Re: PLS2

From: Agustin Lobo (
Date: Thu Jan 21 1999 - 19:25:13 MET

Thanks, some re-comments:

On Thu, 21 Jan 1999, Jean Thioulouse wrote:

> Agustin Lobo <> wrote:
> >I'm reading the doc for PLSgen2 by Luc Monimeau.
> >Both the explanatory (X) and dependent matrices are
> >20r x 3cols, but then the tk explanatory components are 20 x 4,
> >why do we have one more component than initial variables?
> This is an error in the listing. It has of course only 3 columns.

As they are actually pasting ADE output, could it be that they
switched to a different file and did not notice it?

> No, principal component analysis on intrumental variables and
> PLS regression are two different things. PCAIV is a PCA after
> projection on a subspace. This is the same family of methods
> as CCA (canonical correspondence analysis). PLS regression is
> rather like co-inertia analysis methods.

This is what I thought, but the "fiche" is entitled "Regression PLS de
seconde generation", which confused me. Actually, may be you should
split the "fiche" and start the one on PLS2 at section 3.3 (and rearrange
the sections?)

Just 2 more questions:

1. Could I plot the *_PLS2mod components against the original Y variables
using ADE? (The example in p.11 of the "fiche" seems to imply a 3rd variable
(default=1,2,3,...n). I just want an scatter plot for each
(component,variable) pair.

2. Is there any way to get docs by Tenenhaus (93,95 and 97...)?



This archive was generated by hypermail 2b30 : Sat Feb 10 2001 - 10:35:55 MET