Bayesian Estimation of Wildlife Population Size for Small Sample Data

• Activity Number: 298
• Type: Topic Contributed
• Date/Time: Wednesday, August 11, 2004 : 8:30 AM to 10:20 AM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Chong He*+
• Companies: University of Missouri, Columbia
• Keywords: Bayesian estimation ; population size ; small sample ; capture-recapture ; noninformative prior

Abstract

We consider the problem of estimating the population size using capture-recapture data in a Bayesian framework. The model M_t has prodigious application in wildlife management, ecology, software liability, epidemiological study, census undercount, and other research areas. Previous studies showed that Bayesian inference can have a sensitive dependence upon the hyper-parameters of the prior distribution. Four commonly used noninformative priors are onsidered. The optimal choice of noninformative priors depends on the number of sampling occasions. Some guidelines on the choice of noninformative priors are provided based on the simulation results. Propriety of applying improper noninformative prior is discussed. Simulation studies are developed to inspect the frequentist performance of Bayesian point and interval estimates with different noninformative priors under various population size, capture probabilities, and the number of sampling occasions. The simulation results show that the Bayesian approach can provide more accurate estimates of the population size than the MLE for small sample. Two real-data examples are given to illustrate the method.