I have some trouble with mixed effects in R, similar to problems that other people had with not nested models and lme, as I understand from the mailing list archive. Unfortunately, I could not understand the solutions that were proposed...
I have a data set with response variable (y) and two explanatory variables x1 and x2 (x1 - fixed factor, x2 - random factor). Fixed factor x1 is repeated twice for each x2 value.
I believe that the correct way to fit a mixed model would be
ddd <- groupedData(y ~ x1 | x2, dd) l1 <- lme(y ~ x1, random = pdBlocked(list(pdIdent(~x2-1))), data = ddd)
But I get an error Error in pdConstruct.pdBlocked(object, form = form, nam = nam, data = data, : None of the arguments specify more than one block
I would also have to test for significance of each variable (x1 and x2) and the way to do this seem to be to fit a model without x1 and compare it to the original l1 model (and then the same for x2), but I can't seem to find a way to do this.
Thanks a lot.
______________________________________________ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
