I have a dataset with four different treatments and two different values for each sample. I need to compare the subsets(the different treatments) somehow. The data look suspiciously much like some kind of e-function to me, or maybe michaelis-menten so they are not linear. With linear models it's straight forward enough but what about nonlinear regressions? With linear model I do: data<-read.csv(file, header=T) attach(data) mod1<-lm(column1~column2) mod2<-lm(column1~column2+treatment) anova(mod1,mod2)
The I can also go on to get the interaction by: mod3<-lm(column1~column2*treatment) But the same kind of methodology does not seem to work for nls functions. How should I do? Can I linearize the data? how to do that in a good way? The best would of course be if I could do it without linearization. Regards Martin ______________________________________________ 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.
