transformasi: TRUE = ubah Y dan X positif menjadi log natural
pakai_log <- FALSE
alpha <- 0.05
sheets <- excel_sheets(file_path)
cat("Sheet ditemukan:", paste(sheets, collapse = ", "), "\n")
## Sheet ditemukan: Data_Clean, Data_Long_R
pola_tahun <- "^X?(19|20)[0-9]{2}"
# Baca semua sheet sebagai teks (agar aman digabung), deteksi kolom tahun
info <- lapply(sheets, function(sh) {
x <- as.data.frame(read_excel(file_path, sheet = sh, col_types = "text"))
nm <- names(x)
kt <- nm[grepl(pola_tahun, nm)]
ki <- setdiff(nm, kt)
ki <- ki[!grepl("code|kode", ki, ignore.case = TRUE)]
list(data = x, kol_th = kt, kol_id = ki, sheet = sh)
})
wide <- any(sapply(info, function(i) length(i$kol_th) > 0))
if (wide) {
cat("Format terdeteksi: WIDE (tahun sebagai kolom) -> diubah ke format panel long.\n")
long_list <- lapply(info, function(i) {
if (length(i$kol_th) == 0) return(NULL)
ids <- i$kol_id
neg <- if (!is.null(kol_negara)) kol_negara else {
cand <- ids[grepl("negara|country|nation|entity|wilayah", ids, ignore.case = TRUE)]
if (length(cand)) cand[1] else ids[1] }
sisa <- setdiff(ids, neg)
ind <- if (!is.null(kol_indikator)) kol_indikator else {
cand <- sisa[grepl("indikator|indicator|variab|series|seri", sisa, ignore.case = TRUE)]
if (length(cand)) cand[1] else if (length(sisa)) sisa[1] else NA_character_ }
out <- i$data[, c(neg, if (!is.na(ind)) ind, i$kol_th), drop = FALSE]
names(out)[1] <- "Negara"
if (!is.na(ind)) names(out)[2] <- "Indikator" else out$Indikator <- i$sheet
out %>%
pivot_longer(all_of(i$kol_th), names_to = "Tahun", values_to = "Nilai") %>%
mutate(Negara = trimws(Negara),
Indikator = trimws(Indikator),
Tahun = as.integer(substr(gsub("[^0-9]", "", Tahun), 1, 4)),
Nilai = suppressWarnings(as.numeric(Nilai)))
})
long_all <- bind_rows(long_list)
long_all$Indikator <- make.names(long_all$Indikator)
df <- long_all %>%
pivot_wider(names_from = Indikator, values_from = Nilai,
values_fn = ~ mean(.x, na.rm = TRUE)) %>%
mutate(across(where(is.numeric), ~ ifelse(is.nan(.x), NA, .x))) %>%
as.data.frame()
id_var <- "Negara"
time_var <- "Tahun"
} else {
cat("Format terdeteksi: LONG (sudah berbentuk panel). Kolom 1 = negara, kolom 2 = tahun.\n")
df <- as.data.frame(read_excel(file_path, sheet = sheet_no))
names(df) <- make.names(names(df))
id_var <- names(df)[1]
time_var <- names(df)[2]
}
## Format terdeteksi: WIDE (tahun sebagai kolom) -> diubah ke format panel long.
semua_var <- setdiff(names(df), c(id_var, time_var))
cat("\nVariabel/indikator tersedia:\n"); print(semua_var)
##
## Variabel/indikator tersedia:
## [1] "Foreign.direct.investment..net.inflows....of.GDP."
## [2] "Poverty.headcount.ratio.at.national.poverty.lines....of.population."
## [3] "Trade....of.GDP."
## [4] "Population..total"
# Variabel dengan seluruh data kosong dibuang
kosong <- semua_var[sapply(df[semua_var], function(z) all(is.na(z)))]
if (length(kosong)) { cat("\nDibuang (semua NA):", paste(kosong, collapse = ", "), "\n")
semua_var <- setdiff(semua_var, kosong) }
if (!is.null(y_var)) y_var <- make.names(y_var)
if (!is.null(x_vars)) x_vars <- make.names(x_vars)
if (is.null(y_var)) y_var <- semua_var[1]
if (is.null(x_vars)) x_vars <- setdiff(semua_var, y_var)
salah <- setdiff(c(y_var, x_vars), names(df))
if (length(salah)) stop("Variabel tidak ditemukan: ", paste(salah, collapse = ", "),
". Cek daftar variabel di atas.")
