Mean-Parametrized Conway-Maxwell-Poisson Regression Models for Dispersed Counts

• Activity Number: 176 - Modeling
• Type: Contributed
• Date/Time: Monday, July 30, 2018 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistical Computing
• Author(s): Ho Ting Fung* and Alan Huang and Aya Alwan and Justin Wishart
• Companies: Macquarie University and University of Queensland and Macquarie University and Macquarie University
• Keywords: Count data; Generalized linear models; Overdispersion; Underdispersion; Conway-Maxwell-Poisson distribution; Using R

Abstract

Conway-Maxwell-Poisson (CMP) distributions are flexible generalizations of the Poisson distribution for modelling overdispersed or underdispersed counts. The main hindrance to their wider use in practice seems to be the inability to directly model the mean of counts, making them not compatible with nor comparable to competing count regression models, such as the log-linear Poisson, negative-binomial or generalized Poisson regression models. In this talk, we will illustrates how CMP distributions can be parametrized via the mean, so that simpler and more easily interpretable mean-models can be used, such as a log-linear model. Moreover, this talk introduces the R package which provides a collection of functions for estimation, testing and diagnostic checking for the proposed model. The performance of the R routine against the earlier proposed MATLAB routine will also be discussed.