Model choice and squared prediction errors in PLS regression
Authors:
- 16 April 2011
- journal article
- research article
- Published by Wiley in Journal of Chemometrics
- Vol. 25 (6) , 301-312
Abstract
Squared prediction errors (SPE) in are discussed in relation to the conventional PLSR versus bidiagonalization model and algorithm issue concerning residual and prediction consistency, with focus on process monitoring and fault detection. Our analysis leads to the conclusion that conventional PLSR based on the NIPALS algorithm is ambiguous in SPE values caused by process faults. The basic reason for this is that the sample residuals are not found as projections onto the orthogonal complement of the space where the scores and regression solution are located, and where also the statistical limit is defined. The alternative non‐orthogonalized PLSR and bidiagonalization (Bidiag2) algorithms, as well as a simple re‐formulation of the NIPALS algorithm (RE‐PLSR), give unambiguous SPE values, and the last two of these also retain orthogonal score vectors. While prediction results from all of these methods in theory are identical, our conclusion is that methods where the and SPE values for process faults are uncorrelated should be preferred. Tests with added errors on real data do not indicate that this conclusion should be altered because of such errors. Copyright © 2011 John Wiley & Sons, Ltd.Keywords
This publication has 14 references indexed in Scilit:
- A comparison of nine PLS1 algorithmsJournal of Chemometrics, 2009
- The PLS model space: the inconsistency persistsJournal of Chemometrics, 2008
- Re‐interpretation of NIPALS results solves PLSR inconsistency problemJournal of Chemometrics, 2008
- PLS worksJournal of Chemometrics, 2008
- The PLS model space revisitedJournal of Chemometrics, 2008
- The model space in partial least squares regressionJournal of Chemometrics, 2007
- The process chemometrics approach to process monitoring and fault detectionJournal of Process Control, 1996
- Multivariate SPC Methods for Process and Product MonitoringJournal of Quality Technology, 1996
- Analysis of two partial-least-squares algorithms for multivariate calibrationChemometrics and Intelligent Laboratory Systems, 1987
- Calculating the Singular Values and Pseudo-Inverse of a MatrixJournal of the Society for Industrial and Applied Mathematics Series B Numerical Analysis, 1965