[R-sig-ME] Experience with PyMC3 Bambi package?

[Phillip Alday]

I haven't tried Bambi just yet, but the PyMC3 package upon which it is
built has been really quite nice in my experience. The only reason why
I wasn't using PyMC3 more extensively is that it was a pain to
construct the model for complicated GLM(M)s and they only had
convenience functions for constructing non-mixed GLMs.

I will be taking a look soon and will report back!

Best,
Phillip 

On Fri, 2016-09-09 at 13:50 +0000, Douglas Bates wrote:
> Has anyone tried https://github.com/bambinos/bambi for Bayesian
> analysis of
> mixed-effects models?  It looks quite interesting.
> 
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models