[R] PCA

Pedro Mardones mardones.p at gmail.com
Thu Nov 6 23:37:46 CET 2008


try prcomp instead of princomp

On Thu, Nov 6, 2008 at 3:20 PM, Lucke, Joseph F
<Joseph.F.Lucke at uth.tmc.edu> wrote:
> Neola
> I'm a bit rusty on this, but I believe you can conduct on singular-value decomposition on the 436 by 518 matrix.  The squares of your singular values (max of 436, 518-436 will be zero) will be your eigenvalues, the same as in the PC analysis.  The post-eigenvectors will be your components.  As I have said, my knowledge is not completely trustworthy at this point, but SVD would be worth looking into.
> Joe
>
> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On Behalf Of Noela Sánchez
> Sent: Thursday, November 06, 2008 1:10 PM
> To: stephen sefick
> Cc: r-help at r-project.org
> Subject: Re: [R] PCA
>
> My matrix have 436 registers and 518 variables. I need to do a PCA analyst.
>
> Usually I use princomp command to perform PCA analyst, but this time i can't because of my variables are more than my registers.
>
> 2008/11/6 stephen sefick <ssefick at gmail.com>
>
>> would you please provide a dummy example that explains your problem.
>> Then maybe I can help you.
>> thanks
>>
>> Stephen
>>
>> On Thu, Nov 6, 2008 at 1:42 PM, Noela Sánchez <noesanchez at udc.es> wrote:
>> > I need perform PCA analyst with a matrix with more variables than units.
>> >
>> > The princomp command don't match with this matrix.
>> >
>> > Anybody knows a good command to do it?
>> >
>> > --
>> > Noela
>> >
>> >        [[alternative HTML version deleted]]
>> >
>> > ______________________________________________
>> > 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<http://www.r-project.org/p
>> osting-guide.html>
>> > and provide commented, minimal, self-contained, reproducible code.
>> >
>>
>>
>>
>> --
>> Stephen Sefick
>> Research Scientist
>> Southeastern Natural Sciences Academy
>>
>> Let's not spend our time and resources thinking about things that are
>> so little or so large that all they really do for us is puff us up and
>> make us feel like gods.  We are mammals, and have not exhausted the
>> annoying little problems of being mammals.
>>
>>                                                                -K.
>> Mullis
>>
>
>
>
> --
> Noela
> Grupo de Recursos Marinos y Pesquerías
> Universidad de A Coruña
>
>        [[alternative HTML version deleted]]
>
> ______________________________________________
> 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.
>


More information about the R-help mailing list