Penerapan Model Regresi Hurdle Binomial Negatif Menggunakan Algoritma Broyden-Fletcher-Goldfarb-Shanno pada Data Jumlah Kematian Bayi di Kota Makassar Tahun 2017

Article History

Submited : September 15, 2022
Published : January 29, 2024

Poisson regression is a nonlinear regression method used to analyse the relationship between discrete response variables. Equidispersion is the assumption that must be met in the Poisson regression. Furthermore, there are cases in which the equidispersion assumption is invalidated when using the Poisson regression model to analyze data. One such case is overdispersion, which occurs when there is an excess of zero. As a result, the Negative Hurdle Binomial (HBN) regression is implemented to solve the overdispersion issue. Maximum Likelihood Estimation (MLE) with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm was applied in this study to perform parameter estimation. In addition, the HBN regression model was used to analyze the data on the number of infant mortality cases in Makassar in 2017 with the variables assumed to be significant with infant mortality. The percentage of infants who were exclusively breastfed was the variable that had a significant impact on the outcome of HBN regression on the data on the number of infant mortality that experienced overdispersion.


  1. Abdiana. Determinan Kematian Bayi di Kota Payakumbuh. Jurnal Kesehatan Masyarakat Andalas, 9, 2015.
  2. Famoye, F., John T. Wulu, J., & Singh, K. P. On the Generalized Poisson Regression Model with an Application to Accident Data. Journal of Data Science, 287-295, 2004.
  3. Coxe, S., West, S. G., & Aiken, L. S. The Analysis of Count Data: A Gentle Introduction to Poisson Regression and Its Alternatives. Journal of Personality Assessment, 121-136, 2009.
  4. Pontoh, R. S., & Faidah, D. Y. Penerapan Hurdle Negative Binomial pada Data Tersensor. Seminar Nasional Matematika dan Pendidikan Matematika UNY, 2015.
  5. Rahayu, R. L., Asrof, A., & Rustiana, S. Perbandingan Regresi Zero Inflated Negative Binomial dan Regresi Hurdle Negative Binomial pada Data Overdispersi (Studi Kasus: Kejadian Difteri di Indonesia). Jurnal Sains Matematika dan Statistika, 2018.
  6. Bhakta, N. Properties of Hurdle Negative Binomial Models for Zero-Inflated and Overdispersed Count Data. Dalam Dissertation. The Ohio State University. 2018.
  7. Cantoni, E., & Zedini, A. A robust version of the Hurdle model. Journal of Statistical Planning anda Inference, 1214-1223, 2010.


Download data is not yet available.