if (length(x_vars) < 1) stop("Minimal butuh 1 variabel independen. Data hanya berisi: ",
paste(semua_var, collapse = ", "))
cat("\nID :", id_var, "\nWaktu :", time_var,
"\nY :", y_var, "\nX :", paste(x_vars, collapse = ", "), "\n")
##
## ID : Negara
## Waktu : Tahun
## Y : Foreign.direct.investment..net.inflows....of.GDP.
## X : Poverty.headcount.ratio.at.national.poverty.lines....of.population., Trade....of.GDP., Population..total
df <- df[, c(id_var, time_var, y_var, x_vars)]
df[[time_var]] <- as.integer(df[[time_var]])
df[, c(y_var, x_vars)] <- lapply(df[, c(y_var, x_vars)], as.numeric)
n_awal <- nrow(df)
df <- na.omit(df)
cat("\nBaris sebelum/sesudah buang NA:", n_awal, "/", nrow(df), "\n")
##
## Baris sebelum/sesudah buang NA: 375 / 84
if (nrow(df) == 0) stop("Tidak ada baris lengkap. Periksa pilihan y_var dan x_vars.")
if (pakai_log) {
df[, c(y_var, x_vars)] <- lapply(df[, c(y_var, x_vars)], log)
}
pdat <- pdata.frame(df, index = c(id_var, time_var))
form <- as.formula(paste(y_var, "~", paste(x_vars, collapse = " + ")))
form
## Foreign.direct.investment..net.inflows....of.GDP. ~ Poverty.headcount.ratio.at.national.poverty.lines....of.population. +
## Trade....of.GDP. + Population..total
N <- length(unique(df[[id_var]]))
T_ <- length(unique(df[[time_var]]))
cat("Jumlah individu (N):", N, "\nJumlah periode (T):", T_,
"\nJumlah observasi :", nrow(df), "\nPanel seimbang? :", is.pbalanced(pdat), "\n")
## Jumlah individu (N): 10
## Jumlah periode (T): 25
## Jumlah observasi : 84
## Panel seimbang? : FALSE
desk <- sapply(df[, c(y_var, x_vars)], function(x)
c(N = length(x), Mean = mean(x), SD = sd(x), Min = min(x), Max = max(x)))
kable(round(t(desk), 4), caption = "Statistik deskriptif")
| N | Mean | SD | Min | Max | |
|---|---|---|---|---|---|
| Foreign.direct.investment..net.inflows….of.GDP. | 84 | 3.188100e+00 | 2.608400e+00 | -1.8557 | 1.460530e+01 |
| Poverty.headcount.ratio.at.national.poverty.lines….of.population. | 84 | 1.383570e+01 | 8.953900e+00 | 0.0000 | 5.020000e+01 |
| Trade….of.GDP. | 84 | 9.319070e+01 | 4.491710e+01 | 32.9722 | 1.866758e+02 |
| Population..total | 84 | 2.907024e+08 | 4.559845e+08 | 133.0555 | 1.411100e+09 |
Hipotesis untuk semua uji:
Uji ini menentukan apakah uji generasi pertama (LLC/IPS) cukup, atau perlu CIPS.
