A0410
Title: Bayesian Conway-Maxwell-Poisson regression for longitudinal count data
Authors: Yeongjin Gwon - University of Nebraska Medical Center (United States) [presenting]
Jane Meza - University of Nebraska Medical Center (United States)
Abstract: Longitudinal count data has been widely collected in biomedical research, public health, and clinical trials. These repeated measurements over time on the same subjects need to account for an appropriate dependency. The Poisson regression model is the first choice to model the expected count of interest. However, this may not be appropriate when data exhibit over-dispersion or under-dispersion. Recently, Conway-Maxwell-Poisson (CMP) distribution has been popularly used as the distribution offers the flexibility to capture a wide range of dispersion in the data. Bayesian CMP regression model proposed accommodating over and under-dispersion in modelling longitudinal count data. Specifically, a regression model with random intercept and the slope is developed to capture subject heterogeneity and estimate covariate effects to be different across subjects. A Bayesian computation is implemented via Hamiltonian MCMC (HMCMC) algorithm for posterior sampling. Bayesian model assessment measures are then computed for model comparison. Simulation studies are conducted to assess the accuracy and effectiveness of the methodology. A well-known example of Epilepsy data demonstrates the usefulness of the proposed methodology.