On Sun, May 11, 2008 at 07:52:50PM +0100, Federico Calboli wrote: > > The main point of my question is, having a 3 way anova (or ancova, if > you prefer), with *no* nesting, 2 fixed effects and 1 random effect, > why is it so boneheaded difficult to specify a bog standard fully > crossed model? I'm not talking about some rarified esoteric model > here, we're talking about stuff tought in a first year Biology Stats > course here[1].
That may be so, but I've never needed to use one. If it's bog-standard and yet boneheaded difficult, then presumably someone else would have had this problem before you. Perhaps a search of the archives will help? If you try, you will find many qualifiers to the effect that "lme isn't very well set up for crossed random effects". > Now, to avoid any chances of being misunderstood in my use of the > words 'fully crossed model', what I mean is a simple > > y ~ effect1 * effect2 * effect3 > > with effect3 being random (all all the jazz that comes from this > fact). I fully apprecciate that the only reasonable F-tests would be > for effect1, effect2 and effect1:effect2, but there is no way I can > use lme to specify such simple thing without getting the *wrong* > denDF. I need light on this topic and I'd say it's a general enough > question not to need much more handholding than this. Perhaps there are some circumstances unique to your situation. > I fully apprecciate that R is developed for love, not money, ... as is the R-help community ... > and if I > knew how to write an user friendly frontend for nlme and lme4 (and I > knew how to actually get the model I want) I'd be pretty happy to do > so and submit it as a library. In any case, I feel my complaint is > pefectly valid, because specifying such basic model should ideally > not such a chore, and I think the powers that be might actually find > some use from user feedback. This is not feedback. It is a compliant. But, the complaint boils down to the fact that you don't know what you're doing, and you show no evidence of having searched the R-help archives. How is that helpful? > Once I have sorted how to specify such trivial model I'll face the > horror of the nesting, in any case I attach a toy dataset I created > especially to test how to specify the correct model (silly me). Well, these data seem to differ. Is replica block? If not, then how can we reproduce your results? And, if I assume that it is, then the output df differ from what you sent in your original mail. So, I find this confusing. Then, from your original mail, > The easiest model ignores the nested random effects and uses just > selection, males and replica and the relative interactions. The > model > >lme(y ~ selection * males, random = ~1|replica/selection/males, mydata) forgive me, but I seem to see nesting in the random statement. That is what happens when we separate factors with a '/'; they are nested. We would expect that statement to not provide the correct df for the bog-standard fully crossed design. Perhaps if you were to comply with the request at the bottom of each R-help email, and provide commented, minimal, self-contained, reproducible code, that actually ran, ideally with fewer value judgements, you might get more attention from the people who are smarter than you and me, but have less time than either of us. Andrew -- Andrew Robinson Department of Mathematics and Statistics Tel: +61-3-8344-6410 University of Melbourne, VIC 3010 Australia Fax: +61-3-8344-4599 http://www.ms.unimelb.edu.au/~andrewpr http://blogs.mbs.edu/fishing-in-the-bay/ ______________________________________________ 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.