An extension of the Lin-Yip estimator for continous-time capture studies

Abstract

A unified approach is suggested to estimate the population size for continuous time capture studies with possible removals during the capture process. It extends and improves the Lin-Yip estimator. The usual recapture and removal models can be shown to be particular cases of the general formulation. A Horvitz-Thompson procedure is used to estimate the population size based on the estimated capture probabilities. The resultant estimators for the regression parameters and population size are consistent and asymptotically normal under appropriate regularity conditions. We assess the properties of the proposed estimators through Monte Carlo simulation. Two examples are given. © 2002 American Statistical Association and the International Biometric Society.