pkgs <- c(
"readxl", "dplyr", "tidyr", "stringr", "zoo",
"plm", "lmtest", "car", "knitr", "kableExtra"
)
installed <- rownames(installed.packages())
for (p in pkgs) {
if (!p %in% installed) {
install.packages(p, dependencies = TRUE)
}
}
library(readxl)
library(dplyr)
library(tidyr)
library(stringr)
library(zoo)
library(plm)
library(lmtest)
library(car)
library(knitr)
library(kableExtra)parse_num <- function(x) {
s <- str_trim(as.character(x))
has_pct <- str_detect(s, "%")
s_clean <- str_replace_all(s, "%", "")
s_clean <- str_replace_all(s_clean, ",", "")
s_clean[s_clean %in% c("", "..", "NA", "NaN", "null", "NULL", "-")] <- NA_character_
val <- suppressWarnings(as.numeric(s_clean))
ifelse(!is.na(val) & has_pct, val / 100, val)
}
interp_vec <- function(x, yr) {
non_na <- sum(!is.na(x))
if (non_na >= 2) {
as.numeric(zoo::na.approx(x, x = yr, na.rm = FALSE, rule = 2))
} else if (non_na == 1) {
rep(x[!is.na(x)][1], length(x))
} else {
rep(NA_real_, length(x))
}
}
run_cips_manual <- function(df, var_name, lags = 1) {
countries <- sort(unique(df$country))
years <- sort(unique(df$year))
N <- length(countries)
T_len <- length(years)
Y_mat <- sapply(countries, function(ct) {
df$value[df$country == ct][match(years, df$year[df$country == ct])]
})
y_bar <- rowMeans(Y_mat, na.rm = TRUE)
dy_mat <- apply(Y_mat, 2, function(col) c(NA, diff(col)))
dy_bar <- c(NA, diff(y_bar))
t_stats <- numeric(N)
names(t_stats) <- countries
for (j in seq_len(N)) {
y_j <- Y_mat[, j]
dy_j <- dy_mat[, j]
lag_y <- c(NA, y_j[-T_len])
lag_ybar <- c(NA, y_bar[-T_len])
lag_dybar <- c(NA, dy_bar[-T_len])
lag_dyj <- c(NA, dy_j[-T_len])
data_cadf <- data.frame(
dy = dy_j,
lag_y = lag_y,
lag_ybar = lag_ybar,
dybar = dy_bar,
lag_dybar = lag_dybar,
lag_dyj = lag_dyj
)
if (lags >= 1) {
for (l in seq_len(lags)) {
data_cadf[[paste0("lag_dyj_", l)]] <- c(rep(NA, l), dy_j[seq_len(T_len - l)])
}
}
fit_cadf <- lm(dy ~ ., data = data_cadf, na.action = na.omit)
sm_fit <- summary(fit_cadf)$coefficients
t_stats[j] <- if ("lag_y" %in% rownames(sm_fit)) sm_fit["lag_y", "t value"] else NA_real_
}
cips_stat <- mean(t_stats, na.rm = TRUE)
kesimpulan <- ifelse(cips_stat < -2.23, "Stasioner (p < 0.05)", "Tidak Stasioner / Akar Unit")
data.frame(
Variabel = var_name,
Statistik_CIPS = cips_stat,
N_Negara = N,
T_Tahun = T_len,
Keterangan = kesimpulan
)
}
pesaran_yamagata_test <- function(df, formula_obj) {
countries <- unique(df$country)
N <- length(countries)
vars_all <- all.vars(formula_obj)
y_name <- vars_all[1]
x_names <- vars_all[-1]
k <- length(x_names)
fit_pool <- lm(formula_obj, data = df)
beta_pool <- coef(fit_pool)[x_names]
resid_pool <- residuals(fit_pool)
n_tot <- length(resid_pool)
sigma2_pool <- sum(resid_pool^2) / max(1, (n_tot - N - k))
s_tilde_list <- numeric(N)
names(s_tilde_list) <- countries
valid_n <- 0L
for (ct in countries) {
sub_ct <- df[df$country == ct, , drop = FALSE]
T_i <- nrow(sub_ct)
if (T_i > (k + 2)) {
X_mat <- as.matrix(sub_ct[, x_names, drop = FALSE])
y_vec <- sub_ct[[y_name]]
X_dm <- scale(X_mat, center = TRUE, scale = FALSE)
y_dm <- y_vec - mean(y_vec, na.rm = TRUE)
XtX <- crossprod(X_dm)
XtX_inv <- try(solve(XtX), silent = TRUE)
