title: “Tugas Arma”
author: “Ni Kadek Srisuryani 240611010035”
date: “2026-11-18”
output: html_document
library(readxl)
library(dplyr)
library(tidyr)
library(stringr)
library(zoo)
library(tseries)
library(forecast)
library(ggplot2)
library(knitr)
file_path <- "C:/Users/acer/OneDrive/Dokumen/Data indonesia pacific sri 1.xlsx"
raw_df <- read_excel(file_path, sheet = 1, col_types = "text")
country_col <- which(sapply(raw_df, function(col) any(grepl("Malaysia", col, ignore.case = TRUE))))[1]
if (is.na(country_col)) country_col <- 1
var_col <- country_col + 1
data_start_col <- var_col + 1
country_vec <- trimws(as.character(raw_df[[country_col]]))
country_vec[country_vec %in% c("", "NA", "NaN", "..", "-")] <- NA
country_vec <- na.locf(country_vec, na.rm = FALSE)
malaysia_rows <- which(grepl("Malaysia", country_vec, ignore.case = TRUE))
malaysia_sub <- raw_df[malaysia_rows, var_col:ncol(raw_df), drop = FALSE]
colnames(malaysia_sub)[1] <- "Variable"
malaysia_long <- malaysia_sub %>%
mutate(
Country = "Malaysia",
Variable = trimws(as.character(Variable))
) %>%
filter(!is.na(Variable) & Variable != "") %>%
pivot_longer(
cols = -c(Country, Variable),
names_to = "Period",
values_to = "Raw_Value"
) %>%
mutate(
Clean_Value = str_trim(str_remove_all(as.character(Raw_Value), "%|,")),
Value = suppressWarnings(as.numeric(Clean_Value))
)
kable(
data.frame(Available_Indicators = unique(malaysia_long$Variable)),
caption = "Available Indicators for Malaysia"
)
| Available_Indicators |
|---|
| Government expenditure on education, total (% of GDP) |
| Current health expenditure (% of GDP) |
| Life expectancy at birth, total (years) |
| GDP per capita (current US$) |
selected_variable <- "Government expenditure on education, total (% of GDP)"
df_var <- malaysia_long %>%
filter(grepl(selected_variable, Variable, fixed = TRUE)) %>%
mutate(Time_Index = row_number()) %>%
arrange(Time_Index)
if (nrow(df_var) == 0) {
stop("Selected variable not found. Check 'Available_Indicators' table above.")
}
ts_clean <- na.interp(df_var$Value)
ts_mal <- ts(ts_clean, start = 2000, frequency = 1)
autoplot(ts_mal) +
ggtitle(paste("Malaysia Time Series:", selected_variable)) +
xlab("Year") +
ylab("Value") +
theme_minimal()
adf_initial <- tryCatch(
adf.test(na.omit(ts_mal)),
error = function(e) list(statistic = NA, p.value = 1, method = "ADF Test Failed (Series too short)")
)
print(adf_initial)
##
## Augmented Dickey-Fuller Test
##
## data: na.omit(ts_mal)
## Dickey-Fuller = -4.0869, Lag order = 2, p-value = 0.02022
## alternative hypothesis: stationary
d_order <- ifelse(!is.na(adf_initial$p.value) && adf_initial$p.value < 0.05, 0, 1)
if (d_order == 1) {
ts_stat <- diff(na.omit(ts_mal), differences = 1)
adf_diff <- tryCatch(
adf.test(ts_stat),
