On a Discrete New Generalized Pareto-Based Regression Model for Count Data

Abstract

Count data often exhibit overdispersion, heavy tails, and decreasing failure rates, which limit the applicability of classical Poisson regression models. In this paper, we develop a regression model based on the discrete new generalized Pareto (DNGP) distribution to better capture these features. The proposed model incorporates covariate effects through suitable link function and parameters are estimated using maximum likelihood estimation methods. Simulation studies, model comparison and real data applications demonstrate that the DNGP regression model provides a flexible and effective alternative for analyzing complex count data.