vars_all <- c(y_var, x_vars)
cd_var <- do.call(rbind, lapply(vars_all, function(v) {
r <- tryCatch(pcdtest(pdat[[v]] ~ 1, data = pdat, test = "cd"),
error = function(e) NULL)
if (is.null(r)) return(data.frame(Variabel = v, CD = NA, p.value = NA, Keputusan = "gagal dihitung"))
data.frame(Variabel = v, CD = round(unname(r$statistic), 4),
p.value = round(r$p.value, 4),
Keputusan = ifelse(r$p.value < alpha, "Ada CSD -> pakai CIPS", "Tidak ada CSD (independen)"))
}))
kable(cd_var, caption = "Pesaran CD pada tiap variabel")
| Variabel | CD | p.value | Keputusan |
|---|---|---|---|
| Foreign.direct.investment..net.inflows….of.GDP. | NA | NA | gagal dihitung |
| Poverty.headcount.ratio.at.national.poverty.lines….of.population. | NA | NA | gagal dihitung |
| Trade….of.GDP. | NA | NA | gagal dihitung |
| Population..total | NA | NA | gagal dihitung |
uji_ur <- function(x, test, exo = "intercept") {
r <- tryCatch(purtest(x, test = test, exo = exo, lags = "AIC", pmax = 2),
error = function(e) NULL)
if (is.null(r)) return(c(Stat = NA, p = NA))
c(Stat = unname(r$statistic$statistic), p = unname(r$statistic$p.value))
}
uji_cips <- function(x, type = "drift") {
r <- tryCatch(cipstest(x, lags = 1, type = type, model = "cmg", truncated = FALSE),
error = function(e) NULL)
if (is.null(r)) return(c(Stat = NA, p = NA))
c(Stat = unname(r$statistic), p = unname(r$p.value))
}
tabel_ur <- function(data_pdat, vars, exo = "intercept", type = "drift") {
out <- list()
for (v in vars) {
x <- data_pdat[[v]]
llc <- uji_ur(x, "levinlin", exo)
ips <- uji_ur(x, "ips", exo)
mw <- uji_ur(x, "madwu", exo)
cps <- uji_cips(x, type)
out[[v]] <- data.frame(
Variabel = v,
LLC_stat = llc["Stat"], LLC_p = llc["p"],
IPS_stat = ips["Stat"], IPS_p = ips["p"],
Fisher_ADF_stat = mw["Stat"], Fisher_ADF_p = mw["p"],
CIPS_stat = cps["Stat"], CIPS_p = cps["p"],
row.names = NULL)
}
res <- do.call(rbind, out)
res[, -1] <- round(res[, -1], 4)
res
}
ur_level <- tabel_ur(pdat, vars_all)
kable(ur_level, caption = "Uji unit root pada LEVEL (intercept)")
| Variabel | LLC_stat | LLC_p | IPS_stat | IPS_p | Fisher_ADF_stat | Fisher_ADF_p | CIPS_stat | CIPS_p | |
|---|---|---|---|---|---|---|---|---|---|
| Foreign.direct.investment..net.inflows….of.GDP. | Foreign.direct.investment..net.inflows….of.GDP. | NA | NA | NA | NA | NA | NA | NA | NA |
| Poverty.headcount.ratio.at.national.poverty.lines….of.population. | Poverty.headcount.ratio.at.national.poverty.lines….of.population. | NA | NA | NA | NA | NA | NA | NA | NA |
| Trade….of.GDP. | Trade….of.GDP. | NA | NA | NA | NA | NA | NA | NA | NA |
| Population..total | Population..total | NA | NA | NA | NA | NA | NA | NA | NA |
pdat_d <- pdata.frame(
df %>% group_by(.data[[id_var]]) %>%
mutate(across(all_of(vars_all), ~ . - dplyr::lag(.))) %>%
ungroup() %>% na.omit(),
index = c(id_var, time_var))
ur_diff <- tabel_ur(pdat_d, vars_all)
kable(ur_diff, caption = "Uji unit root pada FIRST DIFFERENCE (intercept)")
| Variabel | LLC_stat | LLC_p | IPS_stat | IPS_p | Fisher_ADF_stat | Fisher_ADF_p | CIPS_stat | CIPS_p | |
|---|---|---|---|---|---|---|---|---|---|
| Foreign.direct.investment..net.inflows….of.GDP. | Foreign.direct.investment..net.inflows….of.GDP. | NA | NA | NA | NA | NA | NA | NA | NA |
| Poverty.headcount.ratio.at.national.poverty.lines….of.population. | Poverty.headcount.ratio.at.national.poverty.lines….of.population. | NA | NA | NA | NA | NA | NA | NA | NA |
| Trade….of.GDP. | Trade….of.GDP. | NA | NA | NA | NA | NA | NA | NA | NA |
| Population..total | Population..total | NA | NA | NA | NA | NA | NA | NA | NA |
ringkas <- function(tab, label) {
data.frame(
Variabel = tab$Variabel,
LLC = ifelse(tab$LLC_p < alpha, "Stasioner", "Tidak"),
IPS = ifelse(tab$IPS_p < alpha, "Stasioner", "Tidak"),
Fisher_ADF = ifelse(tab$Fisher_ADF_p < alpha, "Stasioner", "Tidak"),
CIPS = ifelse(tab$CIPS_p < alpha, "Stasioner", "Tidak"),
Data = label)
}
kable(rbind(ringkas(ur_level, "Level"), ringkas(ur_diff, "Diff 1")),
caption = "Ringkasan keputusan (alpha = 5%)")
| Variabel | LLC | IPS | Fisher_ADF | CIPS | Data |
|---|---|---|---|---|---|
| Foreign.direct.investment..net.inflows….of.GDP. | NA | NA | NA | NA | Level |
| Poverty.headcount.ratio.at.national.poverty.lines….of.population. | NA | NA | NA | NA | Level |