if (!inherits(XtX_inv, "try-error")) {
beta_i <- as.numeric(XtX_inv %*% crossprod(X_dm, y_dm))
diff_b <- beta_i - beta_pool
s_tilde_list[ct] <- as.numeric(t(diff_b) %*% XtX %*% diff_b) / sigma2_pool
valid_n <- valid_n + 1L
}
}
}
S_tilde <- sum(s_tilde_list, na.rm = TRUE)
T_bar <- mean(sapply(countries, function(ct) sum(df$country == ct)))
delta_tilde <- sqrt(valid_n) * ((S_tilde / valid_n) - k) / sqrt(2 * k)
v_nk <- max(1e-6, (2 * k * (T_bar - k - 1)) / (T_bar + 1))
delta_adj <- sqrt(valid_n) * ((S_tilde / valid_n) - k) / sqrt(v_nk)
pval_delta <- 2 * (1 - pnorm(abs(delta_tilde)))
pval_adj <- 2 * (1 - pnorm(abs(delta_adj)))
data.frame(
Statistik = c("Delta_tilde (Pesaran-Yamagata)", "Delta_tilde_adj"),
Nilai = c(delta_tilde, delta_adj),
P_Value = c(pval_delta, pval_adj),
Keputusan = ifelse(
c(pval_delta, pval_adj) < 0.05,
"Tolak H0: Slope Heterogen antar-negara",
"Gagal Tolak H0: Slope Homogen"
)
)
}file_path <- "Data indonesia pacific sri 1.xlsx"
stopifnot(file.exists(file_path))
sheets_avail <- readxl::excel_sheets(file_path)
target_sheet <- if ("Data Model Manusia" %in% sheets_avail) {
"Data Model Manusia"
} else {
sheets_avail[1]
}
raw_df <- readxl::read_excel(file_path, sheet = target_sheet, col_names = FALSE)
year_row_idx <- which(apply(raw_df, 1, function(r) {
nums <- suppressWarnings(as.numeric(as.character(r)))
sum(!is.na(nums) & nums >= 1990 & nums <= 2030) >= 10
}))[1]
stopifnot(!is.na(year_row_idx))
years_vec <- suppressWarnings(as.numeric(as.character(unlist(raw_df[year_row_idx, ]))))
valid_year_cols <- which(!is.na(years_vec) & years_vec >= 1990 & years_vec <= 2030)
years_clean <- as.integer(years_vec[valid_year_cols])
data_rows <- raw_df[(year_row_idx + 1):nrow(raw_df), , drop = FALSE]
long_list <- list()
current_country <- NA_character_
idx_counter <- 1L
for (i in seq_len(nrow(data_rows))) {
c_val <- str_trim(as.character(data_rows[[2]][i]))
if (!is.na(c_val) && nzchar(c_val) && !c_val %in% c("NA", "NaN")) {
current_country <- c_val
}
ind_val <- str_trim(as.character(data_rows[[3]][i]))
if (is.na(current_country) || is.na(ind_val) || !nzchar(ind_val)) next
vals_num <- parse_num(unlist(data_rows[i, valid_year_cols]))
long_list[[idx_counter]] <- tibble(
country = current_country,
indicator = ind_val,
year = years_clean,
value = vals_num
)
idx_counter <- idx_counter + 1L
}
long_df <- bind_rows(long_list) %>%
mutate(
var_code = case_when(
str_detect(str_to_lower(indicator), "education") ~ "edu_exp",
str_detect(str_to_lower(indicator), "health") ~ "health_exp",
str_detect(str_to_lower(indicator), "life expectancy") ~ "life_exp",
str_detect(str_to_lower(indicator), "gdp per capita") ~ "gdp_pc",
TRUE ~ make.names(indicator)
)
) %>%
group_by(country, year, var_code) %>%
summarise(
value = if (all(is.na(value))) NA_real_ else mean(value, na.rm = TRUE),
.groups = "drop"
)
panel_raw <- long_df %>%
pivot_wider(names_from = var_code, values_from = value) %>%
arrange(country, year)
for (col_nm in c("gdp_pc", "edu_exp", "health_exp", "life_exp")) {
if (!col_nm %in% names(panel_raw)) {
panel_raw[[col_nm]] <- NA_real_
}
}
panel_bal <- panel_raw %>%
filter(year >= 2001 & year <= 2023) %>%
