USGS Patuxent Wildlife Research Center Product Abstract
Efficient implementation of the Metropolis-Hastings algorithm, with application to the Cormack–Jolly–Seber model
W. A. Link and R. J. Barker
|
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.
Environmental and Ecological Statistics 15:79–87. 2008
Go to NEW product order form
or use BACK key to return to order form and continue making selections
USGS Patuxent Wildlife Research Center Authors:
William A. Link: E-Mail, Staff Profile