| Trade….of.GDP. | NA | NA | NA | NA | Level |
| Population..total | NA | NA | NA | NA | Level |
| Foreign.direct.investment..net.inflows….of.GDP. | NA | NA | NA | NA | Diff 1 |
| Poverty.headcount.ratio.at.national.poverty.lines….of.population. | NA | NA | NA | NA | Diff 1 |
| Trade….of.GDP. | NA | NA | NA | NA | Diff 1 |
| Population..total | NA | NA | NA | NA | Diff 1 |
Catatan interpretasi: jika variabel tidak stasioner
pada level tetapi stasioner pada first difference, variabel terintegrasi
orde 1 (I(1)). Pada regresi panel statis, pertimbangkan memakai data
first difference atau uji kointegrasi (Pedroni/Kao) agar regresi tidak
lancung (spurious). Jika CIPS_p bernilai
NA, kemungkinan panel tidak seimbang (CIPS di
plm butuh panel seimbang).
# Diagnosis awal: jumlah variabel vs jumlah negara, dan rank matriks X
cat("Jumlah negara (N):", N, "| Jumlah variabel independen (K):", length(x_vars), "\n")
## Jumlah negara (N): 10 | Jumlah variabel independen (K): 3
Xm <- model.matrix(form, data = df)[, -1, drop = FALSE]
cat("Rank matriks X:", qr(Xm)$rank, "dari", ncol(Xm), "kolom\n")
## Rank matriks X: 3 dari 3 kolom
if (qr(Xm)$rank < ncol(Xm)) {
cat("PERINGATAN: ada multikolinearitas sempurna. Variabel berikut kombinasi variabel lain:\n")
print(alias(lm(form, data = df))$Complete)
}
if (length(x_vars) >= N - 1) cat("PERINGATAN: K terlalu besar dibanding N; kurangi variabel X.\n")
pool <- plm(form, data = pdat, model = "pooling") # Common Effect Model (CEM)
fe <- plm(form, data = pdat, model = "within") # Fixed Effect Model (FEM)
# REM: coba beberapa metode estimasi komponen error jika yang pertama gagal
re <- NULL; metode_re <- NA
for (m in c("swar", "walhus", "amemiya", "nerlove")) {
re <- tryCatch(plm(form, data = pdat, model = "random", random.method = m),
error = function(e) NULL)
if (!is.null(re)) { metode_re <- m; break }
}
re_ok <- !is.null(re)
if (re_ok) {
cat("REM berhasil diestimasi dengan metode:", metode_re, "\n")
} else {
cat("REM GAGAL diestimasi (matriks singular). Perbaiki variabel X (lihat diagnosis di atas).",
"Analisis dilanjutkan tanpa REM (hanya CEM dan FEM).\n")
}
## REM berhasil diestimasi dengan metode: amemiya
summary(pool)
## Pooling Model
##
## Call:
## plm(formula = form, data = pdat, model = "pooling")
##
## Unbalanced Panel: n = 10, T = 1-25, N = 84
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -5.0735 -0.9672 -0.0789 0.5542 9.3309
##
## Coefficients:
## Estimate
## (Intercept) -1.2176e+00
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. 8.2686e-02
## Trade....of.GDP. 3.1153e-02
## Population..total 1.2333e-09
## Std. Error
## (Intercept) 9.2290e-01
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. 2.8648e-02
## Trade....of.GDP. 6.8866e-03
## Population..total 6.9734e-10
## t-value
## (Intercept) -1.3194
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. 2.8863
## Trade....of.GDP. 4.5238
## Population..total 1.7686
## Pr(>|t|)
## (Intercept) 0.19081
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. 0.00501
## Trade....of.GDP. 2.084e-05
## Population..total 0.08077
##
## (Intercept)
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. **
## Trade....of.GDP. ***
## Population..total .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 564.73
## Residual Sum of Squares: 397.36
## R-Squared: 0.29637
## Adj. R-Squared: 0.26998
## F-statistic: 11.232 on 3 and 80 DF, p-value: 3.1574e-06
summary(fe)
## Oneway (individual) effect Within Model
##
## Call:
## plm(formula = form, data = pdat, model = "within")
##
## Unbalanced Panel: n = 10, T = 1-25, N = 84
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -4.890 -0.835 0.000 0.799 4.853
##
## Coefficients:
## Estimate
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. -5.1113e-02
## Trade....of.GDP. 2.4845e-03
## Population..total -1.5997e-08
## Std. Error
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. 2.9780e-02
## Trade....of.GDP. 1.4077e-02
## Population..total 1.2810e-08
## t-value
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. -1.7163
## Trade....of.GDP. 0.1765
## Population..total -1.2488
## Pr(>|t|)
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. 0.09046 .
