Department of Mathematics and StatisticsUniversity of Otago
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 modelMark-recapture analysisMarkov chain Monte CarloMetropolis-Hastings algorithm