Modeling count data with excess zeroes: An empirical application to traffic accidents

Abstract

There are many studies in social sciences, such as traffic accident analysis, in which the event counts may be characterized by a large number of zero observations. In this article, a proposed model that takes into account both the zero-count state and the non-zero-count state is used to describe the traffic accident phenomenon. The probability of the zero-count state (p) and the mean number of event counts (μ) in the non-zero-count state may depend on the covariates. Sometimes, p and μ, are unrelated, while at other times, p may assume a simple function of μ. In proposing the model, different types of traffic accidents at signalized Intersections in Singapore were investigated. The results demonstrate that the zero-altered probability process is an appropriate technique for modeling specific types of accidents in which the data contain many zero counts.