Dear Alphonse,
You certainly can. But the principal components of (X,Y), say, where X and Y
are uncorrelated, are X and Y themselves if their variances are distinct (if
their variances are equal, principal components are undetermined). Taking
principal components in such case is thus of limited interest.
Marc.
On 25/07/08 15:00, "Alphonse Monkamg" <[log in to unmask]> wrote:
> Dear all,
> PCA is useful if variables involves are highly correlated.
> Does anyone knows whether on can perform PCA with some uncorrelated variables.
> What are some references for that.
>
> Alphonse
>
>
>
>
> _____________________________________________________________________________
> Envoyez avec Yahoo! Mail. Une boite mail plus intelligente
> http://mail.yahoo.fr
_____________________________________________________
Marc Hallin
Université libre de Bruxelles CP 210
Institut de Recherche en Statistique
ECARES
B-1050 Bruxelles
Belgium
_____________________________________________________
Tel +32 2 650 58 86
Fax +32 2 650 58 99
E-mail [log in to unmask]
_____________________________________________________
|