error = function(e) list(statistic = NA, p.value = NA, method = "ADF Test on Differenced Series")
)
print(adf_diff)
} else {
ts_stat <- na.omit(ts_mal)
}
max_lag <- max(1, floor(length(ts_stat) / 2) - 1)
par(mfrow = c(1, 2))
acf(ts_stat, lag.max = max_lag, main = "ACF Plot (MA Order / q)")
pacf(ts_stat, lag.max = max_lag, main = "PACF Plot (AR Order / p)")
par(mfrow = c(1, 1))
fit_safe_arima <- function(series, ord) {
tryCatch(
Arima(series, order = ord, method = "ML"),
error = function(e) Arima(series, order = ord, method = "CSS")
)
}
model_ar1 <- fit_safe_arima(ts_stat, c(1, 0, 0))
model_ma1 <- fit_safe_arima(ts_stat, c(0, 0, 1))
model_arma11 <- fit_safe_arima(ts_stat, c(1, 0, 1))
model_arima <- fit_safe_arima(ts_mal, c(1, d_order, 1))
model_auto <- auto.arima(ts_mal, trace = TRUE, stepwise = FALSE, approximation = FALSE)
##
## ARIMA(0,1,0) : 50.79021
## ARIMA(0,1,0) with drift : 51.65255
## ARIMA(0,1,1) : 52.81049
## ARIMA(0,1,1) with drift : 53.31573
## ARIMA(0,1,2) : 51.22729
## ARIMA(0,1,2) with drift : 53.33167
## ARIMA(0,1,3) : 53.11108
## ARIMA(0,1,3) with drift : 55.98783
## ARIMA(0,1,4) : Inf
## ARIMA(0,1,4) with drift : Inf
## ARIMA(0,1,5) : Inf
## ARIMA(0,1,5) with drift : Inf
## ARIMA(1,1,0) : 52.59873
## ARIMA(1,1,0) with drift : 52.9019
## ARIMA(1,1,1) : 54.09104
## ARIMA(1,1,1) with drift : 54.99
## ARIMA(1,1,2) : 53.60099
## ARIMA(1,1,2) with drift : 56.35909
## ARIMA(1,1,3) : 56.33507
## ARIMA(1,1,3) with drift : 59.56984
## ARIMA(1,1,4) : 58.43405
## ARIMA(1,1,4) with drift : Inf
## ARIMA(2,1,0) : 53.23692
## ARIMA(2,1,0) with drift : 54.76826
## ARIMA(2,1,1) : 56.14061
## ARIMA(2,1,1) with drift : 57.98996
## ARIMA(2,1,2) : Inf
## ARIMA(2,1,2) with drift : Inf
## ARIMA(2,1,3) : Inf
## ARIMA(2,1,3) with drift : Inf
## ARIMA(3,1,0) : 56.13834
## ARIMA(3,1,0) with drift : 57.97792
## ARIMA(3,1,1) : 58.41177
## ARIMA(3,1,1) with drift : Inf
## ARIMA(3,1,2) : Inf
## ARIMA(3,1,2) with drift : Inf
## ARIMA(4,1,0) : 58.51516
## ARIMA(4,1,0) with drift : 60.4761
## ARIMA(4,1,1) : 59.95264
## ARIMA(4,1,1) with drift : Inf
## ARIMA(5,1,0) : 57.15053
## ARIMA(5,1,0) with drift : 57.82799
##
##
##
## Best model: ARIMA(0,1,0)
model_ets <- ets(ts_mal)
summary(model_ar1)
## Series: series
## ARIMA(1,0,0) with non-zero mean
##
## Coefficients:
## ar1 mean
## 0.8918 5.1961
## s.e. 0.0963 0.9467
##
## sigma^2 = 0.4657: log likelihood = -25.67
## AIC=57.34 AICc=58.49 BIC=61
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE
## Training set -0.1317415 0.6545734 0.4892661 -4.012698 9.716177 1.100454
## ACF1
## Training set -0.1590255
summary(model_ma1)
## Series: series
## ARIMA(0,0,1) with non-zero mean
##
## Coefficients:
## ma1 mean
## 0.5708 5.0140
## s.e. 0.1170 0.2856
##
## sigma^2 = 0.9238: log likelihood = -33.64
## AIC=73.27 AICc=74.42 BIC=76.93
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE
