This is discussed for correspondence analysis by Michael Greenacre (1984)
"Theory and applications of correspondence analysis" (something like that).
> From: "Hugo Hidalgo" <[EMAIL PROTECTED]>
> Organization: University of California, Los Angeles
> Newsgroups: sci.stat.edu
> Date: Sat, 14 Apr 2001 16:24:57 -0700
> Subject: Dual Principal Components Analysis
>
>
> Does anybody has any reference to the relationship of the solutions between
> solving a PCA of an X matrix (nxp) and its dual (solving the PCA for the
> transpose of X (pxn))?. The only reference I have so far is Preisendorfer
> (1988), (Sample space vs. state space computation) but it is not a very
> clear reference on the subject.
>
> Thank you in advance.
>
> Hugo
>
>
>
>
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
