Dear all,
I ran a model with 3 chains and I obtained the following acceptance rates:
Chain 1: 6.8844%
Chain 2: 17.4192%
Chain 3: 28.5928%
Which one should I choose in order to play with mh_scale ?
I mean, if the acceptance rate of the last chain is comprised between 0.33 and 0.25, is it sufficient to conclude that we obtained satisfying acceptance rates ?
Or should all the 3 chain's acceptance rates be comprised between 0.33 and 0.25 in order to conclude that we obtained satisfying acceptance rates ?
Thank you for you answer,
Jonathan
Dynare forums
Forums for asking questions, posting comments and uploading examples related to Dynare
Acceptance rates
Forum rules
This forum is closed. You can read the posts but cannot write. We have migrated the forum to a new location (https://forum.dynare.org) where you will have to reset your password.
This forum is closed. You can read the posts but cannot write. We have migrated the forum to a new location (https://forum.dynare.org) where you will have to reset your password.
2 posts
• Page 1 of 1
Acceptance rates
by jonathanb » Tue Dec 08, 2015 5:38 am
- jonathanb
- Posts: 54
- Joined: Wed Sep 17, 2008 8:52 pm
- Location: New York
Re: Acceptance rates
by jpfeifer » Tue Dec 08, 2015 9:31 am
When your are sampling from the ergodic distribution of the MCMC, the chains should have exactly the same properties. The hugely differing acceptance rates suggest that at least one chain has not properly converged yet. Try a trace_plot to find out which one(s) are affected. If it is only chain one, the scale factor is OK. If it is the other two, you should change it.
- jpfeifer
- Posts: 6940
- Joined: Sun Feb 21, 2010 4:02 pm
- Location: Cologne, Germany
2 posts
• Page 1 of 1
Who is online
Users browsing this forum: No registered users and 8 guests