Two ways of modelling overdispersion in non-normal data
Source: Journal of the Royal Statistical Society: Series C (Applied Statistics), Volume 49, Number 4, 2000 , pp. 591-598(8)
Abstract:For non-normal data assumed to have distributions, such as the Poisson distribution, which have an a priori dispersion parameter, there are two ways of modelling overdispersion: by a quasi-likelihood approach or with a random-effect model. The two approaches yield different variance functions for the response, which may be distinguishable if adequate data are available. The epilepsy data of Thall and Vail and the fabric data of Bissell are used to exemplify the ideas.
Document Type: Original Article
Publication date: January 1, 2000