[R-sig-ME] Model selection GLM vs. GLMMs

[Ben Bolker]

Nelida Villaseñor <nvillasenor at ...> writes:

> 
> Thanks Ben.
> 
> On: "I think you would find a bit of disagreement among experts about
> the best procedure -- whether it would be to drop random effects until
> you got a sensible non-singular fit, or to keep them in even though
> they're singular"
> 
> Could you please suggest me some references supporting each of these
procedures?
> 
> Cheers,
> Nelida.
> 

  I believe Barr et al (2013) has become the canonical reference
for "put everything in the model".  Doug Bates has mentioned to
me that he was working on a response, with some co-authors,
that disagrees with Barr et al.; perhaps he will chime in on
its status.  I have a book chapter in press
(Fox, G. Negrete-Yankelevich, S. and Sosa, V. (Eds.) Ecological Statistics:
from principles to application. Oxford University Press) that discusses
this issue.  

  Suggestions from the rest of the community are welcome, as always.
 
  Ben Bolker