Zero Inflated Negative Binomial (ZINB) Regression: Application to the Pneumonia Study and Simulation under Several Scenarios

Santi Wahyu Salsabila, Achmad Efendi, Nurjannah Nurjannah

Abstract


This study aims at evaluating the performance of Zero Inflated Negative Binomial (ZINB) regression analysis using the Maximum Likelihood Estimation (MLE) approach through simulation study. The research data used are secondary data and simulations. Secondary data was obtained from the Ministry of Health of the Republic of Indonesia in 2023 regarding cases of under-five deaths due to pneumonia with a total of 38 samples. The simulation study is conducted to analyze the performance of ZINB regression based on various sample sizes and proportions of zero values. The results show that the ZINB regression model with the MLE approach produces parameter estimates that tend to be more sensitive to sample size, with improved performance at large sample sizes. Data with a large proportion of zeros reflects high variability as well as the presence of excess zeros, so the ZINB regression model can provide more stable and precise parameter estimates than those with a lower proportion of zeros. Therefore, the ZINB regression model is effective for data with a high proportion of zeros as it fits the characteristics of the data distribution, especially in cases of under-five deaths due to pneumonia.

Keywords


Excess Zero; MLE; Pneumonia; Simulation; ZINB

Full Text:

PDF

References


[1] D. C. Montgomery, E. A. Peck, and G. G. Vining, Introduction to linear regression analysis. John Wiley & Sons, 2012.

[2] L. Anisa and N. A. K. Rifai, “Analisis Regresi Logistik Biner dengan Metode Penalized Maximum Likelihood pada Penyakit Covid-19 di RSUD Pringsewu,” J. Ris. Stat., pp. 129–136, 2022, doi: 10.29313/jrs.v2i2.1425.

[3] A. C. Cameron and P. K. Trivedi, Regression analysis of count data, no. 53. Cambridge university press, 2013.

[4] A. R. Nasution, K. Sadik, and A. Rizki, “Perbandingan Kinerja Regresi Conway-Maxwell-Poisson dan Poisson-Tweedie dalam Mengatasi Overdispersi Melalui Data Simulasi,” Xplore J. Stat., vol. 11, no. 3, pp. 215–225, 2022, doi: 10.29244/xplore.v11i3.1018.

[5] R. Cahyandari, “Pengujian Overdispersi pada Model Regresi Poisson (Studi Kasus: Laka Lantas Mobil Penumpang di Provinsi Jawa Barat),” Statistika, vol. 14, no. 2, pp. 69–76, 2014, [Online]. Available: https://ejournal.unisba.ac.id/index.php/statistika/article/view/1204

[6] A. M. Garay, V. H. Lachos, and H. Bolfarine, “Bayesian estimation and case influence diagnostics for the zero-inflated negative binomial regression model,” J. Appl. Stat., vol. 42, no. 6, pp. 1148–1165, 2015, doi: 10.1080/02664763.2014.995610.

[7] J. M. Hilbe, “Negative Binomial Regression Second Edition-Negative Binomial Regression: Second Edition Joseph M. Hilbe Frontmatter More information,” pp. 1–18, 2011, [Online]. Available: www.cambridge.org

[8] D. A. Pradana, “Estimasi parameter regresi zero-inflated negative binomial dengan metode algoritma Expectation Maximization (EM)(studi kasus: penyakit difteri di Jawa Barat tahun 2016),” 2019, Universitas Negeri Malang.

[9] Azizah and D. Novita Sari, The Implementation of ZIP Regression and ZINB Regression to Overcome Overdispersion of Death Cases Due to Filariasis in Indonesia, vol. 20, no. 1. 2023. doi: 10.31851/sainmatika.v20i1.11707.

[10] B. K. Ghosh, R. Bowden, B. Gladwin, and C. Harrell, Simulation Using ProModel. McGraw-Hill, 2004.

[11] A. M. Law, W. D. Kelton, and W. D. Kelton, Simulation modeling and analysis, vol. 3. Mcgraw-hill New York, 2007.

[12] Kementrian Kesehatan, Profil Kesehatan Indonesia 2023. Jakarta: Kementerian Kesehatan RI, 2024.

[13] J. R. Wilson and K. A. Lorenz, Modeling binary correlated responses using SAS, SPSS and R, vol. 9. Springer, 2015.

[14] J. Stachurski, A primer in econometric theory. Mit Press, 2016.

[15] F. Famoye and J. S. Preisser, “Marginalized zero-inflated generalized Poisson regression,” J. Appl. Stat., vol. 45, no. 7, pp. 1247–1259, 2018, doi: 10.1080/02664763.2017.1364717.

[16] H. Zamani and N. Ismail, “Functional form for the zero-inflated generalized poisson regression model,” Commun. Stat. - Theory Methods, vol. 43, no. 3, pp. 515–529, 2014, doi: 10.1080/03610926.2012.665553.

[17] B. Ariawan, S. Suparti, and S. Sudarno, “Pemodelan Regresi Zero-Inflated Negative Binomial (Zinb) Untuk Data Respon Diskrit Dengan Excess Zeros,” J. Gaussian, vol. 1, no. 1, pp. 55–64, 2012.

[18] D. B. Hall, “Zero‐inflated Poisson and binomial regression with random effects: a case study,” Biometrics, vol. 56, no. 4, pp. 1030–1039, 2000.

[19] A. M. Garay, E. M. Hashimoto, E. M. M. Ortega, and V. H. Lachos, “On estimation and influence diagnostics for zero-inflated negative binomial regression models,” Comput. Stat. Data Anal., vol. 55, no. 3, pp. 1304–1318, 2011.

[20] D. Siagian, “Sugiarto,‘Metode Statistika untuk Bisnis dan Ekonomi’, Jakarta: PT,” Gramedia Pustaka Utama, 2002.

[21] M. I. Bhatti and H. Al-Shanfari, Econometric analysis of model selection and model testing. Routledge, 2017.

[22] E. H. Payne, M. Gebregziabher, J. W. Hardin, V. Ramakrishnan, and L. E. Egede, “An empirical approach to determine a threshold for assessing overdispersion in Poisson and negative binomial models for count data,” Commun. Stat. Comput., vol. 47, no. 6, pp. 1722–1738, 2018.

[23] Y. Gençtürk and A. Yiğiter, “Modelling claim number using a new mixture model: negative binomial gamma distribution,” J. Stat. Comput. Simul., vol. 86, no. 10, pp. 1829–1839, 2016, doi: 10.1080/00949655.2015.1085987.




DOI: https://doi.org/10.18860/cauchy.v10i1.32499

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Santi Wahyu Salsabila, Achmad Efendi, Nurjannah Nurjannah

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Editorial Office
Mathematics Department,
Universitas Islam Negeri Maulana Malik Ibrahim Malang
Gajayana Street 50 Malang, East Java, Indonesia 65144
Faximile (+62) 341 558933
e-mail: cauchy@uin-malang.ac.id

Creative Commons License
CAUCHY: Jurnal Matematika Murni dan Aplikasi is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.