[R] PLS regression?

[Ramon Diaz]

Dear Olivier,

This issue has been asked a couple of times on the email list before. I am 
attaching a few messages from previous postings that I have kept around, but 
it might be a good idea to search the archives (I am almost sure there were 
more messages). I also have some R code, which is basically a quick and dirty 
R implementation of the matlab code in the paper by de Jong, Wise, Ricker, 
2001, J. Chemometrics, 15: 85-100, plus a few other things; but there is no 
help, etc, though the code is somewhat commented.


Best,

****************************************************
Re: [R] Partial Least Squares
Date: Mon, 4 Nov 2002 11:39:43 +0100
From: Stephane Dray <dray at biomserv.univ-lyon1.fr>
To: r-help at stat.math.ethz.ch

>Hi everybody!
>

>Is there any package or functions to make Partial Least Squares
>analysis with R?



I don't know.. I have a function to perform NIPALS (Nonlinear 
Iterative Partial Least Squares). This is an alternative for PCA 
based on PLS which can be cery useful in the case of missing values.


Sincerely.



**********************************************
Date: Mon, 04 Nov 2002 10:51:45 +0000
From: Peter Ho <peter at esb.ucp.pt>
To: Luis Silva <lm.silva at sapo.pt>
Cc: R help <r-help at stat.math.ethz.ch>

Luis,


You can find  Ron Wehrens chemometrics toolbox for R at 
http://www-cac.sci.kun.nl/people/rwehrens  
It includes PLS and LDA.


Alternatively, you may be interested in checking out Julian Faraway's 
book Practical regression and ANOVA in R  at
http://www.stat.lsa.umich.edu/~faraway/book/
There is a section on PCR and PLS.


Os melhores cumprimentos,


Peter
----------------------------------------------------------------
Doutor Peter Ho
Departamento de Ciências de Engenharia e Tecnologia
Escola Superior de Tecnologia e Gestão
Instituto Politénico de Viana do Castelo
Avenida do Atlântico- Apartado 574
4901-908 Viana do Castelo
Email: peter at estg.ipvc.pt

****************************************





On Tuesday 14 January 2003 15:31, OTAB (Olivier Taboureau) wrote:
> Hi all,
> I would like to do some QSAR analysis (quantitative structure activity
> relationship). I need to use some Partial Least Squares (PLS) regression,
> but I have not seen this option on the R-project. Is it possible to do this
> kind of regression on R?
> thank you in advance
> best regards,
> olivier
>
> 	[[alternate HTML version deleted]]
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> http://www.stat.math.ethz.ch/mailman/listinfo/r-help

-- 
Ramón Díaz-Uriarte
Bioinformatics Unit
Centro Nacional de Investigaciones Oncológicas (CNIO)
(Spanish National Cancer Center)
Melchor Fernández Almagro, 3
28029 Madrid (Spain)
http://bioinfo.cnio.es/~rdiaz