1. Memuat Paket dan Data China
library(dplyr)
library(tidyr)
library(forecast)
library(ggplot2)
library(knitr)
file_path <- "P_Data_Extract_From_World_Development_Indicators.xlsx"
if (file.exists(file_path) && requireNamespace("readxl", quietly = TRUE)) {
raw_df <- readxl::read_excel(file_path, sheet = "Data")
china_long <- raw_df %>%
filter(`Country Name` == "China") %>%
pivot_longer(
cols = matches("\\[YR\\d{4}\\]"),
names_to = "Kolom_Tahun",
values_to = "Nilai_Raw"
) %>%
mutate(
Tahun = as.integer(gsub(".*\\[YR(\\d{4})\\]", "\\1", Kolom_Tahun)),
Nilai = suppressWarnings(as.numeric(Nilai_Raw))
) %>%
select(`Series Code`, `Series Name`, Tahun, Nilai) %>%
arrange(`Series Code`, Tahun)
} else {
tahun_vec <- 2000:2024
china_long <- bind_rows(
data.frame(
`Series Code` = "NE.GDI.FTOT.ZS",
`Series Name` = "Gross fixed capital formation (% of GDP)",
Tahun = tahun_vec,
Nilai = c(32.647179, 33.459882, 34.987864, 38.084681, 39.350537, 39.270329, 38.521573,
37.670987, 38.803081, 43.409767, 43.520182, 43.515391, 43.873708, 44.075543,
43.380347, 41.616671, 41.080580, 41.418490, 42.380376, 42.250349, 41.849411,
41.352120, 41.232932, 40.454435, 39.651933),
check.names = FALSE
),
data.frame(
`Series Code` = "SL.AGR.EMPL.ZS",
`Series Name` = "Employment in agriculture (% of total employment) (modeled ILO estimate)",
Tahun = tahun_vec,
Nilai = c(50.039561, 50.000008, 49.999993, 49.099489, 46.900252, 44.800196, 42.600488,
40.800044, 39.600071, 38.099885, 36.700610, 34.799791, 33.600592, 31.400286,
29.500473, 28.300472, 27.422125, 26.683583, 25.751495, 24.721990, 23.599860,
22.868778, 24.080109, 22.800877, 22.216498),
check.names = FALSE
),
data.frame(
`Series Code` = "FR.INR.DPST",
`Series Name` = "Deposit interest rate (%)",
Tahun = tahun_vec,
Nilai = c(2.25, 2.25, 1.98, 1.98, 2.25, 2.25, 2.52,
4.14, 2.25, 2.25, 2.75, 3.50, 3.00, 3.00,
2.75, 1.50, 1.50, 1.50, 1.50, 1.50, 1.50,
1.50, 1.50, 1.50, 1.50),
check.names = FALSE
),
data.frame(
`Series Code` = "NY.GDP.TOTL.RT.ZS",
`Series Name` = "Total natural resources rents (% of GDP)",
Tahun = tahun_vec,
Nilai = c(2.697740, 2.592377, 1.956296, 2.017907, 4.724876, 5.102773, 5.521198,
6.327879, 9.648414, 3.917821, 6.286726, 7.685203, 4.088493, 2.983072,
2.310135, 1.174767, 1.052474, 1.314238, 1.425184, 1.266914, 0.863775,
1.707565, NA, NA, NA),
check.names = FALSE
)
)
}
ringkasan_china <- china_long %>%
filter(!is.na(Nilai)) %>%
group_by(`Series Code`, `Series Name`) %>%
summarise(
N = n(),
Tahun_Mulai = min(Tahun),
Tahun_Akhir = max(Tahun),
Rata_Rata = round(mean(Nilai), 4),
Median = round(median(Nilai), 4),
Std_Dev = round(sd(Nilai), 4),
Min = round(min(Nilai), 4),
Max = round(max(Nilai), 4),
.groups = "drop"
)
kable(ringkasan_china, caption = "Ringkasan Statistik Data China")
Ringkasan Statistik Data China
| FR.INR.DPST |
Deposit interest rate (%) |
25 |
2000 |
2024 |
2.1648 |
2.2500 |
0.7194 |
1.5000 |
4.1400 |
| NE.GDI.FTOT.ZS |
Gross fixed capital formation (% of GDP) |
25 |
2000 |
2024 |
40.3143 |
41.2329 |
3.1371 |
32.6472 |
44.0755 |
| NY.GDP.TOTL.RT.ZS |
Total natural resources rents (% of GDP) |
22 |
2000 |
2021 |
3.4848 |
2.6451 |
2.4212 |
0.8638 |
9.6484 |
| SL.AGR.EMPL.ZS |
Employment in agriculture (% of total employment)
(modeled ILO estimate) |
25 |
2000 |
2024 |
34.6555 |
33.6006 |
9.8978 |
22.2165 |
50.0396 |
2. Visualisasi Indikator China
china_long %>%
filter(!is.na(Nilai)) %>%
ggplot(aes(x = Tahun, y = Nilai)) +
