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.
Citation Information
| Publication Year | 2008 |
|---|---|
| Title | Efficient implementation of the Metropolis-Hastings algorithm, with application to the Cormack?Jolly?Seber model |
| Authors | W.A. Link, R. J. Barker |
| Publication Type | Article |
| Publication Subtype | Journal Article |
| Series Title | Environmental and Ecological Statistics |
| Index ID | 5224849 |
| Record Source | USGS Publications Warehouse |
| USGS Organization | Patuxent Wildlife Research Center |