Perbandingan Model ARIMA-GARCH dan ARIMAX-GARCH dalam Peramalan Volatilitas Return Harga Crude Palm Oil dengan Return Soybean Oil Sebagai Variabel Eksogen

Authors

DOI:

https://doi.org/10.30605/proximal.v9i4.9963

Keywords:

ARIMA-GARCH, ARIMAX-GARCH, Crude Palm Oil, Peramalan Volatilitas

Abstract

Indonesia merupakan produsen dan eksportir crude palm oil (CPO) terbesar di dunia, sehingga fluktuasi harga CPO memiliki implikasi penting terhadap perekonomian nasional dan pemodelan volatilitas return-nya diperlukan untuk memperoleh estimasi risiko yang akurat. Penelitian ini bertujuan membandingkan kinerja model ARIMA-GARCH dan ARIMAX-GARCH dalam meramalkan volatilitas return CPO, dengan return soybean oil pada bulan yang sama sebagai variabel eksogen dalam persamaan rata-rata ARIMAX. Data berupa harga bulanan CPO dan soybean oil dari World Bank periode Januari 1990–Desember 2025 sebanyak 432 observasi, terdiri atas 408 observasi in-sample dan 24 observasi out-of-sample. Pendekatan subset ARIMA menghasilkan ARIMA([2,3],0,[1,2]) dan ARIMAX([2],0,[1,2,3]). Uji ARCH-LM menunjukkan adanya efek ARCH pada residual ARIMA, sedangkan pada residual ARIMAX efek ARCH signifikan pada lag 2, 3, dan 12. Kedua spesifikasi menggunakan GARCH(1,1) dengan distribusi Student-t, dengan persistensi volatilitas masing-masing sebesar 0,9138 dan 0,9614. Peramalan satu langkah ke depan secara rolling dievaluasi menggunakan QLIKE dan RMSE pada skala varians  terhadap proksi varians aktual. ARIMA-GARCH menghasilkan QLIKE 1,5834 dan RMSE 36,4594 , sedangkan ARIMAX-GARCH menghasilkan QLIKE 1,5965 dan RMSE 36,9927 . Uji Diebold-Mariano dengan koreksi Harvey-Leybourne-Newbold (HLN) menunjukkan tidak terdapat perbedaan akurasi peramalan yang signifikan secara statistik (statistik −0,3155; p-value 0,7553). Dengan demikian, penambahan return soybean oil pada persamaan rata-rata belum meningkatkan akurasi peramalan volatilitas CPO. ARIMA-GARCH direkomendasikan karena lebih parsimonis dengan kinerja peramalan yang tidak berbeda signifikan secara statistik.

References

Al Haris, M., Prizka, D., & Arum, R. (2020). Peramalan harga emas dengan model generalized autoregressive conditional heteroscedasticity (GARCH). Jurnal Saintika Unpam: Jurnal Sains dan Matematika Unpam, 3(1), 19–30. https://doi.org/10.32493/JSMU.V3I1.5263

Ardiansyah, M. (2002). Impact of the 1997–1998 Asian financial crisis on the Indonesian and Malaysian palm oil and palm kernel oil industries [Doctoral dissertation, Oklahoma State University].

Ashaari, A., Abdullah, M., & Fuzi, N. M. (2022). Malaysian palm oil industry performance during epidemic Covid 19. International Journal of Academic Research in Business and Social Sciences, 12(1), 622–628. https://doi.org/10.6007/IJARBSS/V12-I1/12058

Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3), 307–327. https://doi.org/10.1016/0304-4076(86)90063-1

Box, G. E. P., & Jenkins, G. M. (1976). Time series analysis: Forecasting and control. Holden-Day.

