15th Australian Statistical Conference: Goodness-of-fit methods for species abundance distributions

Robert A. R. King and Phillip Cassey

Australian School of Environmental Studies, Griffith University, Brisbane, Australia

Abstract

A variety of different models have been proposed for the distribution of biomass or abundance across different species in a particular environment. We will briefly review the historical development of goodness-of-fit tests to distinguish among a general class of stochastic resource apportionment models using replicated species abundance data.

We present results from corrections to the existing goodness-of-fit methods, and illustrate the use of a new method with data from a variety of ecological surveys. The goodness-of-fit test we present is equally applicable to models of species abundance and biomass as it is to any comparison of a replicated observed distribution and a theoretical stochastic model.

The examples we present show that our new method provides a good level of discrimination between models that match the data and those that do not.

publication and conference paper details


Publications information
Robert King's page
Statistics
Mathematical and Physical Sciences
University of Newcastle
Robert King-photo
icon
File "rking/publ/asc15.html" last updated 05:24:27 PM, Fri Jul 13, 2001
comments to: robert.king@newcastle.edu.au