Linearized Ridge Regression Modeling with MM-Estimator in Statistical Downscalling for Rainfall Forecasting

SISWANTO SISWANTO; M. Zaky Hisyam Gozhi; Muh. Ikbal Taufik; Anisa Kalondeng; Sitti Sahriman

doi:10.20956/j.v21i3.43203

Authors

SISWANTO SISWANTO Departemen Statistika, Universitas Hasanuddin, Indonesia
M. Zaky Hisyam Gozhi Departemen Statistika, Universitas Hasanuddin, Indonesia
Muh. Ikbal Taufik Departemen Statistika, Universitas Hasanuddin, Indonesia
Anisa Kalondeng Departemen Statistika, Universitas Hasanuddin, Indonesia
Sitti Sahriman Departemen Statistika, Universitas Hasanuddin, Indonesia

DOI:

https://doi.org/10.20956/j.v21i3.43203

Keywords:

Linearized Ridge Regression, MM-Estimator, Rainfall, Statistical Downscaling

Abstract

Rainfall is one of the important climate variables to be predicted because it affects various sectors, such as agriculture, health, and disasters. One method that can be used to forecast rainfall is statistical downscaling, which is the process of relating large-scale climate variables to local-scale climate variables. However, this method has several challenges, such as the presence of heteroscedasticity, multicollinearity, and outliers in the data. To overcome these challenges, this study proposes linearized ridge regression modelling with MM-estimator in statistical downscaling for rainfall forecasting. Linearized ridge regression is a linear regression method that can reduce the influence of multicollinearity by adding a penalty parameter to the covariance matrix. MM-estimator is a robust method that can handle outliers by using two estimators, namely the initial estimator (S-estimator) and the final estimator (M-estimator). This research uses daily rainfall data from BMKG Pangkep station and Global Circulation Model (GCM) output data as predictors. The results showed that linearized ridge regression modelling with MM-estimator has better performance than linearized ridge regression modelling without MM-estimator in terms of accuracy and resilience to outliers with a correlation value of 0.94 against the acute rainfall data, the Root Means Square Error value obtained is 97.26 and 86.57% of determinant coefisient value. Therefore, linearized ridge regression modelling with MM-estimator can be used as an alternative statistical downscaling method for rainfall forecasting. Based on the forecasting results for January - December 2023, it shows that the highest rainfall in Pangkep Regency is in January and the lowest rainfall is in September.

References

[1] Adam, M., Sahriman, S., & Sirajang, N., 2023. Penerapan Metode Linearized Ridge Regression pada Data yang Mengandung Multikolinearitas. ESTIMASI: Journal of Statistics and Its Application, 4(1), 122–129.

[2] Araya-Osses, D., Casanueva, A., Román-Figueroa, C., Uribe, J. M., & Paneque, M., 2020. Climate change projections of temperature and precipitation in Chile based on statistical downscaling. Climate Dynamics, 54(9–10), 4309–4330. https://doi.org/10.1007/s00382-020-05231-4

[3] Asyeifa, V. R., 2017. Pemodelan Statistical Downscaling dengan Projection Pursuit Regression untuk Meramalkan Curah Hujan Bulanan di Sentra Produksi Padi Jawa Timur. Institut Teknologi Sepuluh Npember.

[4] Atamia, N. A., Susanti, Y., & Handajani, S. S., 2021. PRISMA, Prosiding Seminar Nasional Matematika Perbandingan Analisis Regresi Robust Estimasi-S dan Estimasi-M dengan Pembobot Huber dalam Mengatasi Outlier. Prosiding Seminar Nasional Matematika, 4, 673–679. https://journal.unnes.ac.id/sju/index.php/prisma/

[5] Gajbhiye, S., Meshram, C., Singh, S. K., Srivastava, P. K., & Islam, T., 2016. Precipitation trend analysis of Sindh River basin, India, from 102‐year record (1901–2002). Atmospheric Science Letters, 17(1), 71–77. https://doi.org/10.1002/asl.602

[6] Huber, P. J., 1973. Robust Regression: Asymtotics, Conjectures And Monte Carlo. The Annals of Statistics, 1(5), 799–821.

[7] Jadhav, N. H., 2020. On linearized ridge logistic estimator in the presence of multicollinearity. Computational Statistics, 35(2), 667–687. https://doi.org/10.1007/s00180-019-00935-6

[8] Liu, X.-Q., & Gao, F., 2011. Linearized Ridge Regression Estimator in Linear Regression. Communications in Statistics - Theory and Methods, 40(12), 2182–2192. https://doi.org/10.1080/03610921003746693

[9] Mardiana., 2019. Perbandingan Model Regresi Robust Estimasi M, Estimasi S Dan Estimasi MM Pada Faktor Yang Mempengaruhi Angka Kejadian Demam Berdarah Dengue Di Provinsi Jawa Timur Tahun 2017. Universitas Airlangga.

[10] Nugroho, B. D. A. (2021). Penerapan Klimatologi dalam Pertanian 4.0. Deepublish.