Catria, E., Putra, A. A., Permana, D., & Fitria, D. (2023). Adding exogenous variable in forming ARIMAX model to predict export load goods in Tanjung Priok port. UNP Journal of Statistics and Data Science, 1(1), 31–38. https://doi.org/10.24036/UJSDS/VOL1-ISS1/10

Dinda, M., Yulianto, M., & Utomo, A. P. (2026). Peramalan harga minyak goreng sawit di Indonesia: Perbandingan model ARIMAX-GARCH, SVR, dan LSTM. JUSTIN (Jurnal Sistem dan Teknologi Informasi), 14(2), 205–216. https://doi.org/10.26418/JUSTIN.V14I2.97766

Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica, 50(4), 987–1007. https://doi.org/10.2307/1912773

Fousekis, P. (2023). Quantile coherency of futures prices in palm and soybean oil markets. Journal of Economics and Finance, 48(1), 129–141. https://doi.org/10.1007/S12197-023-09647-6

Go, Y. H., & Lau, W. Y. (2021). Extreme risk spillovers between crude palm oil prices and exchange rates. The North American Journal of Economics and Finance, 58, Article 101513. https://doi.org/10.1016/J.NAJEF.2021.101513

Go, Y. H., & Lau, W. Y. (2024). Terms of trade or market power? Further evidence from dynamic spillovers in return and volatility between Malaysian crude palm oil and foreign exchange markets. The North American Journal of Economics and Finance, 73, Article 102178. https://doi.org/10.1016/J.NAJEF.2024.102178

Kilani, L. O., Yahaya, A., Tasi’u, M., Tasi’u, M., Aliyu, Y., & David, R. O. D. R. O. (2025). An assessment on the predictive performance of ARIMA-GARCH and ARIMAX-GARCH models on Nigerian inflation rate. International Journal of Science for Global Sustainability, 11(3), 266–274. https://doi.org/10.57233/ijsgs.v11i3.941

Nathan, T. M., Senadjki, A., & Au Yong, H. N. (2023). The determinant of local palm oil price in Malaysia: Does the Covid-19 pandemic matter? In Proceedings of the 10th International Conference on Business, Accounting, Finance and Economics (BAFE 2022) (pp. 333–347). Atlantis Press. https://doi.org/10.2991/978-2-494069-99-2_26

Putri, R. A., Notodiputro, K. A., & Susetyo, B. (2026). Comparative study of hybrid ARIMA-LSTM and CNN-LSTM for palm oil price forecasting. ZERO: Jurnal Sains, Matematika dan Terapan, 10(1), 69–79. https://doi.org/10.30829/ZERO.V10I1.27631

Sanusi, W., Syam, R., & Sari, Y. (2025). Analysis of the generalized autoregressive conditional heteroskedasticity (GARCH) model in forecasting Antam gold prices in Indonesia. Journal of Mathematics, Computations and Statistics, 8(1), 49–58. https://doi.org/10.35580/JMATHCOS.V8I1.6760

Tee, L.-T., Kew, S.-R., Janor, H., & Rahim, R. A. (2020). Do world crude oil prices, global uncertainty and exchange rates influence palm oil prices? Evidence from the nonlinear ARDL approach. Institutions and Economies, 12(3), 1–18. https://ejournal.um.edu.my/index.php/ijie/article/view/25379

Voora, V., Larrea, C., Bermudez, S., & Balino, S. (2020). Global market report: Palm oil (Sustainable Commodities Marketplace Series 2019). International Institute for Sustainable Development.

Zaidi, M. A. S., Karim, Z. A., & Zaidon, N. A. (2022). External and internal shocks and the movement of palm oil price: SVAR evidence from Malaysia. Economies, 10(1), Article 7. https://doi.org/10.3390/ECONOMIES10010007

Zhang, R., et al. (2021). Comparison of ARIMA and LSTM in forecasting the incidence of HFMD combined and uncombined with exogenous meteorological variables in Ningbo, China. International Journal of Environmental Research and Public Health, 18(11), Article 6174. https://doi.org/10.3390/IJERPH18116174

Downloads

Published

2026-11-21

How to Cite

Perbandingan Model ARIMA-GARCH dan ARIMAX-GARCH dalam Peramalan Volatilitas Return Harga Crude Palm Oil dengan Return Soybean Oil Sebagai Variabel Eksogen. (2026). Proximal: Jurnal Penelitian Matematika Dan Pendidikan Matematika, 9(4), 1051-1069. https://doi.org/10.30605/proximal.v9i4.9963