group_by(country) %>%
arrange(year, .by_group = TRUE) %>%
mutate(
gdp_pc_i = interp_vec(gdp_pc, year),
edu_exp_i = interp_vec(edu_exp, year),
health_exp_i = interp_vec(health_exp, year),
life_exp_i = interp_vec(life_exp, year)
) %>%
ungroup() %>%
mutate(
ln_gdp = ifelse(!is.na(gdp_pc_i) & gdp_pc_i > 0, log(gdp_pc_i), NA_real_),
edu = edu_exp_i,
health = health_exp_i,
life = life_exp_i
) %>%
filter(!is.na(ln_gdp) & !is.na(edu) & !is.na(health) & !is.na(life))
common_years <- Reduce(intersect, split(panel_bal$year, panel_bal$country))
panel_bal <- panel_bal %>%
filter(year %in% common_years) %>%
arrange(country, year)
pdata <- pdata.frame(panel_bal, index = c("country", "year"))
form_panel <- ln_gdp ~ edu + health + lifeHipotesis nol (\(H_0\)) uji cross-sectional dependence adalah cross-sectional independence (tidak ada korelasi lintas-seksi antar-negara).
fe_init <- plm(form_panel, data = pdata, model = "within")
cd_pesaran <- pcdtest(fe_init, test = "cd")
cd_bp_lm <- pcdtest(fe_init, test = "lm")
cd_model_tbl <- data.frame(
Uji = c("Pesaran CD Test (Residual FEM)", "Breusch-Pagan LM Test (Residual FEM)"),
Statistik = c(as.numeric(cd_pesaran$statistic), as.numeric(cd_bp_lm$statistic)),
P_Value = c(as.numeric(cd_pesaran$p.value), as.numeric(cd_bp_lm$p.value)),
Status_Independensi = ifelse(
c(as.numeric(cd_pesaran$p.value), as.numeric(cd_bp_lm$p.value)) >= 0.05,
"Gagal Tolak H0: Cross-Sectional Independent",
"Tolak H0: Ada Cross-Sectional Dependence"
)
)
kable(cd_model_tbl, digits = 4, caption = "Uji Cross-Sectional Independence pada Residual Model Panel") %>%
kable_styling(bootstrap_options = c("striped", "hover"), full_width = FALSE)| Uji | Statistik | P_Value | Status_Independensi |
|---|---|---|---|
| Pesaran CD Test (Residual FEM) | 7.5845 | 0 | Tolak H0: Ada Cross-Sectional Dependence |
| Breusch-Pagan LM Test (Residual FEM) | 452.3273 | 0 | Tolak H0: Ada Cross-Sectional Dependence |
cd_vars <- lapply(c("ln_gdp", "edu", "health", "life"), function(v) {
res <- pcdtest(pdata[[v]], test = "cd")
pval <- as.numeric(res$p.value)
data.frame(
Variabel = v,
Statistik_CD = as.numeric(res$statistic),
P_Value = pval,
Status_Independensi = ifelse(
pval >= 0.05,
"Cross-Sectional Independent",
"Ada Cross-Sectional Dependence"
)
)
}) %>% bind_rows()
kable(cd_vars, digits = 4, caption = "Uji Pesaran CD per Variabel (pseries)") %>%
kable_styling(bootstrap_options = c("striped", "hover"), full_width = FALSE)| Variabel | Statistik_CD | P_Value | Status_Independensi |
|---|---|---|---|
| ln_gdp | 41.0789 | 0.0000 | Ada Cross-Sectional Dependence |
| edu | -0.4415 | 0.6588 | Cross-Sectional Independent |
| health | 6.6317 | 0.0000 | Ada Cross-Sectional Dependence |
| life | 37.9252 | 0.0000 | Ada Cross-Sectional Dependence |
cips_results <- lapply(c("ln_gdp", "edu", "health", "life"), function(v) {
sub_df <- panel_bal %>% select(country, year, value = all_of(v))
run_cips_manual(sub_df, v, lags = 1)
}) %>% bind_rows()
kable(cips_results, digits = 4, caption = "Uji Stasioneritas Generasi Kedua (Pesaran CIPS)") %>%
kable_styling(bootstrap_options = c("striped", "hover"), full_width = FALSE)| Variabel | Statistik_CIPS | N_Negara | T_Tahun | Keterangan |
