Group-wise partial least square regression

José Camacho*, Edoardo Saccenti

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)

Abstract

This paper introduces the group-wise partial least squares (GPLS) regression. GPLS is a new sparse PLS technique where the sparsity structure is defined in terms of groups of correlated variables, similarly to what is done in the related group-wise principal component analysis. These groups are found in correlation maps derived from the data to be analyzed. GPLS is especially useful for exploratory data analysis, because suitable values for its metaparameters can be inferred upon visualization of the correlation maps. Following this approach, we show GPLS solves an inherent problem of sparse PLS: its tendency to confound the data structure because of setting its metaparameters using standard approaches for optimizing prediction, like cross-validation. Results are shown for both simulated and experimental data.
Original languageEnglish
Article numbere2964
JournalJournal of Chemometrics
Volume32
Issue number3
Early online date1 Dec 2017
DOIs
Publication statusPublished - Mar 2018

Keywords

  • Exploratory data analysis
  • Group-wise principal component analysis
  • Partial least squares
  • Sparse partial least squares
  • Sparsity

Fingerprint Dive into the research topics of 'Group-wise partial least square regression'. Together they form a unique fingerprint.

  • Projects

    Cite this