[R] PCA - princomp can only be used with more units than variables

Prof Brian Ripley ripley at stats.ox.ac.uk
Sat Mar 26 16:00:04 CET 2005


On Sat, 26 Mar 2005, Srinivas Iyyer wrote:

> Hi all:
> I am trying to do PCA on the following matrix.
>
>
>            N1     N2    A1      A2     B1     B2
> gene_a      90    110    190    210    290    310
> gene_b     190    210    390    410    590    610
> gene_c      90    110    110     90    120     80
> gene_d     200    100    400     90    600    200
>
>
>> dataf<-read.table("matrix")
>
>> pca<-princomp(dataf,cor=TRUE,scores=TRUE)
> Error in princomp.default(dataf, cor = TRUE, scores =
> TRUE) :
>        princomp can only be used with more units than
> variables
>
>
> Can any one help me, whats wrong here.

What is wrong is that you failed to read the help page before posting as 
the posting guide asks you to.  The explanation *IS* on the help page.
Please don't expect a help list to read the help for you.

-- 
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