A semiparametric bayesian approach for mark-recapture estimation

Abstract

This paper describes a semiparametric Bayesian approach for modelling mark-recapture data. A main assumption in modelling mark-recapture data is that survival probabilities are homogeneous. We relax this assumption by modelling survival probabilities as a function of two parameters which explain variations due to unknown biological and environmental reasons. The heterogeneity in travel times and survival probabilities is accounted using the Dirichlet process. The Dirichlet process also provides a clustering mechanism which is often suitable for mark-recapture data where groups of animals can be thought of as arising from the same cohort. The approach is highlighted using actual data arising from thed Pacific Ocean Shelf Tracking (POST) project. Log-pseudo marginal likelihood (LPML) model selection procedure indicates that the proposed model performs better over conventional alternative methods.