Richard Arnold

Victoria University of Wellington

Capture-Recapture estimation using finite mixtures of arbitrary dimension

Reversible Jump MCMC methods are used to fit Bayesian capture-recapture models incorporating heterogeneity in individuals and samples. Heterogeneity in capture probabilities comes from finite mixtures and/or fixed sample effects allowing for interactions. Estimation by Reversible Jump MCMC allows automatic model selection and/or model averaging. Priors on the parameters stabilise the estimates and produce realistic credible intervals for population size for over-parameterised models, in contrast to likelihood based methods. To demonstrate the approach we analyse the standard Snowshoe Hare and Cottontail Rabbit data sets from ecology, and a reliability testing data set.