|---|---|---|---|---|
| ln_gdp | -2.2655 | 15 | 23 | Stasioner (p < 0.05) |
| edu | -1.7494 | 15 | 23 | Tidak Stasioner / Akar Unit |
| health | -2.0238 | 15 | 23 | Tidak Stasioner / Akar Unit |
| life | -2.4367 | 15 | 23 | Stasioner (p < 0.05) |
het_tbl <- pesaran_yamagata_test(panel_bal, form_panel)
kable(het_tbl, digits = 4, caption = "Uji Heterogenitas Slope (Pesaran & Yamagata)") %>%
kable_styling(bootstrap_options = c("striped", "hover"), full_width = FALSE)| Statistik | Nilai | P_Value | Keputusan |
|---|---|---|---|
| Delta_tilde (Pesaran-Yamagata) | 0.7699 | 0.4414 | Gagal Tolak H0: Slope Homogen |
| Delta_tilde_adj | 0.8653 | 0.3869 | Gagal Tolak H0: Slope Homogen |
cem_mod <- plm(form_panel, data = pdata, model = "pooling")
fem_mod <- plm(form_panel, data = pdata, model = "within", effect = "individual")
rem_mod <- plm(form_panel, data = pdata, model = "random", effect = "individual")
chow_test <- pFtest(fem_mod, cem_mod)
hausman_test <- phtest(fem_mod, rem_mod)
bplm_test <- plmtest(cem_mod, type = "bp")
cat("--- Ringkasan CEM ---\n")## --- Ringkasan CEM ---
## Pooling Model
##
## Call:
## plm(formula = form_panel, data = pdata, model = "pooling")
##
## Balanced Panel: n = 15, T = 23, N = 345
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -2.541 -0.329 0.100 0.277 1.738
##
## Coefficients:
## Estimate Std. Error t-value Pr(>|t|)
## (Intercept) -7.1809952 0.3867272 -18.5686 < 2.2e-16 ***
## edu -0.0077740 0.0191739 -0.4054 0.6854
## health -0.0841943 0.0181851 -4.6299 5.21e-06 ***
## life 0.2212783 0.0056449 39.1994 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 757.13
## Residual Sum of Squares: 130.31
## R-Squared: 0.8279
## Adj. R-Squared: 0.82638
## F-statistic: 546.788 on 3 and 341 DF, p-value: < 2.22e-16
##
## --- Ringkasan FEM ---
## Oneway (individual) effect Within Model
##
## Call:
## plm(formula = form_panel, data = pdata, effect = "individual",
## model = "within")
##
## Balanced Panel: n = 15, T = 23, N = 345
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -1.1482 -0.1249 0.0106 0.1446 1.5054
##
## Coefficients:
## Estimate Std. Error t-value Pr(>|t|)
## edu -0.05349987 0.01838044 -2.9107 0.003854 **
## health 0.00083196 0.01864089 0.0446 0.964429
## life 0.21734584 0.00846563 25.6739 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 101.57
## Residual Sum of Squares: 30.303
## R-Squared: 0.70167
## Adj. R-Squared: 0.68616
## F-statistic: 256.365 on 3 and 327 DF, p-value: < 2.22e-16
##
## --- Ringkasan REM ---
## Oneway (individual) effect Random Effect Model
## (Swamy-Arora's transformation)
##
## Call:
## plm(formula = form_panel, data = pdata, effect = "individual",
## model = "random")
##
## Balanced Panel: n = 15, T = 23, N = 345
##
## Effects:
## var std.dev share
## idiosyncratic 0.09267 0.30442 0.198
## individual 0.37580 0.61303 0.802
## theta: 0.897
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -1.2836 -0.1302 0.0239 0.1515 1.4878
