Abstract: The primary goal of this paper is to estimate population size associated with the capture-recapture model when the capture probability vary with behavior response and time (or trapping occasion). We cast the capture-recapture model in a Bayesian framework and make inference by using the Gibbs sampler, a Markov Chain Monte Carlo method. Using the method of maximum likelihood estimation, certain assumptions on the relationship between the capture and recapture probabilities are required in order to make inference of population size for the behavior response model. The major advantage of this approach is that no assumption is needed in our proposed procedure. The proposed methodology is illustrated with real data and a simulation study. The results show that the Gibbs sampler provides sound inference of population size.
Key words and phrases: Behavior response, capture-recapture model, Gibbs sampler, Markov Chain Monte Carlo method, population size, time variation.