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


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


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.


Cormack–Jolly–Seber model Mark-recapture analysis Markov chain Monte Carlo Metropolis-Hastings algorithm 

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  1. 1.USGS Patuxent Wildlife Research CenterLaurelUSA
  2. 2.Department of Mathematics and StatisticsUniversity of OtagoDunedinNew Zealand

Personalised recommendations