Partial least squares models and their formulations, diagnostics and applications to spectroscopy

Mauricio Huerta, VICTOR ELISEO LEIVA SANCHEZ, Carolina Marchant, Marcelo Rodríguez

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Partial least squares (PLS) models are a multivariate technique developed to solve the problem of multicollinearity and/or high dimensionality related to explanatory variables in multiple linear models. PLS models have been extensively applied assuming normality, but this assumption is not always fulfilled. For example, if the response variable has an asymmetric distribution or it is bounded into an interval, normality is violated. In this work, we present a collection of PLS models and their formulations, diagnostics and applications. Formulations are based on different symmetric, asymmetric and bounded distributions, such as normal, beta and Birnbaum-Saunders. Diagnostics are based on residuals and the Cook and Mahalanobis distances. Applications are provided using real-world spectroscopy data.

Original languageEnglish
Title of host publicationProceedings of the 13th International Conference on Management Science and Engineering Management, 2019 - Volume 1
EditorsJiuping Xu, Gheorghe Duca, Fang Lee Cooke, Syed Ejaz Ahmed
PublisherSpringer Verlag
Pages470-495
Number of pages26
ISBN (Print)9783030212476
DOIs
StatePublished - 1 Jan 2020
Event13th International Conference on Management Science and Engineering Management, ICMSEM 2019 - St. Catharines, Canada
Duration: 5 Aug 20198 Aug 2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1001
ISSN (Print)2194-5357

Conference

Conference13th International Conference on Management Science and Engineering Management, ICMSEM 2019
CountryCanada
CitySt. Catharines
Period5/08/198/08/19

Keywords

  • Cook distance
  • Linear models
  • Mahalanobis distance
  • NIR spectra data
  • Principal component analysis
  • Quantile residuals
  • R software

Fingerprint Dive into the research topics of 'Partial least squares models and their formulations, diagnostics and applications to spectroscopy'. Together they form a unique fingerprint.

Cite this