In the brms package the function bayes_factor allows you to compare two models. Personally, I prefer the WAIC or LOO methods of comparing, but it is helpful to have both these and bayes factors for those who like bayes factors for these purposes.

I fit my models with the option to save prior samples in order to be able to use the hypothesis function to obtain Savage-Dickey Bayes Factors for point null hypotheses. Because of this attempting to use the bayes_factor function to compare whole models throws the error message " Models including prior samples are not usable in method 'bridge_sampler'."

Is there a way to get rid of the prior samples or make bayes_factor ignore them in order to use this function without having to wait what can sometimes be a very long time to refit my models without the prior samples?

Again, I'm aware of the superiority of WAIC for model comparison, but not everyone I communicate results with feels that way.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.