Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

If You Use a Screen Reader

This content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.

A New Method for Estimating Population Size from Removal Data

Frank Louis Carle and Mike R. Strub
Biometrics
Vol. 34, No. 4 (Dec., 1978), pp. 621-630
DOI: 10.2307/2530381
Stable URL: http://www.jstor.org/stable/2530381
Page Count: 10
  • Read Online (Free)
  • Download ($14.00)
  • Subscribe ($19.50)
  • Cite this Item
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
A New Method for Estimating Population Size from Removal Data
Preview not available

Abstract

The theory leading to the maximum likelihood (ML) estimation of population size from removal data is reviewed. The assumptions of the removal method are that changes in population size occur only through capture, and the probability of capture is equal for all individuals in a population during the removal sequence. A modification of the multinomial model is proposed and a new estimator developed. In the new model the likelihood density of the probability of capture is weighted with a beta prior. The case where α = β = 1 (uniform prior) is compared with ML estimation and found to have lower bias and variance. The new method, unlike previous methods, does not fail for any catch vector thus avoiding the substitution of the total catch for the estimate of N when infinite estimates occur. The assumptions that result from applying large sample theory while estimating the variance of ML estimates are reviewed, and a condition presented for the inadequacy of asymptotic variance formulae when using the weighted estimator (α = β = 1). Examples illustrating the use of the new method are given; one example illustrates the use of the new method when previous methods fail. Various assumption violations are investigated and the new method is found to be more robust against the violation of assumptions than previous methods.

Page Thumbnails

  • Thumbnail: Page 
621
    621
  • Thumbnail: Page 
622
    622
  • Thumbnail: Page 
623
    623
  • Thumbnail: Page 
624
    624
  • Thumbnail: Page 
625
    625
  • Thumbnail: Page 
626
    626
  • Thumbnail: Page 
627
    627
  • Thumbnail: Page 
628
    628
  • Thumbnail: Page 
629
    629
  • Thumbnail: Page 
630
    630