A Negative Binomial Regression Approach to Address Overdispersion in the Analysis of Maternal Mortality in Indonesia

Authors

  • Sischa Wahyuning Tyas Universitas Pembangunan Nasional "Veteran" Jawa Timur
  • Muhammad Nasrudin Universitas Pembangunan Nasional "Veteran" Jawa Timur
  • Awang Putra Sembada Universitas Pembangunan Nasional "Veteran" Jawa Timur
  • Robiansyah Putra Universitas Sumatera Utara

DOI:

https://doi.org/10.32734/jormtt.v8i1.25387

Keywords:

Maternal Mortality Rate, Negative Binomial Regression, AIC, Overdispersion, Public Health

Abstract

Maternal Mortality Rate (MMR) is one of the major indicators utilized for measuring the performance of public health systems. In Indonesia, there is a considerable level of MMR as shown by its MMR value of 189 per 100,000 live births in 2023 which is far from reaching its SDG target. This paper seeks to determine factors that influence maternal mortality in Indonesia .This research uses MMR as the response variable along with ten independent variables as predictors. The predictors consist of health-related factors and socio-economic conditions. The process starts with performing a descriptive statistic followed by multicollinearity test using Variance Inflation Factor (VIF). Poisson regression is initially applied and overdispersion was detected. Thus, Negative Binomial regression should be used as a better alternative. Selection of models is performed using AIC. Based on the result, factors that influence maternal mortality in Indonesia are percentages of medical personnel, proper sanitation, deliveries in health facilities, and T2 immunization. The optimal Negative Binomial Regression model has an AIC value of 416.0637.

Downloads

Download data is not yet available.

Downloads

Published

2026-05-20

How to Cite

[1]
S. W. Tyas, M. Nasrudin, A. P. Sembada, and R. Putra, “A Negative Binomial Regression Approach to Address Overdispersion in the Analysis of Maternal Mortality in Indonesia”, J. of Research in Math. Trends and Tech., vol. 8, no. 1, May 2026.