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