Someone has asked me how to go about analysing the following study. I think maybe nlme is appropriate, though I have never used it and know little about it. Each subject has either unilateral or bilateral case of disease under study. Subjects are randomly assigned to treatments A or B. The subjects are given 6 tests. One of these dependent measures is a 4 point categorical scale; the rest are continuous. These measures are taken repeatedly: Baseline measurement before treatment Follow up 1, 3 months after treatment Follow up 2, 6 months after treatment Follow up 3, 9 months after treatment Follow up 4, 12 months after treatment Follow up 5, 18 months after treatment Follow up 6, 24 months after treatment Follow up 7, 36 months after treatment I have never done an analysis of an expt like this, so any advice is welcome. Naively it looks like one wants something like a regression of each measure against time (there will be 6, one for each DV), and one would hope that the slope of the functions obtained in groups A and B is different. That would show that one treatment slows the progression of the disease relative to the other treatment. The fancy part is that these regressions are time series and so the autocorrelated errors must be taken into account... Is nlme a good tool for analysing this sort of thing? If so, how to do it? Thanks very much for any help. Bill Simpson -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._