Logo image
Data Dispersion: Now You See it... Now You Don't
Technical documentation

Data Dispersion: Now You See it... Now You Don't

Kimberly F. Sellers and Galit Shmueli
Robert H. Smith School Research Paper No. RHS-06-122
05/2010

Abstract

Conway-Maxwell-Poisson (COM-Poisson) regression;mixture model;negative binomial regression;over dispersion;under-dispersion

The most popular method for modeling count data is Poisson regression. When data display over-dispersion, thereby deeming Poisson regression inadequate, typically negative-binomial regression is instead used. We show that count data that appear to be equi-dispersed or over-dispersed may actually stem from a mixture of populations with different dispersion levels. To detect and model such a mixture, we introduce a generalization of the Conway-Maxwell-Poisson (COM-Poisson) regression that allows for group-level dispersion. We illustrate mixed dispersion effects and the proposed methodology via semi-authentic data.

Metrics

1 Record Views

Details

Logo image