[R] manova: R vs SAS...need some clarification

Prof Brian Ripley ripley at stats.ox.ac.uk
Wed Aug 13 08:20:44 CEST 2008

Please see the footer of this message: we need to know what you did.

Also, SAS may have made some assumptions for you without telling you (for 
example used a numerically ill-conditioned covariance matrix), and we 
don't know what you did in SAS, either.

On Tue, 12 Aug 2008, Pedro Mardones wrote:

> Dear all;
> working with a 'fat' data set (700 variables / 50 samples) and trying
> to run a manova test on it (I'm aware that it's not the best option
> for this kind of data set) I got the error in the summary.manova
> function about the rank of the residuals (rank < # variables). Ok. The
> thing that I don't understand is why I don't get the same type of
> error in SAS. There seems to be no problem with rank deficiency and
> the fit-statistics in SAS (no negative DF or something like that...).
> I'm sure it must be some differences in the way the manova test is
> calculated but I don't know what they are, so I'll appreciate any
> comments...
> Thanks
> PM
> ______________________________________________
> R-help at 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.

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

More information about the R-help mailing list