Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

On the reliability of N‐mixture models for count data

On the reliability of N‐mixture models for count data IntroductionStrategies for inference about abundance N from count data under imperfect detection include: (i) capture–recapture modeling in which auxiliary data supplement the counts in order to allow direct inference about detection rates p; (ii) N‐mixture modelling in which no such auxiliary data are collected but instead the model is structured in order to allow inference about N and p (which is assumed constant after controlling for covariates, hereafter, “constant p”); or (iii) index models in which inference is made about relative abundance assuming constant p.N‐mixture models were developed by Royle () as an alternative to estimating abundance using tools such as capture–recapture that can be difficult, expensive, and impractical (Royle, ; Dennis et al., ). They are popular among field biologists and the original model of Royle () has been extended, for example, to model zero‐inflation, extra‐Poisson variation in abundance, and to relax the assumption of population closure between visits (see Dénes et al., , for a recent review).The idea that we can estimate both N and p without marking animals seems appealing. However, this economy of field effort imposes a cost on the analysis. Recaptures of marked animals provide auxiliary data for estimation of p; we can model http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Biometrics Wiley

On the reliability of N‐mixture models for count data

Download PDF
9 pages

Loading next page...
 
/lp/wiley/on-the-reliability-of-n-mixture-models-for-count-data-QJCRHhBkg8

References (20)

Publisher
Wiley
Copyright
© 2018, The International Biometric Society
ISSN
0006-341X
eISSN
1541-0420
DOI
10.1111/biom.12734
Publisher site
See Article on Publisher Site

Abstract

IntroductionStrategies for inference about abundance N from count data under imperfect detection include: (i) capture–recapture modeling in which auxiliary data supplement the counts in order to allow direct inference about detection rates p; (ii) N‐mixture modelling in which no such auxiliary data are collected but instead the model is structured in order to allow inference about N and p (which is assumed constant after controlling for covariates, hereafter, “constant p”); or (iii) index models in which inference is made about relative abundance assuming constant p.N‐mixture models were developed by Royle () as an alternative to estimating abundance using tools such as capture–recapture that can be difficult, expensive, and impractical (Royle, ; Dennis et al., ). They are popular among field biologists and the original model of Royle () has been extended, for example, to model zero‐inflation, extra‐Poisson variation in abundance, and to relax the assumption of population closure between visits (see Dénes et al., , for a recent review).The idea that we can estimate both N and p without marking animals seems appealing. However, this economy of field effort imposes a cost on the analysis. Recaptures of marked animals provide auxiliary data for estimation of p; we can model

Journal

Biometrics – Wiley

Published: Jan 1, 2018

Keywords: ; ; ; ;

There are no references for this article.