liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Fast and stable partial least squares modelling: A benchmark study with theoretical comments
Linköping University, Department of Mathematics, Computational Mathematics. Linköping University, Faculty of Science & Engineering.
Norwegian University of Life Science, Norway.
2017 (English)In: Journal of Chemometrics, ISSN 0886-9383, E-ISSN 1099-128X, Vol. 31, no 8, article id e2898Article in journal (Refereed) Published
Abstract [en]

Algorithms for partial least squares (PLS) modelling are placed into a sound theoretical context focusing on numerical precision and computational efficiency. NIPALS and other PLS algorithms that perform deflation steps of the predictors (X) may be slow or even computationally infeasible for sparse and/or large-scale data sets. As alternatives, we develop new versions of the Bidiag1 and Bidiag2 algorithms. These include full reorthogonalization of both score and loading vectors, which we consider to be both necessary and sufficient for numerical precision. Using a collection of benchmark data sets, these 2 new algorithms are compared to the NIPALS PLS and 4 other PLS algorithms acknowledged in the chemometrics literature. The provably stable Householder algorithm for PLS regression is taken as the reference method for numerical precision. Our conclusion is that our new Bidiag1 and Bidiag2 algorithms are themethods of choice for problems where both efficiency and numerical precision are important. When efficiency is not urgent, the NIPALS PLS and the Householder PLS are also good choices. The benchmark study shows that SIMPLS gives poor numerical precision even for a small number of factors. Further, the nonorthogonal scores PLS, direct scores PLS, and the improved kernel PLS are demonstrated to be numerically less stable than the best algorithms. PrototypeMATLAB codes are included for the 5 PLS algorithms concluded to be numerically stable on our benchmark data sets. Other aspects of PLS modelling, such as the evaluation of the regression coefficients, are also analyzed using techniques from numerical linear algebra.

Place, publisher, year, edition, pages
WILEY , 2017. Vol. 31, no 8, article id e2898
Keywords [en]
Bidiag1; Bidiag2; bidiagonalization; deflation; Golub-Kahan Householder; Lanczos process; NIPALS; PLS; regression; reorthogonalization; stability
National Category
Pharmaceutical Sciences
Identifiers
URN: urn:nbn:se:liu:diva-140970DOI: 10.1002/cem.2898ISI: 000409047800001OAI: oai:DiVA.org:liu-140970DiVA, id: diva2:1142315
Note

Funding Agencies|Research Council of Norway [239070]

Available from: 2017-09-19 Created: 2017-09-19 Last updated: 2018-01-13

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Search in DiVA

By author/editor
Björck, Åke
By organisation
Computational MathematicsFaculty of Science & Engineering
In the same journal
Journal of Chemometrics
Pharmaceutical Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 34 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf