search

paul-buerkner / brms

brms R package for Bayesian generalized multivariate non-linear multilevel models using Stan
https://paul-buerkner.github.io/brms/
GNU General Public License v2.0
1.28k stars 184 forks source link

extending pp_average to work with posterior_epred #1022

Closed JakeJing closed 3 years ago

JakeJing commented 4 years ago

I am using pp_average to get the posterior predictive values across different models via Bayesian model stacking. But it seems that pp_average calls posterior_predict by default, which makes it hard to specify other dependent parameters in a distributional model.

It would be better to extend pp_average to work with posterior_epred as well, which will allow, for example, predictions of sigma to be averaged in a normal regression. Thanks!

paul-buerkner commented 3 years ago

I realized this is already possible via the method argument. Just the doc wasn't up to date because it said pp_expect rather than posterior_epred but the latter worked already. Closing this issue.