multiple numerical variables in aov
Prof, It is true that you sent me the email earlier but the way that my email is sorted, Chuck's emails were at the top of my list and hence I read it and responded to it first. With respect to providing me with *all* the info, Chuck did this also although he did so in two differnt emails. He seems to have CCed only one of them two the r-help mailing list though. Finally, my follow up question was about something that was mentioned in Chuck's email but was not in yours. THANK YOU Rishabh
--- Prof Brian Ripley <ripley at stats.ox.ac.uk> wrote: > On Fri, 11 Apr 2003, Rishabh Gupta wrote:
Thanks very much for your help. Just a follow up question..
Although you had been told precisely that earlier, for some reason I don't get any thanks.
Like I said I was using aov() instead of anova(). I want to maintain maximum compatability
with
what I've been using so far and I notice that manova() is just a wrapper to aov().
Notice a bit harder. The `wrapper' changes the class, and summary.manova does all the work.
How important is it to use summary(......, test="Wilks") exactly, do you think that the default test
statistic
would be sufficient.
Sufficient for what? The default test is the default for a good reason.
Once again, many thanks for your help.
Once again, it is not polite to ignore others who give you the same help, especially when it comes from the person who provided you with *all* of this. -- Brian D. Ripley, ripley at stats.ox.ac.uk Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UK Fax: +44 1865 272595