##
## Coefficients:
## Estimate Std. Error z-value Pr(>|z|)
## (Intercept) -7.0821024 0.5972727 -11.8574 < 2.2e-16 ***
## edu -0.0528495 0.0179961 -2.9367 0.003317 **
## health -0.0027042 0.0182471 -0.1482 0.882185
## life 0.2172349 0.0080726 26.9102 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 108.53
## Residual Sum of Squares: 31.459
## R-Squared: 0.71012
## Adj. R-Squared: 0.70757
## Chisq: 835.366 on 3 DF, p-value: < 2.22e-16
sel_tbl <- data.frame(
Uji = c("Uji Chow (CEM vs FEM)", "Uji Hausman (REM vs FEM)", "Uji Breusch-Pagan LM (CEM vs REM)"),
Statistik = c(
as.numeric(chow_test$statistic),
as.numeric(hausman_test$statistic),
as.numeric(bplm_test$statistic)
),
P_Value = c(
as.numeric(chow_test$p.value),
as.numeric(hausman_test$p.value),
as.numeric(bplm_test$p.value)
),
Rekomendasi = c(
ifelse(as.numeric(chow_test$p.value) < 0.05, "Pilih FEM", "Pilih CEM"),
ifelse(as.numeric(hausman_test$p.value) < 0.05, "Pilih FEM", "Pilih REM"),
ifelse(as.numeric(bplm_test$p.value) < 0.05, "Pilih REM", "Pilih CEM")
)
)
kable(sel_tbl, digits = 4, caption = "Ringkasan Uji Pemilihan Model Panel Statis") %>%
kable_styling(bootstrap_options = c("striped", "hover"), full_width = FALSE)| Uji | Statistik | P_Value | Rekomendasi |
|---|---|---|---|
| Uji Chow (CEM vs FEM) | 77.0817 | 0.0000 | Pilih FEM |
| Uji Hausman (REM vs FEM) | 1.2605 | 0.7385 | Pilih REM |
| Uji Breusch-Pagan LM (CEM vs REM) | 2051.5213 | 0.0000 | Pilih REM |
best_model <- if (as.numeric(chow_test$p.value) < 0.05) {
if (as.numeric(hausman_test$p.value) < 0.05) fem_mod else rem_mod
} else {
if (as.numeric(bplm_test$p.value) < 0.05) rem_mod else cem_mod
}
best_name <- if (identical(best_model, fem_mod)) {
"Fixed Effect Model (FEM)"
} else if (identical(best_model, rem_mod)) {
"Random Effect Model (REM)"
} else {
"Common Effect Model (CEM)"
}
cat("Model panel statis terpilih otomatis:", best_name, "\n\n")## Model panel statis terpilih otomatis: Random Effect Model (REM)
# 1. Multikolinearitas (VIF)
ols_aux <- lm(form_panel, data = panel_bal)
cat("--- Multikolinearitas (VIF) ---\n")## --- Multikolinearitas (VIF) ---
## edu health life
## 1.057802 1.211220 1.149950
##
## --- Heteroskedastisitas (Breusch-Pagan) ---
##
## studentized Breusch-Pagan test
##
## data: ols_aux
## BP = 20.432, df = 3, p-value = 0.0001381
# 3. Autokorelasi Serial Panel (Breusch-Godfrey & Durbin-Watson)
cat("\n--- Autokorelasi Serial Panel ---\n")##
## --- Autokorelasi Serial Panel ---
##
## Breusch-Godfrey/Wooldridge test for serial correlation in panel models
##
## data: form_panel
## chisq = 197.98, df = 23, p-value < 2.2e-16
## alternative hypothesis: serial correlation in idiosyncratic errors
##
## Durbin-Watson test for serial correlation in panel models
##
## data: form_panel
## DW = 0.56493, p-value < 2.2e-16
## alternative hypothesis: serial correlation in idiosyncratic errors
##
## --- Estimasi Robust (Driscoll-Kraay SE) ---
print(lmtest::coeftest(best_model, vcov. = function(x) plm::vcovSCC(x, type = "HC1", cluster = "group")))##
## t test of coefficients:
##
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -7.0821024 0.5468268 -12.9513 < 2e-16 ***
## edu -0.0528495 0.0313890 -1.6837 0.09316 .
## health -0.0027042 0.0334646 -0.0808 0.93564
## life 0.2172349 0.0067554 32.1574 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1