Count Models Based on Weibull Interarrival Times

TL;DR

This paper introduces a flexible Weibull-based count model that generalizes Poisson and negative binomial models, effectively handling overdispersion and underdispersion in count data with straightforward covariate integration.

Contribution

The paper presents a novel Weibull interarrival time model for count data that encompasses existing models and offers improved flexibility and ease of use.

Findings

Models both over and underdispersed data

Allows covariates via hazard function

Computable with standard software

Abstract

In this paper, we introduce a generalized model for count data based upon an assumed Weibull interarrival process that nests the Poisson and negative binomial models as special cases. In addition, we demonstrate that this new Weibull count model can model both over and underdispersed count data, allow covariates to be introduced in a straightforward manner through the hazard function, and be computed in standard software.