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.
KeywordsCormack–Jolly–Seber model Mark-recapture analysis Markov chain Monte Carlo Metropolis-Hastings algorithm
- 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
- Cormack RM (1964). Estimates of survival from the sighting of marked animals. Biomatrika 51: 429–438 Google Scholar