Title
A Comparison of Multinomial Likelihood and Chi-Square Approaches to Statistical Population Reconstruction
Department/School
Statistics
Date
2021
Document Type
Article
DOI
https://doi.org/10.1142/S0218339021400106
Abstract
Statistical population reconstruction using age-at-harvest and catch-effort data has recently emerged as a robust and versatile approach to estimating the demographic dynamics of harvested populations of wildlife. Although most reconstruction efforts employ the multinomial likelihood approach to identify which set of model parameters best describes the observed age-at-harvest and catch-effort data, using a χ 2 objective function may provide a suitable alternative with a less steep learning curve. Using a harvested population of North American river otter (Lontra canadensis) in Kentucky as a case study, we investigated the performance of population reconstruction using multinomial likelihood and chi-square formulations. We simulated populations under a range of conditions and found that both the accuracy and precision of reconstruction estimates were similar under the two approaches. These results illustrate the potential benefits of using the χ 2 approach, which may also allow agencies to incorporate auxiliary information from studies for which the corresponding likelihood contributions have yet to be developed.
Volume
29
Issue
2
Published in
Journal of Biological Systems
Citation/Other Information
Berg, S.S. & Palmer, L. (2021). A comparison of multinomial likelihood and chi-square approaches to statistical population reconstruction. Journal of Biological Systems, 29(2), 543-559. https://doi.org/10.1142/S0218339021400106