Metode Geographically Weighted Logistic Regression untuk Memodelkan Kasus Kemiskinan di Indonesia Tahun 2022

Ane Nurahmi, Dwi Agustin Nuriani Sirodj

Abstract

Geographically Weighted Logistic Regression (GWLR) merupakan pengembangan dari model regresi logistik yang dirancang untuk menganalisis data spasial dengan variabel dependen kategorik. Penelitian ini bertujuan untuk memodelkan kasus kemiskinan di Indonesia pada tahun 2022 menggunakan fungsi pembobot Adaptive Gaussian Kernel serta mengidentifikasi faktor-faktor yang memengaruhinya. Hal ini penting mengingat garis kemiskinan nasional Indonesia (Rp 535.547/kapita/bulan) masih berada di bawah standar Bank Dunia (Rp 962.130/kapita/bulan). Tingkat kemiskinan di Indonesia menunjukkan variasi yang tinggi antarwilayah, yang dipengaruhi oleh perbedaan kondisi geografis dan karakteristik sosial ekonomi setempat. Dengan demikian, hubungan antara variabel-variabel penentu kemiskinan bersifat lokal dan bervariasi secara spasial. Pendekatan GWLR lebih tepat digunakan dibandingkan regresi logistik klasik karena mampu mengakomodasi heterogenitas spasial melalui pembobotan geografis. Kategori provinsi miskin ditetapkan berdasarkan nilai Head Count Index sebagai variabel dependen. Variabel independen yang dianalisis meliputi Pengeluaran Per Kapita Disesuaikan, Tingkat Pengangguran Terbuka, dan Upah Minimum Provinsi. Melalui penggunaan fungsi pembobot Adaptive Gaussian Kernel, diperoleh 34 model GWLR. Hasil penelitian menunjukkan bahwa Upah Minimum Provinsi berpengaruh signifikan terhadap tingkat kemiskinan pada delapan provinsi: Jawa Tengah, DI Yogyakarta, Jawa Timur, Bali, Nusa Tenggara Barat, Kalimantan Tengah, Kalimantan Selatan, dan Kalimantan Timur.

Kata kunci: adaptive gaussian; geographically weighted logistic regression; kemiskinan

Geographically Weighted Logistic Regression (GWLR) is a development of Logistic Regression for spatial data with a categorical dependent variable. The research aims to model poverty cases in Indonesia in 2022 using the Adaptive Gaussian Kernel weighting function and the factors that influence it, considering that Indonesia's poverty line is IDR 535,547/capita/month lower than the World Bank standard, IDR 962,130/capita/month. Poverty levels in Indonesia vary between regions due to different contributing factors based on geographical and socioeconomic conditions. Therefore, the relationship between variables that determine poverty is local and varies spatially, making the Geographically Weighted Logistic Regression (GWLR) method more appropriate than logistic regression because it is able to capture differences in influence between regions through geographical weighting. The poor province category is based on the Head Count Index value as the dependent variable. The dependent variables are adjusted Per Capita Expenditure, Open Unemployment Rate, and Provincial Minimum Wage. By using the Adaptive Gaussian Kernel weighting function, 34 models were obtained. The Provincial Minimum Wage has a significant effect on poverty cases in Indonesia in 8 provinces, namely the Provinces of Central Java, DI Yogyakarta, East Java, Bali, West Nusa Tenggara, Central Kalimantan, South Kalimantan and East Kalimantan.

Keywords: adaptive gaussian; geographically weighted logistic regression; poverty

References

H. H. Dukalang, “Perbandingan regresi logistik biner dan probit biner dalam pemodelan tingkat partisipasi angkatan kerja,” Euler : Jurnal Ilmiah Matematika, Sains dan Teknologi, vol. 7, no. 2, pp. 62–70, 2019, https://doi.org/10.34312/euler.v7i2.10355

A. Agresti, Categorical Data Analysis, 2nd ed. New York, NY, USA: Wiley, 2002.

N. A. Solekha and M. F. Qudratullah, “Pemodelan geographically weighted logistic regression dengan fungsi adaptive gaussian kernel terhadap kemiskinan di Provinsi NTT,” Jambura Journal of Mathematics, vol. 4, no. 1, pp. 17–32, 2022, https://doi.org/10.34312/jjom.v4i1.11452

M. Fathurahman, P. Purhadi, S. Sutikno, and V. Ratnasari, “Pemodelan geographically weighted logistic regression pada indeks pembangunan kesehatan masyarakat di Provinsi Papua,” Prosiding Seminar Nasional MIPA 2016, no. April, pp. 34–42, 2016, https://www.researchgate.net/publication/324690057_Pemodelan_Geographically_Weighted_Logistic_Regression_pada_Indeks_Pembangunan_Kesehatan_Masyarakat_di_Provinsi_Papua

A. S. Fotheringham, C. Brunsdon, and M. Charlton, Geographically Weighted Regression: The Analysis of Spatially Varying Relationships. Chichester, UK: Wiley, 2002.

