[R] EOF and CCA analysis

Prof Brian Ripley ripley at stats.ox.ac.uk
Tue Aug 29 15:22:04 CEST 2006


That's a 10,000 x 120 matrix, if I understand you right.  That is quite 
modest.  The key issue is to be able to do an SVD:

> A <- matrix(rnorm(1e4*120), 1e4, 120)
> dim(A)
[1] 10000   120
> system.time(svd(A))
[1] 2.79 0.13 2.93   NA   NA

on a similar machine to yours, using 50Mb.

It would be worth considering downloading a suitable ATLAS-based 
Rblas.dll if you are doing much of this.


On Tue, 29 Aug 2006, isidora k wrote:

> 
> I have got windows and 1Gb ram. my matrices are
> monthly data for 10 years for sometimes more than
> 10,000 locations. I am going to perform the EOF on one
> variable at a time and then the CCA on the principal
> components that I will get from EOF. Do you think I
> could do that in R?I could also find a macintosh I
> could work with or get more RAM if you think this will
> cause problems, but I am more concerned with the
> software limitations if any!
> thank you so much for your help.
> Kind Regards
> Isidora
> 
> __________________________________________________
> Do You Yahoo!?
> Tired of spam?  Yahoo! Mail has the best spam protection around 
> http://mail.yahoo.com 
> 

-- 
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