PLS works

In a recent paper, claims were made that most current implementations of PLS provide wrong and misleading residuals [1]. In this paper the relation between PLS and Lanczos bidiagonalization is described and it is shown that there is a good rationale behind current implementations of PLS. Most import...

Full description

Saved in:
Bibliographic Details
Published in:Journal of chemometrics 2009-02, Vol.23 (2), p.69-71
Main Authors: Bro, R., Eldén, L.
Format: Article
Language:English
Subjects:
Algorithms
Forecasting
Lanczos bidiagonalization
MATEMATIK
Mathematical models
MATHEMATICS
Matrix
NIPALS
PLS
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In a recent paper, claims were made that most current implementations of PLS provide wrong and misleading residuals [1]. In this paper the relation between PLS and Lanczos bidiagonalization is described and it is shown that there is a good rationale behind current implementations of PLS. Most importantly, the residuals determined in current implementations of PLS are independent of the scores used for predicting the dependent variable(s). Oppositely, in the newly suggested approach, the residuals are correlated to the scores and hence may be high due to variation that is actually used for predicting. It is concluded that the current practice of calculating residuals be maintained. Copyright © 2008 John Wiley & Sons, Ltd. Claims have been made that most current implementations of PLS provide wrong and misleading residuals. Here, it is shown that there is a good rationale behind current implementations of PLS. In the newly suggested approach, the residuals are correlated to the scores which is different from all common latent variable regression models.
ISSN:0886-9383
1099-128X
1099-128X
DOI:10.1002/cem.1177