ABSTRACT
Count data consist of non-negative integer values and are encountered frequently in the modeling of transportation-related phenomenon. Examples of count data variables in transportation include the number of driver route changes per week, the number of trip departure changes per week, drivers’ frequency-of-use of ITS technologies over some time period, number of vehicles waiting in a queue, and the number of accidents observed on road segments per year. Count data can be properly modeled by using a number of methods, the most popular of which are Poisson and negative binomial regression models. This chapter discusses count data models and the issues related to them such as over-dispersion, truncation (the truncated Poisson model), and count models that may be part of a two-state process (the zero-inflated Poisson and zero-inflated negative binomial models). Numerous examples of the models are provided to demonstrate their application and limitations of these models. The chapter demonstrates the great potential of these models to transportation data analysis.
