Modeling Railway Level Crossing Accidents Using Zero-Inflated Poisson and Zero-Inflated Negative Binomial Approaches
DOI:
https://doi.org/10.37367/jpi.v10i1.604Keywords:
Jumlah kecelakaan, Perlintasan Sebidang, Regresi Zero-Inflated Poisson, Regresi Zero-Inflated Negative BinomialAbstract
Railway level crossing accidents constitute a complex transportation safety issue influenced by various geometric, operational, human, and infrastructure-related factors. Accident data at each crossing are generally in the form of count data dominated by zero values, making them difficult to model optimally using conventional Poisson or Negative Binomial regression models. This study aims to model the number of accidents at railway level crossings in the DAOP 7 region using the Zero-Inflated Poisson (ZIP) and Zero-Inflated Negative Binomial (ZINB) approaches. The predictor variables include train frequency, road width, road–rail intersection gradients on both the right and left sides, type of crossing, presence of an Early Warning System (EWS), road status, and type of crossing gate. The analysis was conducted using SPSS and Stata software, involving stages of zero proportion examination, estimation of ZIP and ZINB regression models, and selection of the best model based on the Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and log-likelihood values. The results indicate that the ZINB regression model provides a better fit compared to the ZIP model. Factors that significantly influence the number of accidents at railway level crossings in the DAOP 7 region include train frequency, right-side gradient, left-side gradient, type of crossing, presence of an Early Warning System, and type of crossing gate.
Downloads
References
Nov. 2020, doi: 10.1016/j.trip.2020.100249. DOI: https://doi.org/10.1016/j.trip.2020.100249
[10] T. Simmachan, N. Wongsai, S. Wongsai, and R. Lerdsuwansri, “Modeling road accident fatalities with underdispersion and zero-inflated counts,” PLoS One, vol. 17, no. 11 November, Nov. 2022, doi: 10.1371/journal.pone.0269022. DOI: https://doi.org/10.1371/journal.pone.0269022
[11] M. Salman Al Farisyi, “PERBANDINGAN REGRESI ZERO INFLATED POISSON (ZIP) DAN REGRESI ZERO-INFLATED NEGATIVE BINOMIAL (ZINB) PADA KASUS TANAH LONGSOR DI KOTA SEMARANG JURNAL ILMIAH Diajukan sebagai salah satu syarat memperoleh gelar Sarjana Statistika.” [Online]. Available: http://repository.unimus.ac.id
[12] L. H. Hashim, K. H. Hashim, and M. A. K. Shiker, “An Application Comparison of Two Poisson Models on Zero Count Data,” in Journal of Physics: Conference Series, IOP Publishing Ltd, Mar. 2021. doi: 10.1088/1742-6596/1818/1/012165. DOI: https://doi.org/10.1088/1742-6596/1818/1/012165
[13] C. Feng, “Zero-inflated models for adjusting varying exposures: a cautionary note on the pitfalls of using offset,” J. Appl. Stat., vol. 49, no. 1, pp. 1–23, 2022, doi: 10.1080/02664763.2020.1796943. DOI: https://doi.org/10.1080/02664763.2020.1796943
[14] D. C. Jhwueng and C. Y. Wu, “A Novel Phylogenetic Negative Binomial Regression Model for Count-Dependent Variables,” Biology (Basel)., vol. 12, no. 8, Aug. 2023, doi: 10.3390/biology12081148. DOI: https://doi.org/10.3390/biology12081148
[15] Y. N. Phang and E. F. Loh, “Statistical Analysis for Overdispersed Medical Count Data,” 2014.
[16] A. Fajri et al., “Pemodelan Regresi Zero Inflated Negative Binomial pada Data yang Mengalami Overdispersi,” ESTIMASI: Journal of Statistics and Its Application, vol. 6, no. 1, pp. 2721–379, 2025, doi: 10.20956/ejsa.v6i1.21037.
[17] D. Nada Fitriani and yunin Sofro, “PEMODELAN KASUS PNEUMONIA BERAT PADA BALITA DI KOTA SURABAYA MENGGUNAKAN ZERO-INFLATED NEGATIVE BINOMIAL,” Jurnal Matematika Januari, vol. 6, 2026, [Online]. Available: https://ejurnal.unisap.ac.id/leibniz/index
[18] Sugiyono, Metode Penelitian Manajemen, vol. 1. Bandung: Alfabeta, 2014.
[19] J. H. Kim, “Multicollinearity and misleading statistical results,” Korean J. Anesthesiol., vol. 72, no. 6, pp. 558–569, Dec. 2019, doi: 10.4097/kja.19087. DOI: https://doi.org/10.4097/kja.19087
[20] O. G. A, O. C. N, and O.-I. H. O, “Effect of Akaike Information Criterion on Model Selection in Analyzing Auto-crash Variables,” International Journal of Sciences: Basic and Applied Research (IJSBAR) International Journal of Sciences: Basic and Applied Research, vol. 26, no. 1, pp. 98–109, 2016, [Online]. Available: http://gssrr.org/index.php?journal=JournalOfBasicAndApplied
[21] M. Selviana, A. Atti, J. Rosalina Pahnael, and D. Program Studi Matematika, “Tahun 2025 MODEL REGRESI POISSON UNTUK MENGANALISIS FAKTOR-FAKTOR YANG BERPENGARUH TERHADAP JUMLAH PENGANGGURAN DI NUSA TENGGARA TIMUR Robertus Dole Guntur”.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jurnal Perkeretaapian Indonesia (Indonesian Railway Journal)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
The Authors submitting a manuscript do so on the understanding that if accepted for publication, the copyright of the article shall be assigned to Jurnal Perkeretaapian Indonesia (Indonesian Railway Journal).