## Trade....of.GDP. 0.86041
## Population..total 0.21584
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 169.24
## Residual Sum of Squares: 161.57
## R-Squared: 0.045272
## Adj. R-Squared: -0.11609
## F-statistic: 1.12225 on 3 and 71 DF, p-value: 0.34594
if (re_ok) summary(re) else cat("REM tidak tersedia.\n")
## Oneway (individual) effect Random Effect Model
## (Amemiya's transformation)
##
## Call:
## plm(formula = form, data = pdat, model = "random", random.method = m)
##
## Unbalanced Panel: n = 10, T = 1-25, N = 84
##
## Effects:
## var std.dev share
## idiosyncratic 2.276 1.509 0.096
## individual 21.527 4.640 0.904
## theta:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.6908 0.9066 0.9256 0.9046 0.9351 0.9351
##
## Residuals:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -5.0080 -0.9403 -0.0823 -0.0563 0.5783 4.7888
##
## Coefficients:
## Estimate
## (Intercept) 4.6272e+00
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. -2.8581e-02
## Trade....of.GDP. 9.5739e-03
## Population..total -2.9315e-09
## Std. Error
## (Intercept) 2.3158e+00
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. 2.4536e-02
## Trade....of.GDP. 1.3064e-02
## Population..total 3.6652e-09
## z-value
## (Intercept) 1.9981
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. -1.1649
## Trade....of.GDP. 0.7328
## Population..total -0.7998
## Pr(>|z|)
## (Intercept) 0.0457 *
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. 0.2441
## Trade....of.GDP. 0.4637
## Population..total 0.4238
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 193.81
## Residual Sum of Squares: 177.8
## R-Squared: 0.085642
## Adj. R-Squared: 0.051354
## Chisq: 2.54418 on 3 DF, p-value: 0.46736
H0: CEM lebih baik. H1: FEM lebih baik.
chow <- pFtest(fe, pool)
chow
##
## F test for individual effects
##
## data: form
## F = 11.512, df1 = 9, df2 = 71, p-value = 6.529e-11
## alternative hypothesis: significant effects
H0: REM konsisten (REM lebih baik). H1: FEM lebih baik.
if (re_ok) {
haus <- phtest(fe, re)
} else {
haus <- list(p.value = NA_real_)
cat("Uji Hausman tidak dapat dihitung karena REM tidak tersedia.\n")
}
haus
##
## Hausman Test
##
## data: form
## chisq = 3.0984, df = 3, p-value = 0.3767
## alternative hypothesis: one model is inconsistent
H0: CEM lebih baik. H1: REM lebih baik.
