Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
NCTM or The Math Forum.



Re: sampling from a posterior distribution
Posted:
Jan 16, 2013 1:15 PM


On 20130116, majeti dinesh <dinesh.majeti@gmail.com> wrote: > Hi,
> Does anyone know how to sample mean / covariance etc from a posterior distribution? Does anyone know how to use Metropolis algorithm to do this sampling?
A posterior distribution is a distribution. One should sample only if there are no better ways, and there usually are better ways. The Metropolis algorithm is one way of creating samples with the desired limiting distribution, but estimating errors from it can be quite difficult; importance sampling instead is more efficient and is computationally as easy.
 This address is for information only. I do not claim that these views are those of the Statistics Department or of Purdue University. Herman Rubin, Department of Statistics, Purdue University hrubin@stat.purdue.edu Phone: (765)4946054 FAX: (765)4940558



