header image
Home arrow Tutorial arrow PLS Regression and the Covariance
PLS Regression and the Covariance PDF Print E-mail
Written by Agnar Höskuldsson, DTU   
The PLS regression is characterized by finding a score vector in X and a score vector in Y that provide with maximal covariance. In the analysis of data the results of this optimization task should be reported. Here it is shown how this should be done. It is also illustrated how this can provide with useful information on the modeling task.


Download this tutorial (pdf)
< Prev   Next >
Search website

Editorial flash
PLS vs canonical correlation and relation to the O2PLS method

I have compiled a few obvious differences between PLS2 and canonical correlation below . In addition, I also describe their relation to a recent development of the OPLS method called O2PLS.
Read more...
News flash
SSC11, Loen, Nordfjord, NORWAY, June 8-11, 2009

Fellow chemometricians,
On behalf of the organizers, it is my pleasure to invite you to the 11th Scandinavian Symposium on Chemometrics:
http://www.kj.uib.no/ssc11

The program is finalized, but we still accept some late poster contributions.We have approx. 100 excellent contributions for the conference and also three high-quality pre-conference courses.
Read more...
Tutorial flash
Multivariate Solutions to Metabonomic Profiling and Functional Genomics, Part 1
Metabonomics, defined as a systems approach to investigating the metabolic consequences of (patho)physiological or genetic modification in a multivariate and dynamic manner, has evolved from the work of Nicholson and co-workers using high field NMR spectroscopic analysis of biological matrices as the dominant analytical platform.
A link (pdf) will be added during September 2006 to the full tutorial
Read more...