lmbp <- plmtest(pool, type = "bp", effect = "individual")
lmbp
##
## Lagrange Multiplier Test - (Breusch-Pagan)
##
## data: form
## chisq = 10.591, df = 1, p-value = 0.001136
## alternative hypothesis: significant effects
pilih <- if (chow$p.value < alpha) {
if (!re_ok || haus$p.value < alpha) "Fixed Effect Model (FEM)" else "Random Effect Model (REM)"
} else {
if (re_ok && lmbp$p.value < alpha) "Random Effect Model (REM)" else "Common Effect Model (CEM)"
}
final <- switch(pilih,
"Fixed Effect Model (FEM)" = fe,
"Random Effect Model (REM)" = re,
"Common Effect Model (CEM)" = pool)
kable(data.frame(
Uji = c("Chow", "Hausman", "LM Breusch-Pagan"),
p.value = round(c(chow$p.value, haus$p.value, lmbp$p.value), 4)),
caption = "Ringkasan uji pemilihan model")
| Uji | p.value | |
|---|---|---|
| F | Chow | 0.0000 |
| Hausman | 0.3767 | |
| chisq | LM Breusch-Pagan | 0.0011 |
cat("\nModel terpilih:", pilih, "\n")
##
## Model terpilih: Random Effect Model (REM)
H0: residual berdistribusi normal.
res_final <- as.numeric(residuals(final))
jb <- jarque.bera.test(res_final)
sw <- if (length(res_final) <= 5000) shapiro.test(res_final) else NULL
jb
##
## Jarque Bera Test
##
## data: res_final
## X-squared = 18.078, df = 2, p-value = 0.0001187
sw
##
## Shapiro-Wilk normality test
##
## data: res_final
## W = 0.95563, p-value = 0.005624
hist(res_final, breaks = 20, main = "Histogram Residual", xlab = "Residual", col = "grey80")
qqnorm(res_final); qqline(res_final)
Nilai VIF < 10 (ketat: < 5) menunjukkan tidak ada multikolinearitas serius.
if (length(x_vars) > 1) {
vif_val <- car::vif(lm(form, data = df))
kable(data.frame(Variabel = names(vif_val), VIF = round(as.numeric(vif_val), 3)),
caption = "Variance Inflation Factor")
kable(round(cor(df[, x_vars]), 3), caption = "Matriks korelasi antar variabel independen")
} else {
cat("Hanya satu variabel independen; VIF tidak relevan.")
}
| Poverty.headcount.ratio.at.national.poverty.lines….of.population. | Trade….of.GDP. | Population..total | |
|---|---|---|---|
| Poverty.headcount.ratio.at.national.poverty.lines….of.population. | 1.000 | 0.196 | -0.300 |
| Trade….of.GDP. | 0.196 | 1.000 | -0.612 |
| Population..total | -0.300 | -0.612 | 1.000 |
a. Breusch-Pagan (pooled) - H0: homoskedastis.
bp <- bptest(form, data = pdat, studentize = FALSE)
bp
##
## Breusch-Pagan test
##
## data: form
## BP = 39.014, df = 3, p-value = 1.724e-08
b. Modified Wald (groupwise heteroskedasticity, untuk FEM) - H0: homoskedastis antar unit (sigma_i^2 = sigma^2).
modified_wald <- function(model) {
e <- as.numeric(residuals(model))
id <- as.character(index(model)[[1]])
s2i <- tapply(e, id, function(z) mean(z^2))
Ti <- tapply(e, id, length)
Vi <- sapply(names(s2i), function(g) {
z <- e[id == g]
sum((z^2 - s2i[[g]])^2) / (length(z) * (length(z) - 1))
})
s2 <- mean(s2i)
W <- sum((s2i - s2)^2 / Vi)
df_ <- length(s2i)
list(statistic = W, df = df_, p.value = pchisq(W, df_, lower.tail = FALSE))
}
mw <- modified_wald(fe)
cat("Modified Wald chi2 =", round(mw$statistic, 4), "| df =", mw$df,
"| p-value =", round(mw$p.value, 4), "\n")
## Modified Wald chi2 = NaN | df = 10 | p-value = NaN
a. Wooldridge - H0: tidak ada autokorelasi orde pertama.
pwar <- pwartest(fe)
pwar
##
## Wooldridge's test for serial correlation in FE panels
##
## data: fe
## F = 20.4, df1 = 1, df2 = 72, p-value = 2.403e-05
## alternative hypothesis: serial correlation
b. Breusch-Godfrey/Wooldridge panel
pbg <- pbgtest(fe)
pbg
##
## Breusch-Godfrey/Wooldridge test for serial correlation in panel models
##
## data: form
## chisq = 8.6472, df = 1, p-value = 0.003276
## alternative hypothesis: serial correlation in idiosyncratic errors
a. Pesaran CD - H0: tidak ada dependensi antar-unit.
