Drexel dragonThe Math ForumDonate to the Math Forum



Search All of the Math Forum:

Views expressed in these public forums are not endorsed by Drexel University or The Math Forum.


Math Forum » Discussions » sci.math.* » sci.stat.math.independent

Topic: rjmcmc
Replies: 4   Last Post: Nov 26, 2012 9:57 AM

Advanced Search

Back to Topic List Back to Topic List Jump to Tree View Jump to Tree View   Messages: [ Previous | Next ]
David Jones

Posts: 62
Registered: 2/9/12
Re: rjmcmc
Posted: Nov 24, 2012 3:11 PM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply



"majeti dinesh" wrote in message
news:356ece8f-0b88-4a3d-88d2-b3bd23bab14b@googlegroups.com...

It is a method to samples from a posterior distribution. I am applying it to
a gaussian mixture. I am sampling the mixture parameters and weights and the
number of mixtures using this method. The sampling is done using the
Metropolis method. To accept a move, we need to compute the probability of
accepting it. This value is becoming very large negative value for me.

-----------------------------------------------------------

Given that clue, I found
http://en.wikipedia.org/wiki/Reversible-jump_Markov_chain_Monte_Carlo and
there are many other online pages to be found using an online search. You
might try
http://www1.imperial.ac.uk/resources/8b3cf549-039e-4f96-8bec-cab969a0695c/eph-2005-01.pdf
if you have not seen it, as it discusses some practical issues. Also
www.springerlink.com/index/w72n45j33w754g94.pdf seems on-topic.



Date Subject Author
11/20/12
Read rjmcmc
majeti dinesh
11/21/12
Read Re: rjmcmc
David Jones
11/24/12
Read Re: rjmcmc
majeti dinesh
11/24/12
Read Re: rjmcmc
David Jones
11/26/12
Read Re: rjmcmc
majeti dinesh

Point your RSS reader here for a feed of the latest messages in this topic.

[Privacy Policy] [Terms of Use]

© Drexel University 1994-2014. All Rights Reserved.
The Math Forum is a research and educational enterprise of the Drexel University School of Education.