Hello,
I've checked the archives and apparently model averaging is very difficult
in WinBUGS. However, my situation is pretty simple. I have two different
regression models on the same set of data. In one model the response is
transformed, and in the other it's not. I'd like to set the prior
probability on each model to .5, and then obtain the posterior probabilities
for the models. I could do this 'by hand' if I could obtain the values
integral(f_1(x) pi_1(tau))d(tau) and integral(f_2(x) pi_2(theta))d(theta)
for the two different models. Is there any way to get the normalization
constants out of WinBUGS? It must be calculated in there somewhere.
Also: How is the response transformation accounted for? Do I need to create
a new prior distribution on the parameters, or is there some coding trick
that will allow me to get the likelihood functions on the same scale?
Thanks for any advice on this.
Paul Louisell
Statistician
Pratt & Whitney
TechNet: 435-5417
[log in to unmask]
-------------------------------------------------------------------
This list is for discussion of modelling issues and the BUGS software.
For help with crashes and error messages, first mail [log in to unmask]
To mail the BUGS list, mail to [log in to unmask]
Before mailing, please check the archive at www.jiscmail.ac.uk/lists/bugs.html
Please do not mail attachments to the list.
To leave the BUGS list, send LEAVE BUGS to [log in to unmask]
If this fails, mail [log in to unmask], NOT the whole list
|