topic Re: Overall log likelihood of a hierarchical bayes model in Statistical Procedures

Overall log likelihood of a hierarchical bayes model

ahoeweler — Sat, 22 Oct 2016 14:47:00 GMT

Hi everyone,

I want to compare the overall if of an MNL model, a fixed effects Bayes model and a random-effects hierarchical Bayes model. The log likelihood measure seems to be most appropirate for that, however how do I calculate the overall log likelihood for the HB model in the PROC BCHOICE procedure?

Thank you for your help.

Best,

Alex

Re: Overall log likelihood of a hierarchical bayes model

Damien_Mather — Fri, 09 Dec 2016 03:08:19 GMT

you could try holding all parameter estimates to the values you estimate using the 3 model frameworks in a framework that can nest all 3 specifications and outputs a true (not psuedo) likelihood. Maybe proc glimmix with method=laplace might work, depending on your original procedures.