<![CDATA[Tuberculosis (TB) remains a major public health problem, particularly in developing countries. The analysis of TB case counts typically involves count data that often exhibit overdispersion, making the selection of an appropriate statistical model essential. This study aims to model the number of TB cases in Lampung Province and to identify factors associated with its incidence using a Generalized Linear Model (GLM) approach. The analytical methods applied include Poisson regression and negative binomial regression. Poisson regression was first employed, followed by testing the equidispersion assumption. The results indicate the presence of overdispersion in the data; therefore, negative binomial regression was adopted as a more suitable alternative. Model selection was based on the Akaike Information Criterion (AIC). The results show that negative binomial regression outperforms Poisson regression in modeling TB case counts. The number of people living in poverty has a statistically significant effect on increasing TB cases, while the number of public hospitals and population density do not exhibit statistically significant effects. These findings suggest that socioeconomic factors play a critical role in the spread of TB in Lampung Province. This study concludes that negative binomial regression is a more appropriate model for analyzing TB case counts with overdispersion. The findings are expected to provide useful insights for policymakers in designing TB control strategies that integrate socioeconomic interventions with improvements in healthcare service quality.]]>
Copyrights © 2026
