Professor Filzmoser.
Thank you so much for the detailed response. It is very helpful.
-- TMK --
212-460-5430home
917-656-5351cell
>From: Peter Filzmoser <[EMAIL PROTECTED]>
>To: Talbot Katz <[EMAIL PROTECTED]>
>CC: r-help@stat.math.ethz.ch
>Subject: Re: Questions about results from P
Hi,
PCAproj is mainly designed for robust PCA and not for classical PCA.
Therefore, when applying classical estimators to the results of a
robust PCA, like the mean to the robust PCA scores, this will usually
not give zeros. The robust PCs have been centred robustly, and
not classically by the mea
Hi.
I have been looking at the PCAproj function in package pcaPP (R 2.4.1) for
robust principal components, and I'm trying to interpret the results. I
started with a data matrix of dimensions RxC (R is the number of rows /
observations, C the number of columns / variables). PCAproj returns a