Implementation of Robust Mixed Geographically and Temporally Weighted Regression for Crime Rate Prediction in East Java

Affa  Lelira Ibrahim; Trimono; Aviolla Terza Damaliana

doi:10.36456/jstat.vol19.no1.a11261

Authors

Affa Lelira Ibrahim Universitas Pembangunan Nasional Veteran Jawa Timur
Trimono Universitas Pembangunan Nasional Veteran Jawa Timur
Aviolla Terza Damaliana Universitas Pembangunan Nasional Veteran Jawa Timur

DOI:

https://doi.org/10.36456/jstat.vol19.no1.a11261

Keywords:

Crime, East Java, Robust Mixed GTWR, MM-Estimator, Outlier

Abstract

The total number of crimes in East Java Province reached 60,102 cases in 2024, indicating spatial and temporal variation in crime patterns. These data characteristics are heterogeneous and contain several extreme values (outliers) that may affect the stability of standard regression model estimates. This study applies the Robust Mixed Geographically and Temporally Weighted Regression (RMGTWR) model to examine spatiotemporal crime patterns in East Java during the 2020–2024 period and to evaluate the model’s ability to handle outliers in heterogeneous data. The evaluation results show that the RMGTWR model produced an of 0.84 and an MSE of 1912.247. This robust approach provides more stable parameter estimates and reduces the influence of the 14 identified outlier observations compared with the non-robust model. The findings indicate that the Human Development Index (HDI) and the Gini Ratio have significant global effects, while the Police Ratio variable shows varying local effects. These results confirm that the RMGTWR approach accommodates data heterogeneity while mitigating distortions caused by outliers in crime analysis in East Java.

References

[1] Institute for Economics & Peace. Global Peace Index 2024: Measuring Peace in a Complex World, Sydney, June 2024. Available from: http://visionofhumanity.org/resources

[2] Badan Pusat Statistik, Statistik Kriminal 2024, Jakarta: BPS RI, 2024. [Online]. Available: https://www.bps.go.id.

[3] Sustainable development goal 16: Perdamaian, Keadilan Dan Kelembagaan Yang Tangguh perserikatan Bangsa-Bangsa di Indonesia,” https://indonesia.un.org/id/sdgs/16/key-functions.

[4] H. Leitner and E. Sheppard, “Theorizing Globally, But Analyzing Locally: The Importance Of Geographically Weighted Regression In Crime Analysis”, Crime Science, vol. 11, no. 1, pp. 1–14, 2022.

[5] X. X. Zhu et al, “Geographically and Temporally Weighted Regression in Assessing Dengue Fever Spread Factors in Yunnan Border Regions,” Biomedical and Environmental Sciences, vol. 37, no. 5, pp. 511–520, May 2024, doi: 10.3967/bes2024.056.

[6] J. Liu et al., “A mixed geographically and temporally weighted regression: Exploring spatial-temporal variations from global and local perspectives,” Entropy, vol. 19, no. 2, 2017, doi: 10.3390/e19020053.

[7] Z. Hong, C. Mei, H. Wang, and W. Du, “Spatiotemporal effects of climate factors on childhood hand, foot, and mouth disease: a case study using mixed geographically and temporally weighted regression models,” International Journal of Geographical Information Science, vol. 35, 2021, doi: 10.1080/13658816.2021.1882681.

[8] S. A. Ania, N. Ilyas, and E. T. Herdiani, “Robust Spatial Temporal Analysis with Improved Geographically and Temporally Weighted Regression Model of Dengue Incidence Rate,” Communications in Mathematical Biology and Neuroscience, 2024, doi: 10.28919/cmbn/8376.

[9] N. Nessyana Debataraja, D. Kusnandar, R. Mahalalita, and N. Imro’ah, “Penerapan Model Geographically and Temporally Weighted Regression Pada Kecelakaan Lalu Lintas,” Jurnal Siger Matematika, vol. 02, pp. 19–24, 2021.

[10] Y. Rahkmawati, R. Faulina, and I. Nur Laily Fitriana, “Spatial Analysis of Gross Enrollment Ratio in Higher Education Using the Geographically Weighted Regression Approach,” J Statistika, vol. 18, no. 2, 2025.

[11] M. Jainudin, M. N. Hayati, and D. I. Purnamasari, “Deteksi Pencilan Spasial pada Data Kandungan Klorida di Sungai Mahakam Wilayah Samarinda Kalimantan Timur,” Jurnal EKSPONENSIAL, vol. 10, no. 2, 2019.

[12] A. Hujjah Asianingrum and A. Djuraidah, “Robust Mixed Geographically and Temporally Weighted Regression to Modeling the Percentage of Poverty Population in Java in 2012-2018,” International Journal of Sciences: Basic and Applied Research (IJSBAR), vol. 53, no. 2, pp. 186–197, 2020.

[13] G. Khusnul Ma’rifah, M. Idhom, and Trimono, “Implementation of Geographically and Temporally Weighted Regression with Cross Validation and Generalized Cross Validation Methods for Deforestation Modeling in Kalimantan,” J Statistika, vol. 18, no. 1, 2025

[14] A. Rahmah Putri, H. Yozza, and F. Yanuar, “Regresi Robust MM-Estimator untuk Memodelkan Jumlah Kematian Balita di Provinsi Jawa Timur Tahun 2017,” Jurnal Matematika UNAND, vol. 10, no. 1, pp. 71–78, 2021.

[15] E. Itskovich, “Economic Inequality, Relative Deprivation, and Crime: An Individual-Level Examination,” Justice Quarterly, vol. 42, no. 4, pp. 637–658, 2025, doi: 10.1080/07418825.2024.2435859.