justin bem <justin_bem <at> yahoo.fr> writes: > I want to estimate a nonlinear mixed effect model using nlme package or lme4. How can I specify this > > y=exp(B'X)/(1+exp(B'X)). the same model can be obtained with logit(y)=B'X but I have many value of 1 in y logit(1)=Inf.
Using exp in this case is a fairly common approach, and there are some examples in the Pinheiro/Bates Book, chapter 8.2 (look for orange tree); or, if you do not have access to it, look at ch08.r in library/nlme/scripts Dieter ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
