| varimax rotation [message #18341] |
Tue, 21 December 1999 00:00  |
Terry Haran
Messages: 2
Registered: December 1999
|
Junior Member |
|
|
I'm using IDL 5.2 and the PCOMP function which principal component
analysis. Does anyone know where I can find an IDL-callable library that
would contain a routine to perform a "varimax" (i.e. a maximum variance)
rotation of the principal component vectors returned by PCOMP? Thanks in
advance.
--
Terence (Terry) Haran National Snow & Ice Data Center
tharan@kryos.colorado.edu University of Colorado
voice: 303-492-1847 Campus Box 449
fax: 303-492-2468 Boulder, CO 80309-0449
|
|
|
|
|
|
| Re: Varimax Rotation [message #60387 is a reply to message #18341] |
Tue, 13 May 2008 17:25  |
russell.grew
Messages: 74
Registered: February 2005
|
Member |
|
|
Hi David,
Seems to be gobbled up inside
http://cimss.ssec.wisc.edu/clavr/amato/cloud_climatology/EOF _analysis/isccp_eof.pro
Search the text for 'varimax'
Enjoy.
Russell.
On May 13, 11:57 pm, David Fanning <n...@dfanning.com> wrote:
> Folks,
>
> I made the mistake of becoming somewhat familiar with EOF
> (empirical orthogonal function) analysis recently. As a
> result, I have been asked to investigate the possibility
> of doing "rotated" EOF analysis. In this technique, you
> take a handful of the eigenvectors that come out of the
> EOF analysis, and rotate them in a way that reapportions
> the variance between them. The most popular rotation
> method is called "varimax rotation." This is apparently
> the method used in a Matlab command named roteofs.
>
> Naturally, I am looking for an IDL implementation of
> this technique, if such a thing exists. My math skills
> are improving, but I still appreciate the cheat sheets. :-)
>
> Cheers,
>
> David
> --
> David Fanning, Ph.D.
> Fanning Software Consulting, Inc.
> Coyote's Guide to IDL Programming (www.dfanning.com)
> Sepore ma de ni thui. ("Perhaps thou speakest truth.")
|
|
|
|
comp.lang.idl-pvwave archive
Members
Search
Help
Login
Home