geom_line(color = "#1f77b4", linewidth = 1) +
geom_point(color = "#1f77b4", size = 1.8) +
facet_wrap(~ `Series Name`, scales = "free_y", ncol = 2) +
labs(
title = "Indikator Deret Waktu China (2000–2024)",
x = "Tahun",
y = "Nilai"
) +
theme_minimal()

3. Stasioneritas & Pembagian Data Train/Test
target_code <- "NE.GDI.FTOT.ZS"
df_sub <- china_long %>%
filter(`Series Code` == target_code, !is.na(Nilai))
nama_indikator <- unique(df_sub$`Series Name`)
ts_china <- ts(df_sub$Nilai, start = min(df_sub$Tahun), frequency = 1)
cat("Indikator terpilih :", nama_indikator, "\n")
## Indikator terpilih : Gross fixed capital formation (% of GDP)
cat("Jumlah differencing disarankan (d) :", ndiffs(ts_china), "\n")
## Jumlah differencing disarankan (d) : 1
cat("Ljung-Box p-value (lag 5) :", round(Box.test(ts_china, lag = 5, type = "Ljung-Box")$p.value, 4), "\n")
## Ljung-Box p-value (lag 5) : 0
par(mfrow = c(1, 2))
acf(ts_china, main = "ACF (Data Level)")
pacf(ts_china, main = "PACF (Data Level)")

par(mfrow = c(1, 1))
n_obs <- length(ts_china)
n_train <- floor(0.8 * n_obs)
n_test <- n_obs - n_train
train_ts <- window(ts_china, end = time(ts_china)[n_train])
test_ts <- window(ts_china, start = time(ts_china)[n_train + 1])
4. Pemodelan AR, MA, ARMA, dan Model Lainnya
mod_ar <- Arima(train_ts, order = c(1, 0, 0))
mod_ma <- Arima(train_ts, order = c(0, 0, 1))
mod_arma <- Arima(train_ts, order = c(1, 0, 1))
mod_arima <- Arima(train_ts, order = c(1, 1, 1))
mod_auto <- auto.arima(train_ts, seasonal = FALSE)
mod_holt <- holt(train_ts, h = n_test)
mod_ets <- ets(train_ts)
fc_ar <- forecast(mod_ar, h = n_test)
fc_ma <- forecast(mod_ma, h = n_test)
fc_arma <- forecast(mod_arma, h = n_test)
fc_arima <- forecast(mod_arima, h = n_test)
fc_auto <- forecast(mod_auto, h = n_test)
fc_ets <- forecast(mod_ets, h = n_test)
summary(mod_ar)
## Series: train_ts
## ARIMA(1,0,0) with non-zero mean
##
## Coefficients:
## ar1 mean
## 0.9380 38.5304
## s.e. 0.0674 3.4696
##
## sigma^2 = 2.463: log likelihood = -37.4
## AIC=80.8 AICc=82.3 BIC=83.79
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE ACF1
## Training set 0.4680784 1.488971 1.046264 1.094838 2.651876 1.03419 0.2446508
summary(mod_ma)
## Series: train_ts
## ARIMA(0,0,1) with non-zero mean
##
## Coefficients:
## ma1 mean
## 0.8553 40.0079
## s.e. 0.1283 0.8612
##
## sigma^2 = 5.005: log likelihood = -44.09
## AIC=94.17 AICc=95.67 BIC=97.16
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE ACF1
## Training set 0.13061 2.122352 1.605593 -0.1156417 4.15102 1.587064 0.4156517
summary(mod_arma)
## Series: train_ts
## ARIMA(1,0,1) with non-zero mean
##
## Coefficients:
## ar1 ma1 mean
## 0.8831 0.5011 38.8322
## s.e. 0.1086 0.1873 2.9071
##
## sigma^2 = 2.021: log likelihood = -35.06
## AIC=78.11 AICc=80.78 BIC=82.09
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE
## Training set 0.3166194 1.310568 0.9428653 0.7212279 2.365605 0.931984
## ACF1
## Training set -0.09318985
5. Evaluasi Model & Grafik Prediksi
tabel_metrik <- bind_rows(
data.frame(
Model = "AR(1)",
AIC = round(AIC(mod_ar), 2),
RMSE = round(accuracy(fc_ar, test_ts)["Test set", "RMSE"], 4),
MAE = round(accuracy(fc_ar, test_ts)["Test set", "MAE"], 4),
MAPE = round(accuracy(fc_ar, test_ts)["Test set", "MAPE"], 4)
),
data.frame(
Model = "MA(1)",
AIC = round(AIC(mod_ma), 2),
RMSE = round(accuracy(fc_ma, test_ts)["Test set", "RMSE"], 4),
