[R-sig-ME] modelling proportions, with aggregated data, and the new/old lme4

Adam Smith raptorbio at hotmail.com
Wed Mar 21 17:10:39 CET 2012


Sorry, the binomial model should have read:

b.glm <- glm(cbind(success,total-success) ~ (a+b+c)^2 - 1, family="binomial", data=test)

But the outcome is little changed...

Adam 
 		 	   		  



More information about the R-sig-mixed-models mailing list