Re: PCA Principal component analysis

From: Gottfried Helms <helms@xxxxxxxxxxxxx>
Date: Sat, 02 Jun 2007 14:45:15 +0200

Am 02.06.2007 13:03 schrieb Andersen:

Hello,
I have a few q about PCA.
Why would one NOT want to rotate when using PCA?
Also what happens if the variables are multivariate normal? How will the
components be distributed?

Sincerely

If the unnrotated solutions agrees best with your
theoretical model of factors (expecting one dominant
general factor, second...., third...) ?

Gottfried Helms
.

Follow-Ups:
- Re: PCA Principal component analysis
  - From: Andersen

References:
- PCA Principal component analysis
  - From: Andersen

Prev by Date: Re: finding the centre of a cluster
Next by Date: Need Help With Case In Statistics
Previous by thread: PCA Principal component analysis
Next by thread: Re: PCA Principal component analysis
Index(es):
- Date
- Thread

Relevant Pages

Re: PCA
... Why would one NOT want to rotate when using PCA? ... your primary reason for doing PCA is to find a lower ... Jackson, J.E. "A User's Guide to Principal Components", John ...
(sci.stat.edu)
Re: creating artificial dataset for nonlinear PCA
... Am 17.12.04 23:35 schrieb Tomasz Rogala: ... I think with PCA ... > nonlinear dimensionality reduction techniques. ... Gottfried Helms ...
(sci.math.num-analysis)
Re: PCA allowing bias
... information on the first components? ... Well PCA don't loose any information. ... to maximize variance on the first factor and minimize variance on last factor. ... Gottfried Helms, Kassel ...
(sci.math)