The L-Curve Criterion as a Model Selection Tool in PLS Regression

Partial least squares (PLS) regression is an alternative to the ordinary least squares (OLS) regression, used in the presence of multicollinearity. As with any other modelling method, PLS regression requires a reliable model selection tool. Cross validation (CV) is the most commonly used tool with m...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdelmounaim Kerkri, Jelloul Allal, Zoubir Zarrouk
Format: Article
Language:English
Published: Wiley 2019-01-01
Series:Journal of Probability and Statistics
Online Access:http://dx.doi.org/10.1155/2019/3129769
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850222064065052672
author Abdelmounaim Kerkri
Jelloul Allal
Zoubir Zarrouk
author_facet Abdelmounaim Kerkri
Jelloul Allal
Zoubir Zarrouk
author_sort Abdelmounaim Kerkri
collection DOAJ
description Partial least squares (PLS) regression is an alternative to the ordinary least squares (OLS) regression, used in the presence of multicollinearity. As with any other modelling method, PLS regression requires a reliable model selection tool. Cross validation (CV) is the most commonly used tool with many advantages in both preciseness and accuracy, but it also has some drawbacks; therefore, we will use L-curve criterion as an alternative, given that it takes into consideration the shrinking nature of PLS. A theoretical justification for the use of L-curve criterion is presented as well as an application on both simulated and real data. The application shows how this criterion generally outperforms cross validation and generalized cross validation (GCV) in mean squared prediction error and computational efficiency.
format Article
id doaj-art-6e68e61851ec4bf28a4b9f504b65326b
institution OA Journals
issn 1687-952X
1687-9538
language English
publishDate 2019-01-01
publisher Wiley
record_format Article
series Journal of Probability and Statistics
spelling doaj-art-6e68e61851ec4bf28a4b9f504b65326b2025-08-20T02:06:28ZengWileyJournal of Probability and Statistics1687-952X1687-95382019-01-01201910.1155/2019/31297693129769The L-Curve Criterion as a Model Selection Tool in PLS RegressionAbdelmounaim Kerkri0Jelloul Allal1Zoubir Zarrouk2Laboratory of Stochastic and Deterministic Modelling (LMSD), Department of Mathematics, Faculty of Sciences, University Mohamed the First, Oujda 60000, MoroccoLaboratory of Stochastic and Deterministic Modelling (LMSD), Department of Mathematics, Faculty of Sciences, University Mohamed the First, Oujda 60000, MoroccoLaboratory of Management and Economy of Organizations, Faculty of Social Sciences, University Mohamed the First, Oujda 60000, MoroccoPartial least squares (PLS) regression is an alternative to the ordinary least squares (OLS) regression, used in the presence of multicollinearity. As with any other modelling method, PLS regression requires a reliable model selection tool. Cross validation (CV) is the most commonly used tool with many advantages in both preciseness and accuracy, but it also has some drawbacks; therefore, we will use L-curve criterion as an alternative, given that it takes into consideration the shrinking nature of PLS. A theoretical justification for the use of L-curve criterion is presented as well as an application on both simulated and real data. The application shows how this criterion generally outperforms cross validation and generalized cross validation (GCV) in mean squared prediction error and computational efficiency.http://dx.doi.org/10.1155/2019/3129769
spellingShingle Abdelmounaim Kerkri
Jelloul Allal
Zoubir Zarrouk
The L-Curve Criterion as a Model Selection Tool in PLS Regression
Journal of Probability and Statistics
title The L-Curve Criterion as a Model Selection Tool in PLS Regression
title_full The L-Curve Criterion as a Model Selection Tool in PLS Regression
title_fullStr The L-Curve Criterion as a Model Selection Tool in PLS Regression
title_full_unstemmed The L-Curve Criterion as a Model Selection Tool in PLS Regression
title_short The L-Curve Criterion as a Model Selection Tool in PLS Regression
title_sort l curve criterion as a model selection tool in pls regression
url http://dx.doi.org/10.1155/2019/3129769
work_keys_str_mv AT abdelmounaimkerkri thelcurvecriterionasamodelselectiontoolinplsregression
AT jelloulallal thelcurvecriterionasamodelselectiontoolinplsregression
AT zoubirzarrouk thelcurvecriterionasamodelselectiontoolinplsregression
AT abdelmounaimkerkri lcurvecriterionasamodelselectiontoolinplsregression
AT jelloulallal lcurvecriterionasamodelselectiontoolinplsregression
AT zoubirzarrouk lcurvecriterionasamodelselectiontoolinplsregression