Environmental and Ecological Statistics

, Volume 15, Issue 1, pp 79–87

Efficient implementation of the Metropolis-Hastings algorithm, with application to the Cormack–Jolly–Seber model

Authors

    • USGS Patuxent Wildlife Research Center
  • Richard J. Barker
    • Department of Mathematics and StatisticsUniversity of Otago
Article

DOI: 10.1007/s10651-007-0037-9

Cite this article as:
Link, W.A. & Barker, R.J. Environ Ecol Stat (2008) 15: 79. doi:10.1007/s10651-007-0037-9

Abstract

Judicious choice of candidate generating distributions improves efficiency of the Metropolis-Hastings algorithm. In Bayesian applications, it is sometimes possible to identify an approximation to the target posterior distribution; this approximate posterior distribution is a good choice for candidate generation. These observations are applied to analysis of the Cormack–Jolly–Seber model and its extensions.

Keywords

Cormack–Jolly–Seber modelMark-recapture analysisMarkov chain Monte CarloMetropolis-Hastings algorithm

Copyright information

© Springer Science+Business Media, LLC 2007