Modeling Road Traffic Accident Cases in Benue State of Nigeria Using Count Data Regression Models

The aim of this study is to model annual road traffic accident death cases in Benue state of Nigeria using fatal, serious and minor cases as independent variables. The research employs three count data regression models-Poisson regression, Negative Binomial regression, and Generalized Poisson regression-to predict road traffic accident-related deaths based on these variables. Annual secondary data from the Federal Road Safety Corps (FRSC), covering the period from January 2000 to December 2022, were utilized. The study found that Poisson Regression could not handle the over-dispersion present in the accident data in Benue State. As a result, Negative Binomial Regression and Generalized Poisson Regression were considered, with Generalized Poisson Regression identified as the best model based on performance criteria such as -2 log likelihood (-2logL), Akaike information criterion (AIC), and Bayesian information criterion (BIC).