Estimation of population size by a single tagging capture-recapture process

Gilson Yuuji SHIMIZU[1]

José Galvão LEITE[2]

Nelson Ithiro TANAKA1

§    ABSTRACT: We consider the estimation of the size of a closed animal population and of the related capture probabilities, based on a capture-recapture process with a single tagging stage. Such process consists in tagging a number of randomly selected animals, replacing them and in each one of several samplings done subsequently in the population, counting both marked and non marked animals. No animals are marked after the first sampling. In some cases this method is cheaper and easier to implement than the usual capture-recapture process. We obtain maximum and conditional maximum likelihood estimates for the population size, for the capture probabilities and approximate confidence interval for the population size. We present examples with both simulated and real data.

§    KEYWORDS: Closed population; single tagging capture-recapture process; maximum and conditional maximum likelihood estimates; confidence interval.



[1] Departamento de Estatística, Instituto de Matemática e Estatística -- IME, Universidade de São Paulo -- USP, Rua do Matão, 1010 - Cidade Universitária, CEP: 05508-090, São Paulo, SP, Brasil, E-mail: gshimizu@ime.usp.br / nitanaka@ime.usp.br

[2] Departamento de Estatística, Centro de Ciências Exatas e Tecnologia, Universidade Fe-deral de São Carlos-UFSCar, Caixa Postal 676, CEP: 13565-905, São Carlos, SP, Brasil, E-mail: leite@power.ufscar.br