AIC comparisons between lmer and glm
I will let the more knowledgeable folks get back address the issues regarding specification of your model structure; but try to give you my thoughts on comparison of AIC or other information criteria for that matter. 1. Yes, the best model is the one with the smallest AIC value; and it is also advisable to check the p values generated when you run the anova command. 2. I don't think you can compare AIC values obtained from lmer and glm; and so the short answer to your question is no. Good luck, Patrick
On Jul 29, 2009, at 12:11 PM, cacabelos at uvigo.es wrote:
Hi R-users, I was unfortunately not able to find a solution to my problem about model selection. I have fixed (e.g. Height) and random (e.g.Time) factors, and I created these kind of model structures: Model1<-lmer(H~Height+(1|Time)+Biomass)+(Biomass| Time),data=dat,family=gaussian) Model2<-glm(H~Height+Biomass,data=dat,family=gaussian) I am using the criterion ?the best model is the one that has the lowest AIC?, but are these AIC from different procedures (i.e. glm and lmer) comparable? I wonder if anyone can help me... Thank you!
_______________________________________________ R-sig-mixed-models at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models