Re: PCA Principal component analysis

From: Andersen <andersen_800@xxxxxxxxxxx>
Date: Sun, 03 Jun 2007 10:45:51 +0200

Hello, Thank you,
Another add-on, how do I know if the unrotated fits better? Also what happens with the distribution of the components if they are multivariate normal?

Gottfried Helms wrote:

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

References:
- PCA Principal component analysis
  - From: Andersen
- Re: PCA Principal component analysis
  - From: Gottfried Helms

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