## Training set -0.02930144 0.9218805 0.7250667 -4.401672 14.73135 1.630815
## ACF1
## Training set 0.305952
summary(model_arma11)
## Series: series
## ARIMA(1,0,1) with non-zero mean
##
## Coefficients:
## ar1 ma1 mean
## 0.9074 -0.0524 5.2188
## s.e. 0.1002 0.1734 1.0128
##
## sigma^2 = 0.4841: log likelihood = -25.63
## AIC=59.25 AICc=61.25 BIC=64.13
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE
## Training set -0.1413718 0.6526987 0.4912079 -4.174671 9.767698 1.104822
## ACF1
## Training set -0.1107895
summary(model_arima)
## Series: series
## ARIMA(1,0,1) with non-zero mean
##
## Coefficients:
## ar1 ma1 mean
## 0.9074 -0.0524 5.2188
## s.e. 0.1002 0.1734 1.0128
##
## sigma^2 = 0.4841: log likelihood = -25.63
## AIC=59.25 AICc=61.25 BIC=64.13
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE
## Training set -0.1413718 0.6526987 0.4912079 -4.174671 9.767698 1.104822
## ACF1
## Training set -0.1107895
comparison_table <- data.frame(
Model = c(
"AR(1)",
"MA(1)",
"ARMA(1,1)",
paste0("ARIMA(1,", d_order, ",1)"),
"Auto-ARIMA",
"ETS"
),
AIC = c(
AIC(model_ar1),
AIC(model_ma1),
AIC(model_arma11),
AIC(model_arima),
AIC(model_auto),
AIC(model_ets)
),
BIC = c(
BIC(model_ar1),
BIC(model_ma1),
BIC(model_arma11),
BIC(model_arima),
BIC(model_auto),
BIC(model_ets)
)
)
kable(comparison_table, digits = 4, caption = "Model Comparison Based on AIC and BIC")
| Model | AIC | BIC |
|---|---|---|
| AR(1) | 57.3443 | 61.0010 |
| MA(1) | 73.2741 | 76.9308 |
| ARMA(1,1) | 59.2539 | 64.1294 |
| ARIMA(1,0,1) | 59.2539 | 64.1294 |
| Auto-ARIMA | 50.6084 | 51.7864 |
| ETS | 64.7432 | 68.3999 |
summary(model_auto)
## Series: ts_mal
## ARIMA(0,1,0)
##
## sigma^2 = 0.4437: log likelihood = -24.3
## AIC=50.61 AICc=50.79 BIC=51.79
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE
## Training set -0.158487 0.6526775 0.4271191 -3.796766 8.481882 0.9606734
## ACF1
## Training set -0.2326272
checkresiduals(model_auto)
##
## Ljung-Box test
##
## data: Residuals from ARIMA(0,1,0)
## Q* = 8.1477, df = 5, p-value = 0.1483
##
## Model df: 0. Total lags used: 5
forecast_5_periods <- forecast(model_auto, h = 5)
kable(as.data.frame(forecast_5_periods), digits = 4, caption = "5-Period Ahead Forecast Results")
| Point Forecast | Lo 80 | Hi 80 | Lo 95 | Hi 95 | |
|---|---|---|---|---|---|
| 2025 | 3.5148 | 2.6611 | 4.3685 | 2.2092 | 4.8204 |
| 2026 | 3.5148 | 2.3075 | 4.7221 | 1.6684 | 5.3612 |
| 2027 | 3.5148 | 2.0362 | 4.9934 | 1.2534 | 5.7762 |
| 2028 | 3.5148 | 1.8074 | 5.2222 | 0.9036 | 6.1260 |
| 2029 | 3.5148 | 1.6059 | 5.4237 | 0.5954 | 6.4342 |
autoplot(forecast_5_periods) +
ggtitle(paste("5-Period Projection - Malaysia:", selected_variable)) +
xlab("Year") +
ylab("Value") +
theme_minimal()