[11] Özkale, M. R., & Nyquist, H., 2021. The stochastic restricted ridge estimator in generalized linear models. Statistical Papers, 62(3), 1421–1460. https://doi.org/10.1007/s00362-019-01142-7

[12] Pangestu, B. A. W., & Purhadi, P., 2020. Pemodelan Faktor-faktor yang Mempengaruhi Angka Kematian Bayi dan Angka Kematian Ibu di Provinsi Jawa Timur Tahun 2017 dan Tahun 2018 Menggunakan Bivariate Gamma Regression. Inferensi, 3(2), 89. https://doi.org/10.12962/j27213862.v3i2.7363

[13] Paramita, R. M., & Mukono, J., 2018. Hubungan Kelembapan Udara Dan Curah Hujan dengan Kejadian Demam Berdarah Dengue Di Puskesmas Gunung AnyaR 2010-2016. The Indonesian Journal of Public Health, 12(2), 202. https://doi.org/10.20473/ijph.v12i2.2017.202-212

[14] Rahayu, D. A., Nursholihah, U. F., Suryaputra, G., & Surono, S., 2023. Comparasion of The M, MM and S Estimator in Robust Regression Analysis on Indonesian Literacy Index Data 2018. EKSAKTA: Journal of Sciences and Data Analysis, 11–22. https://doi.org/10.20885/eksakta.vol4.iss1.art2

[15] Ruslana, Z. N., Tresnawati, R., Rosyidah, R., Harmoko, I. W., & Siswanto, S. (2021). Reliabilitas Prediksi Curah Hujan Dasarian Pada Kejadian Curah Hujan Ekstrim Pemicu Banjir 26 Oktober 2020 di Kebumen: Model Statistik (HyBMG) versus Model Dinamik (ECMWF). Jurnal Geosains dan Teknologi, 4(2), 83–100. https://doi.org/10.14710/jgt.4.2.2021.83-100

[16] Sahriman, S., Randa, E. L., Surianda, S. A., Hisyam, M. Z. G., Taufik, Muh. I., & Putra, G. D., 2024. Rainfall Forecasting Of Salt Producing Areas In Pangkep Regency Using Statistical Downscaling Model With Linearized Ridge Regression Dummy. BAREKENG: Jurnal Ilmu Matematika dan Terapan, 18(1), 0483–0492. https://doi.org/10.30598/barekengvol18iss1pp0483-0492

[17] Sahriman, S., & Yulianti, A. S., 2023. Statistical Downscaling Model With Principal Component Regression And Latent Root Regression To Forecast Rainfall In Pangkep Regency. BAREKENG: Jurnal Ilmu Matematika dan Terapan, 17(1), 0401–0410. https://doi.org/10.30598/barekengvol17iss1pp0401-0410

[18] Saputra, M. D., Hadi, A. F., Riski, A., & Anggraeni, D., 2021. Principal Component Regression in Statistical Downscaling with Missing Value for Daily Rainfall Forecasting. International Journal of Quantitative Research and Modeling, 2(3), 139–146. https://doi.org/10.46336/ijqrm.v2i3.151

[19] Setiawan, W., Nessyana Debataraja, N., & Sulistianingsih, E., 2019. Metode Estimasi-S Pada Analisis Regresi Robust Dengan Pembobotan Tukey Bisquare (Vol. 08, Nomor 2).

[20] Shodiqin, A., Aini, A. N., & Rubowo, M. R., 2018. Perbanding Dua Metode Regresi Robust Yakni Metode Least Trimmed Squares (LTS) dengan Metode Estimator-MM (ESTMASI-MM) (Studi Kasus Data Ujian Tulis Masuk Terhadap Hasil Ipk Mahasiswa Upgris). Jurnal Ilmiah Teknosains, 4(1).

[21] Susanti, Y., Pratiwi, H., Sulistijowati, H., & Liana, T., 2014. M Estimation, s estimation, and mm estimation in robust regression. International Journal of Pure and Applied Mathematics, 3, 349–360. https://doi.org/10.12732/ijpam.v91i3.7

[22] Upa, D. S., Sahriman, S., & Thamrin, S. A., 2021. Pemodelan Statistical Downscaling dengan Regresi Modifikasi Jackknife Ridge Dummy Berbasis K-means untuk Pendugaan Curah Hujan. ESTIMASI: Journal of Statistics and Its Application, 2(1), 19–28. https://doi.org/10.20956/ejsa.v2i1.11189

[23] Wigena, A. H., Djuraidah, A., & Sahriman, S., 2015. Statistical Downscaling Dengan Pergeseran Waktu Berdasarkan Korelasi Silang. Jurnal Meteorologi dan Geofisika, 16(1), 19–24. https://doi.org/10.31172/jmg.v16i1.259

[24] Yangfan, L., Bian, C., & Chen, H., 2023. Generalized Ridge Regression-Based Channelwise Feature Map Weighted Reconstruction Network for Fine-Grained Few-Shot Ship Classification. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–10. https://doi.org/10.1109/TGRS.2023.3235747