MAE = round(accuracy(fc_ma, test_ts)["Test set", "MAE"], 4),
MAPE = round(accuracy(fc_ma, test_ts)["Test set", "MAPE"], 4)
),
data.frame(
Model = "ARMA(1,1)",
AIC = round(AIC(mod_arma), 2),
RMSE = round(accuracy(fc_arma, test_ts)["Test set", "RMSE"], 4),
MAE = round(accuracy(fc_arma, test_ts)["Test set", "MAE"], 4),
MAPE = round(accuracy(fc_arma, test_ts)["Test set", "MAPE"], 4)
),
data.frame(
Model = "ARIMA(1,1,1)",
AIC = round(AIC(mod_arima), 2),
RMSE = round(accuracy(fc_arima, test_ts)["Test set", "RMSE"], 4),
MAE = round(accuracy(fc_arima, test_ts)["Test set", "MAE"], 4),
MAPE = round(accuracy(fc_arima, test_ts)["Test set", "MAPE"], 4)
),
data.frame(
Model = "Auto ARIMA",
AIC = round(AIC(mod_auto), 2),
RMSE = round(accuracy(fc_auto, test_ts)["Test set", "RMSE"], 4),
MAE = round(accuracy(fc_auto, test_ts)["Test set", "MAE"], 4),
MAPE = round(accuracy(fc_auto, test_ts)["Test set", "MAPE"], 4)
),
data.frame(
Model = "Holt's Trend",
AIC = round(AIC(mod_holt$model), 2),
RMSE = round(accuracy(mod_holt, test_ts)["Test set", "RMSE"], 4),
MAE = round(accuracy(mod_holt, test_ts)["Test set", "MAE"], 4),
MAPE = round(accuracy(mod_holt, test_ts)["Test set", "MAPE"], 4)
),
data.frame(
Model = "ETS",
AIC = round(AIC(mod_ets), 2),
RMSE = round(accuracy(fc_ets, test_ts)["Test set", "RMSE"], 4),
MAE = round(accuracy(fc_ets, test_ts)["Test set", "MAE"], 4),
MAPE = round(accuracy(fc_ets, test_ts)["Test set", "MAPE"], 4)
)
)
kable(tabel_metrik, caption = paste("Evaluasi Model pada Data Test —", nama_indikator))
Evaluasi Model pada Data Test — Gross fixed capital formation
(% of GDP)
| AR(1) |
80.80 |
0.8688 |
0.7046 |
1.7464 |
| MA(1) |
94.17 |
0.9463 |
0.8581 |
2.0836 |
| ARMA(1,1) |
78.11 |
0.4621 |
0.3234 |
0.8052 |
| ARIMA(1,1,1) |
71.27 |
1.3337 |
1.0915 |
2.7049 |
| Auto ARIMA |
69.30 |
1.3396 |
1.0955 |
2.7147 |
| Holt’s Trend |
83.24 |
3.2687 |
2.9089 |
7.1820 |
| ETS |
81.27 |
1.5479 |
1.3422 |
3.3181 |
thn_test <- as.numeric(time(test_ts))
df_plot <- bind_rows(
data.frame(Tahun = as.numeric(time(ts_china)), Nilai = as.numeric(ts_china), Model = "Aktual"),
data.frame(Tahun = thn_test, Nilai = as.numeric(fc_ar$mean), Model = "AR(1)"),
data.frame(Tahun = thn_test, Nilai = as.numeric(fc_ma$mean), Model = "MA(1)"),
data.frame(Tahun = thn_test, Nilai = as.numeric(fc_arma$mean), Model = "ARMA(1,1)"),
data.frame(Tahun = thn_test, Nilai = as.numeric(fc_arima$mean), Model = "ARIMA(1,1,1)"),
data.frame(Tahun = thn_test, Nilai = as.numeric(fc_auto$mean), Model = "Auto ARIMA"),
data.frame(Tahun = thn_test, Nilai = as.numeric(mod_holt$mean), Model = "Holt's Trend")
)
ggplot(df_plot, aes(x = Tahun, y = Nilai, color = Model, linetype = Model)) +
geom_line(linewidth = 0.9) +
geom_point(size = 2) +
labs(
title = paste("Perbandingan Prediksi Model —", nama_indikator),
subtitle = "China (Data Test)",
x = "Tahun",
y = "Nilai"
) +
theme_minimal()

fit_full <- Arima(ts_china, order = c(1, 0, 1))
fc_full <- forecast(fit_full, h = 5)
print(fc_full)
## Point Forecast Lo 80 Hi 80 Lo 95 Hi 95
## 2025 39.38956 37.77558 41.00354 36.92119 41.85792
## 2026 39.29540 36.53417 42.05663 35.07246 43.51834
## 2027 39.21172 35.80749 42.61596 34.00539 44.41806
## 2028 39.13736 35.30069 42.97402 33.26968 45.00503
## 2029 39.07127 34.92482 43.21772 32.72982 45.41272
autoplot(fc_full) +
labs(
title = paste("Forecast 5 Tahun ke Depan (ARMA(1,1)) —", nama_indikator),
x = "Tahun",
y = "Nilai"
) +
theme_minimal()
