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

被引:1
|
作者
Link, William A. [1 ]
Barker, Richard J. [2 ]
机构
[1] USGS Patuxent Wildlife Res Ctr, Laurel, MD 20708 USA
[2] Univ Otago, Dept Math & Stat, Dunedin, New Zealand
关键词
Cormack-Jolly-Seber model; Mark-recapture analysis; Markov chain Monte Carlo; Metropolis-Hastings algorithm;
D O I
10.1007/s10651-007-0037-9
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
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.
引用
收藏
页码:79 / 87
页数:9
相关论文
共 50 条