eCite Digital Repository

A Poisson-Gamma model for analysis of ecological non-negative continuous data


Foster, SD and Bravington, MV, A Poisson-Gamma model for analysis of ecological non-negative continuous data, Environmental and Ecological Statistics, 20, (4) pp. 533-552. ISSN 1352-8505 (2013) [Refereed Article]

Copyright Statement

Springer Science+Business Media New York 2012

DOI: doi:10.1007/s10651-012-0233-0


The statistical analysis of continuous data that is non-negative is a common task in quantitative ecology. An example, and our motivation, is the weight of a given fish species in a fish trawl. The analysis task is complicated by the occurrence of exactly zero observations. It makes many statistical methods for continuous data inappropriate. In this paper we propose a model that extends a Tweedie generalised linear model. The proposed model exploits the fact that a Tweedie distribution is equivalent to the distribution obtained by summing a Poisson number of gamma random variables. In the proposed model, both the number of gamma variates, and their average size, are modelled separately. The model has a composite link and has a flexible mean-variance relationship that can vary with covariates. We illustrate the model, and compare it to other models, using data from a fish trawl survey in south-east Australia.

Item Details

Item Type:Refereed Article
Keywords:compound gamma, compound poisson, generalised linear model, poisson mixture of gammas, Tweedie, zeros
Research Division:Mathematical Sciences
Research Group:Statistics
Research Field:Stochastic analysis and modelling
Objective Division:Environmental Management
Objective Group:Other environmental management
Objective Field:Other environmental management not elsewhere classified
UTAS Author:Foster, SD (Dr Scott Foster)
ID Code:119094
Year Published:2013
Web of Science® Times Cited:55
Deposited By:Directorate
Deposited On:2017-07-26
Last Modified:2017-10-16

Repository Staff Only: item control page