Environmental and Ecological Statistics

, Volume 15, Issue 1, pp 79–87 | Cite as

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



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 


  1. Bishop JA, Cook LM and Muggleton J (1978). The response of two species of moths to industrialization in northwest England. II Relative fitness of morphs and populations size. Phil Trans R Soc Lond B 281: 517–540 CrossRefGoogle Scholar
  2. Burnham KP (1991) On a unified theory for release-resampling of animal populations. Proceedings: Taipei symposium in statistics. Institute of Statistical Science, Academia, Sinica. Taiwan, Republic of ChinaGoogle Scholar
  3. Cormack RM (1964). Estimates of survival from the sighting of marked animals. Biomatrika 51: 429–438 Google Scholar
  4. Link WA and Barker RJ (2005). Modeling association among demographic parameters in analysis of open population capture–recapture data. Biometrics 61: 46–54 PubMedCrossRefGoogle Scholar
  5. Jolly GM (1965). Explicit estimates from capture–recapture data with both death and immigration–stochastic model. Biometrika 52: 225–247 PubMedGoogle Scholar
  6. Seber GAF (1965). A note on the multiple–recapture census. Biometrika 52: 249–259 PubMedGoogle Scholar

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