Dear All, I met problems when doing contrast and now really need some help in the model below:
Fit=gam(y~treat+SEQUENCE+PERIOD+SEX+s(x),data=dat, random=list(SUBJID=~1),correlation=corAR1(form=~1|SUBJID)) And error message keeps coming out when I want to compare the differences between treatments: Diff=contrast(Fit, list(treat=treatment[-placebo.pos]),list(treat="Placebo"), conf.int=0.9)-- (here placebo.pos=position of "Placebo" in treatment vector) I wonder if the function contrast could be used here? If not, what other options I might have? I hope it's not a stupid questionÂ… Thanks a lot! Xia Li [[alternative HTML version deleted]]
______________________________________________ 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.