Penerapan Metode ARIMA dalam Peramalan NTP di Indonesia Periode 2020-2025
DOI:
https://doi.org/10.29313/bcss.v6i1.23699Keywords:
Nilai Tukar Petani, ARIMA, PeramalanAbstract
Abstract. The Farmer’s Terms of Trade (FTT) is an important indicator for assessing the welfare level of farmers in Indonesia. Movements in the FTT, influenced by national and global economic dynamics, exhibit fluctuating patterns as well as long-term trends, requiring a forecasting method capable of capturing these characteristics statistically. This study aims to apply the Autoregressive Integrated Moving Average (ARIMA) method to model and forecast Indonesia’s Farmer’s Terms of Trade for the period 2020–2025. The data used consist of monthly FTT data obtained from Statistics Indonesia (BPS). The analysis follows the Box–Jenkins approach, including model identification, parameter estimation, and residual diagnostic testing. The results indicate that the FTT data are non-stationary in the mean and require first-order differencing to achieve stationarity. Based on the analysis of the Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF), several candidate ARIMA models were identified, with the best model selected based on parameter significance and the fulfilment of the white noise assumption in the residuals. The selected ARIMA model provides reasonably accurate forecasting results. Therefore, the ARIMA method can serve as an effective approach for forecasting FTT movements and may support policy considerations in the agricultural sector.
Abstrak. Nilai Tukar Petani (NTP) merupakan indikator penting untuk menilai tingkat kesejahteraan petani di Indonesia. Pergerakan NTP yang dipengaruhi oleh dinamika ekonomi nasional dan global menunjukkan pola fluktuatif serta tren jangka panjang, sehingga memerlukan metode peramalan yang mampu menangkap karakteristik tersebut secara statistik. Penelitian ini bertujuan untuk menerapkan metode Autoregressive Integrated Moving Average (ARIMA) dalam memodelkan dan meramalkan Nilai Tukar Petani (NTP) di Indonesia periode 2020–2025. Data yang digunakan berupa data bulanan NTP yang diperoleh dari Badan Pusat Statistik (BPS). Metode analisis mengikuti tahapan pendekatan Box–Jenkins, meliputi identifikasi model, estimasi parameter, serta pengujian diagnostik residual. Hasil analisis menunjukkan bahwa data NTP bersifat tidak stasioner pada rata-rata dan memerlukan proses differencing satu kali. Berdasarkan analisis Autocorrelation Function (ACF) dan Partial Autocorrelation Function (PACF), diperoleh beberapa kandidat model ARIMA, dengan model terbaik dipilih berdasarkan signifikansi parameter dan pemenuhan asumsi white noise pada residual. Model ARIMA terpilih mampu memberikan hasil peramalan yang cukup akurat. Dengan demikian, metode ARIMA dapat digunakan sebagai pendekatan yang efektif dalam meramalkan pergerakan NTP serta berpotensi menjadi dasar pertimbangan kebijakan di sektor pertanian.
References
Badan Pusat Statistik. (2025). BADAN PUSAT STATISTIK BPS-STATISTICS INDONESIA.
Bernardino, M. (2023). Penerapan CUSUM-Tukey’s Control Chart untuk Mendeteksi Perubahan Rata-Rata Proses pada Data Non-Normal. Jurnal Riset Statistika, 3(2), 119–124. https://doi.org/10.29313/jrs.v3i2.2955
Box, G. E. P., & Jenkins, G. M. (1976). Peramalan dan Metode Box-Jenkins (ARIMA) EKONOMETRIK A.
Khalis Syahril Suryana, Syahla Anisah, & Aceng Komarudin Mutaqin. (2024). Uji Dua Rata-Rata Waktu Belajar Mandiri Antara Mahasiswa Laki-Laki dan Perempuan. Jurnal Riset Statistika, 103–110. https://doi.org/10.29313/jrs.v4i2.5002
BPS Prov Sulawesi Barat. (2021). NILAI TUKAR PETANI.
Oktoriandi, D. (2022). Penerapan uji Q Cochran terhadap Atribut Produk Laptop Menggunakan Multiple Response Analysis (MRA). Jurnal Riset Statistika, 1(2), 127–134. https://doi.org/10.29313/jrs.v1i2.521
Makridakis, Spyros G. Wheelwright, & Rob J Hyndman. (2020). Forecasting Methodsfor Management 3rd Edition.
Montgomery, D. C., Jennings, C. L., & Kulahci, M. (2015). Wiley Series in Probability and Statistics.
Rob J Hyndman. (2018). Forecasting: Principles & Practice.
Risnandar, A., & Achmad, A. I. (2023). Pemodelan Generalized Space Time Autoregressive untuk Meramalkan Indeks Harga Konsumen. Jurnal Riset Statistika, 43–50. https://doi.org/10.29313/jrs.v3i1.1792
SAS/ETS ® 14.3 User’s Guide The ARIMA Procedure. (2017). http://support.sas.com/thirdpartylicenses.
Sofia Yanti, T., Nur Azizah Komara Rifai, Ms., Marizsa Herlina, Ms., & Agustin Nuriani Sirodj, D. (n.d.). Modul Praktikum Modul Praktikum Analisis Data II.
Ugoh, C. I., Echebiri, U. V., Temisan, G. O., Iwuchukwu, J. K., & Guobadia, E. K. (2022). On Forecasting Nigeria’s GDP: A Comparative Performance of Regression with ARIMA Errors and ARIMA Method. In International Journal of Mathematics and Statistics Studies (Vol. 10, Number 4). https://www.eajournals.org/