cd1 <- pcdtest(final, test = "cd")
cd1
##
## Pesaran CD test for cross-sectional dependence in panels
##
## data: Foreign.direct.investment..net.inflows....of.GDP. ~ Poverty.headcount.ratio.at.national.poverty.lines....of.population. + Trade....of.GDP. + Population..total
## z = 1.4075, p-value = 0.1593
## alternative hypothesis: cross-sectional dependence
b. Breusch-Pagan LM (cocok bila T > N)
cd2 <- pcdtest(fe, test = "lm")
cd2
##
## Breusch-Pagan LM test for cross-sectional dependence in panels
##
## data: Foreign.direct.investment..net.inflows....of.GDP. ~ Poverty.headcount.ratio.at.national.poverty.lines....of.population. + Trade....of.GDP. + Population..total
## chisq = 21.767, df = 13, p-value = 0.05907
## alternative hypothesis: cross-sectional dependence
asumsi <- data.frame(
Uji = c("Jarque-Bera (normalitas)", "Breusch-Pagan (heteroskedastisitas)",
"Modified Wald (heteroskedastisitas grup)", "Wooldridge (autokorelasi)",
"Pesaran CD (cross-sectional dependence)"),
p.value = round(c(jb$p.value, bp$p.value, mw$p.value, pwar$p.value, cd1$p.value), 4))
asumsi$Keputusan <- ifelse(asumsi$p.value < alpha, "Asumsi dilanggar", "Asumsi terpenuhi")
kable(asumsi, caption = "Ringkasan uji asumsi (alpha = 5%)")
| Uji | p.value | Keputusan |
|---|---|---|
| Jarque-Bera (normalitas) | 0.0001 | Asumsi dilanggar |
| Breusch-Pagan (heteroskedastisitas) | 0.0000 | Asumsi dilanggar |
| Modified Wald (heteroskedastisitas grup) | NaN | NA |
| Wooldridge (autokorelasi) | 0.0000 | Asumsi dilanggar |
| Pesaran CD (cross-sectional dependence) | 0.1593 | Asumsi terpenuhi |
Menguji apakah intersep (efek individu) berbeda antar negara. H0: tidak ada heterogenitas individu (pooling dapat dipakai). Ini setara dengan uji Chow di atas.
pFtest(fe, pool)
##
## F test for individual effects
##
## data: form
## F = 11.512, df1 = 9, df2 = 71, p-value = 6.529e-11
## alternative hypothesis: significant effects
H0: koefisien slope sama untuk semua negara (homogen). Jika ditolak, koefisien berbeda antar negara.
Sudah diuji lewat Modified Wald dan Breusch-Pagan di atas. Visualisasi:
dres <- data.frame(Negara = as.character(index(final)[[1]]), Residual = as.numeric(residuals(final)))
ggplot(dres, aes(x = Negara, y = Residual)) +
geom_boxplot(fill = "grey85") +
geom_hline(yintercept = 0, linetype = "dashed") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 60, hjust = 1)) +
labs(title = "Sebaran residual per negara", x = NULL)
fx <- fixef(fe)
kable(data.frame(Negara = names(fx), Efek_Individu = round(as.numeric(fx), 4)),
caption = "Intersep spesifik tiap negara (FEM)")
| Negara | Efek_Individu |
|---|---|
| CAMBODIA | 8.9826 |
| CHINA | 24.7698 |
| FIJI | 7.0012 |
| INDONESIA | 6.1427 |
| MALAYSIA | 4.0070 |
| MONGOLIA | 15.7067 |
| PHILIPINA | 3.8656 |
| SOLOMON ISLAND | 2.4128 |
| THAILAND | 2.7512 |
| VIETNAM | 6.5307 |
Jika terdapat heteroskedastisitas, autokorelasi, atau cross-sectional dependence, gunakan standar error robust agar inferensi valid.
