A conditionally unbiased estimator for the equal-catchability model

Ian Britton James Goudie, J Ashbridge

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

In this article we reconsider an estimator of population size previously advocated for use when sampling from a population subdivided into different types. We show that it may be usefully adopted in the simple equal-catchability model used in mark-recapture. Unlike the commonly used maximum likelihood estimator, this conditionally unbiased estimator is always finite-valued. Except in situations in which the data contain little relevant information, its performance, in terms of bias and precision, is seen to be at least as good as that of the maximum likelihood estimator. Two estimators of the standard deviation of the conditionally unbiased estimator are considered.

Original languageEnglish
Pages (from-to)1543-1553
Number of pages11
JournalCommunications in Statistics: Theory and Methods
Volume34
Issue number7
DOIs
Publication statusPublished - Jul 2005

Keywords

  • capture-recapture sampling
  • C-number
  • factorial series distribution
  • population size
  • OCCUPANCY PROBLEM
  • POPULATION-SIZE
  • MARK-RECAPTURE
  • COVERAGE
  • NUMBER
  • CENSUS

Fingerprint

Dive into the research topics of 'A conditionally unbiased estimator for the equal-catchability model'. Together they form a unique fingerprint.

Cite this