posterior standard deviation

This forum is closed. You can read the posts but cannot write. We have migrated the forum to a new location where you will have to reset your password.
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.

posterior standard deviation

Postby earsmall » Tue Aug 04, 2015 2:37 pm

One of output resulting from DSGE-estimation is 'oo_' and as far as I know, this variable contains various estimated results.
My question is that whether 'oo_.posterior_std' includes standard deviations of MCMC-simulated draws.
One thing strange is that there is also 'oo_posterior_variance' and I was sure that I could get values in 'oo_.posterior_std'
after imposing square root on them. However, resulting values are little bit different.
Is there any one could explain these outputs?

Thanks.
earsmall
 
Posts: 40
Joined: Mon Jun 15, 2015 3:44 pm

Re: posterior standard deviation

Postby jpfeifer » Wed Aug 05, 2015 6:24 am

This is an unfortunate inconsistency. The
oo_.posterior_std

field is set after mode-finding, i.e. it is the parameter standard deviation at the posterior mode.
The
oo_.posterior_variance

field is set after the MCMC algorithm. That explains why they are not the same. We will fix this in future versions.
------------
Johannes Pfeifer
University of Cologne
https://sites.google.com/site/pfeiferecon/
jpfeifer
 
Posts: 6940
Joined: Sun Feb 21, 2010 4:02 pm
Location: Cologne, Germany


Return to Dynare help

Who is online

Users browsing this forum: Google [Bot] and 7 guests