Premium
The O‐PLS methodology for orthogonal signal correction—is it correcting or confusing?
Author(s) -
Indahl Ulf G.
Publication year - 2020
Publication title -
journal of chemometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.47
H-Index - 92
eISSN - 1099-128X
pISSN - 0886-9383
DOI - 10.1002/cem.2884
Subject(s) - chemometrics , orthogonal transformation , computer science , orthographic projection , preprocessor , focus (optics) , contrast (vision) , artificial intelligence , projection (relational algebra) , principal component analysis , similarity (geometry) , latent variable , transformation (genetics) , pattern recognition (psychology) , mathematics , algorithm , machine learning , image (mathematics) , chemistry , physics , optics , biochemistry , gene
The separation of predictive and nonpredictive (or orthogonal) information in linear regression problems is considered to be an important issue in chemometrics. Approaches including net analyte preprocessing methods and various orthogonal signal correction (OSC) methods have been studied in a considerable number of publications. In the present paper, we focus on the simplest single response versions of some of the early OSC approaches including Fearns OSC, the orthogonal projections to latent structures, the target projection (TP), and the projections to latent structures (PLS) postprocessing by similarity transformation. These methods are claimed to yield improved model building and interpretation alternatives compared with ordinary PLS, by filtering “off” the response‐orthogonal parts of the samples in a dataset. We point out at some fundamental misconceptions that were made in the justification of the PLS‐related OSC algorithms and explain the key properties of the resulting modelling.