cat("Model terpilih:", pilih, "\n\n")
## Model terpilih: Random Effect Model (REM)
cat("--- Standar error konvensional ---\n")
## --- Standar error konvensional ---
print(coeftest(final))
##
## t test of coefficients:
##
## Estimate
## (Intercept) 4.6272e+00
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. -2.8581e-02
## Trade....of.GDP. 9.5739e-03
## Population..total -2.9315e-09
## Std. Error
## (Intercept) 2.3158e+00
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. 2.4536e-02
## Trade....of.GDP. 1.3064e-02
## Population..total 3.6652e-09
## t value
## (Intercept) 1.9981
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. -1.1649
## Trade....of.GDP. 0.7328
## Population..total -0.7998
## Pr(>|t|)
## (Intercept) 0.0491 *
## Poverty.headcount.ratio.at.national.poverty.lines....of.population. 0.2475
## Trade....of.GDP. 0.4658
## Population..total 0.4262
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cat("\n--- Robust Arellano (cluster per negara; atasi heteroskedastisitas & autokorelasi) ---\n")
##
## --- Robust Arellano (cluster per negara; atasi heteroskedastisitas & autokorelasi) ---
cat("\n--- Driscoll-Kraay (atasi heteroskedastisitas, autokorelasi, & cross-sectional dependence) ---\n")
##
## --- Driscoll-Kraay (atasi heteroskedastisitas, autokorelasi, & cross-sectional dependence) ---
s <- summary(final)
cat("R-squared :", round(s$r.squared["rsq"], 4),
"\nAdj. R-squared:", round(s$r.squared["adjrsq"], 4),
"\nF-statistic :", round(s$fstatistic$statistic, 4),
"(p =", round(s$fstatistic$p.value, 4), ")\n")
## R-squared : 0.0856
## Adj. R-squared: 0.0514
## F-statistic : 2.5442 (p = 0.4674 )
Tulis kesimpulan Anda berdasarkan keluaran di atas:
sessionInfo()
## R version 4.6.1 (2026-06-24 ucrt)
## Platform: x86_64-w64-mingw32/x64
## Running under: Windows 11 x64 (build 26200)
##
## Matrix products: default
## LAPACK version 3.12.1
##
## locale:
## [1] LC_COLLATE=English_Indonesia.utf8 LC_CTYPE=English_Indonesia.utf8
## [3] LC_MONETARY=English_Indonesia.utf8 LC_NUMERIC=C
## [5] LC_TIME=English_Indonesia.utf8
##
## time zone: Asia/Makassar
## tzcode source: internal
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] ggplot2_4.0.4 knitr_1.52 sandwich_3.1-3 tseries_0.10-63
## [5] car_3.1-5 carData_3.0-6 lmtest_0.9-40 zoo_1.9-1
## [9] plm_2.6-7 tidyr_1.3.2 dplyr_1.2.1 readxl_1.6.0
##
## loaded via a namespace (and not attached):
## [1] sass_0.4.10 generics_0.1.4 lattice_0.22-9 digest_0.6.39
## [5] magrittr_2.0.5 RColorBrewer_1.1-3 evaluate_1.0.5 grid_4.6.1
## [9] fastmap_1.2.0 cellranger_1.1.0 jsonlite_2.0.0 Formula_1.2-6
## [13] purrr_1.2.2 scales_1.4.0 jquerylib_0.1.4 abind_1.4-8
## [17] Rdpack_2.6.6 cli_3.6.6 rlang_1.3.0 rbibutils_2.4.1
## [21] miscTools_0.6-30 withr_3.0.3 cachem_1.1.0 yaml_2.3.12
## [25] otel_0.3.0 tools_4.6.1 parallel_4.6.1 bdsmatrix_1.3-7
## [29] maxLik_1.6-10 curl_8.0.0 vctrs_0.7.3 R6_2.6.1
## [33] lifecycle_1.0.5 MASS_7.3-65 pkgconfig_2.0.3 gtable_0.3.6
## [37] pillar_1.11.1 bslib_0.12.0 quantmod_0.4.29 glue_1.8.1
## [41] Rcpp_1.1.2 collapse_2.1.9 xfun_0.60 tibble_3.3.1
## [45] tidyselect_1.2.1 rstudioapi_0.19.0 farver_2.1.2 htmltools_0.5.9
## [49] nlme_3.1-169 labeling_0.4.3 xts_0.14.3 rmarkdown_2.31
## [53] compiler_4.6.1 S7_0.2.2 quadprog_1.5-8 TTR_0.24.4