Looks like my post might get some problems, so I re-wrote my question plus some
new one...
I noticed that the points on the biplot are not exactly the same as the
predicted values.
Another relevant question: should I expect that all the vector points have the
same length if chose parameters of "cor=T ",
for example, pca2=princomp((data), cor=T)?
Could any body give me a hint about any of these questions?
Thanks.
________________________________
To: Jim Lemon <j...@bitwrit.com.au>
Cc: "r-help@r-project.org" <r-help@r-project.org>
Sent: Tuesday, April 30, 2013 9:51 AM
Subject: Re: [R] biplot for principal componens analysis
very helpful!! Thanks a lot.
________________________________
From: Jim Lemon <j...@bitwrit.com.au>
Cc: "r-help@r-project.org" <r-help@r-project.org>
Sent: Monday, April 29, 2013 6:53 PM
Subject: Re: [R] biplot for principal componens analysis
On 04/30/2013 08:24 AM, capricy gao wrote:
>
>
> I did a PCA for my data which has a dimension of 19000X4 using princomp
>> pca2=princomp((data), cor=F)
>
>
>
>
>
> and obtained a biplot with 19000 labels which were very busy. How can I just
> show 19000 spot w/o labels?
>> biplot(pca2)
>
Hi capricy,
I suppose you could try:
biplot(pca2,xlabs=rep(".",19000))
Jim
[[alternative HTML version
deleted]]
______________________________________________
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.
[[alternative HTML version deleted]]
______________________________________________
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.
