Bayesian hierarchical generalized linear models for a geographical subset of recovery data

Abstract

AbstractThe aim of this work is to check whether modifications in the length of the hunting seasons had an effect on the chance of reproduction of different species of ringed birds. We start from a national data set of ringing‐recovered data on three species of game birds. Only data on birds recovered as juveniles are used. Data on recoveries are organized in a 4‐way contingency table. Several generalized linear models are proposed for the counts of recovered birds. Bayesian hierarchical modeling is particularly suitable for this kind of data, for which an over‐dispersion parameter can be introduced at the second level of the hierarchy. Maximum Likelihood and Bayesian solutions are computed for the different models: the Bayesian framework, in particular under an individual modeling of over‐dispersion, exhibits the best fit in terms of Bayesian p‐value. The results show that the modification in the length of the hunting seasons does not produce equal benefits for the three species considered. Copyright © 2002 John Wiley & Sons, Ltd.