[R-sig-ME] lme4, glmmPQL and calculating QAICc

[Gosselin Frederic]

Dear colleagues,

the problem you mention is close to the one I posted here: http://markmail.org/message/s4abxhhdacqjkunm. In other words, quasi-likelihood within glmer might be problematic for the lattest versions of R and not in older versions... This is my provisional conclusion.

Sincerely,

Frédéric Gosselin 
Engineer & Researcher (PhD) in Forest Ecology 
Cemagref 
Domaine des Barres 
F-45290 Nogent sur Vernisson 
France 

http://www.cemagref.fr/les-contacts/les-pages-personnelles-professionnelles/gosselin-frederic/english-short-scientific-cv