M. A. Aliu, F. Zubedi, L. Yahya, and F. A. Oroh, “The comparison of kernel weighting functions in geographically weighted logistic regression in modeling poverty in Indonesia,” Jurnal Matematika, Statistika dan Komputasi, vol. 18, no. 3, pp. 362–384, 2022, https://doi.org/10.20956/j.v18i3.19567

Q. S. Wardhani, S. S. Handajani, and I. Susanto, “Pemodelan indeks pembangunan kesehatan masyarakat dengan metode geographically weighted logistic regression,” Jurnal Aplikasi Statistika dan Komputasi, vol. 14, no. 1, pp. 1–12, 2022, https://doi.org/10.34123/jurnalasks.v14i2.333

R. E. Caraka and H. Yasin, Geographically Weighted Regression (GWR): Sebuah Pendekatan Regresi Geografis, Yogyakarta: Mobius, 2017.

K. P. Burnham and D. R. Anderson, “Multimodel inference: understanding AIC and BIC in model selection,” Sociological Methods & Research, vol. 33, no. 2, pp. 261–304, 2004, https://doi.org/10.1177/0049124104268644

A. Dwinata, “Model Regresi Logistik Terboboti Geografis (Studi Kasus: Pemodelan Kemiskinan di Provinsi Jawa Timur),” master’s thesis, IPB University, Bogor, Indonesia, 2012.

L. Anselin, Spatial Econometrics: Methods and Models. Dordrecht, The Netherlands: Kluwer Academic Publishers, 1989.

C. C. Yrigoyen, I. G. Rodríguez, and J. V. Otero, “Modeling spatial variations in household disposable income with geographically weighted regression,” Munich Pers. RePEc Arch., vol. 50, no. 1682, p. 31, 2007, https://mpra.ub.uni-muenchen.de/1682/

U. R. Inayah, “Model Geographically Weighted Logistic Regression dengan Fungsi Pembobot Adaptive Bisquare (Studi Kasus: Indikator Pencemaran Air Biochemical Oxygen Demand di Daerah Aliran Sungai Mahakam Provinsi Kalimantan Timur Tahun 2016),” undergraduate thesis, Universitas Mulawarman, Samarinda, Indonesia, 2020.

D. W. Hosmer and S. Lemeshow, Applied Logistic Regression, 2nd ed. New York, NY, USA: John Wiley & Sons, 2000.

Badan Pusat Statistik (2022), Persentase Penduduk Miskin Menurut Provinsi [Online]. Available: http://bit.ly/49epT9q.

M. H. M. Saefulloh, M. R. Fahlevi, and S. A. Centauri, “Pengaruh inflasi terhadap pertumbuhan ekonomi: perspektif Indonesia,” Jurnal Keuangan Negara dan Kebijakan Publik, vol. 3, no. 1, pp. 17–26, 2023, https://paperity.org/p/339666110/pengaruh-inflasi-terhadap-pertumbuhan-ekonomi-perspektif-indonesia

R. S. D. B. Nahor and E. D. Anggraini, “Analysis of factors affecting poverty in Indonesia 2017-2022,” Converg. J. Econ. Dev., vol. 6, no. 1, pp. 16–33, 2025, https://doi.org/10.33369/convergencejep.v6i1.32904

H. Zirtana, M. Baiquni, and S. Sudrajat, “Pengaruh ketimpangan sosial ekonomi terhadap kemiskinan di daerah tertinggal Indonesia : analisis data panel 2015 – 2021,” Aspir. J. Masal. Sos., vol. 16, no. 1, pp. 35–51, 2025, https://doi.org/10.46807/aspirasi.v16i1.3260

E. Fernando and M. A. Samsuddin, “Analisis pengaruh tingkat kesehatan dan tingkat pendidikan terhadap tingkat kemiskinan di Indonesia tahun 2017-2024,” vol. 02, no. 02, pp. 54–59, 2025, https://doi.org/10.70134/jukoni.v2i2.533

L. Priseptian and W. P. Primandhana, “Analisis faktor-faktor yang mempengaruhi kemiskinan,” Forum Ekon., vol. 24, no. 1, pp. 45–53, 2022, https://doi.org/ 10.30872/jfor.v24i1.10362

DOI: https://doi.org/10.13057/ijas.v8i1.92564

Refbacks

  • There are currently no refbacks.