Sequential and orthogonalized PLS (SO‐PLS) regression for path analysis: Order of blocks and relations between effects. (4th May 2020)

• Record Type: Journal Article
• Authors: Næs, Tormod; Romano, Rosaria; Tomic, Oliver; Måge, Ingrid; Smilde, Age; Liland, Kristian H.
• Is Part Of: Journal of chemometrics. Volume 35:Number 10(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-05-04
• Subjects: common components -- graphical modelling -- path analysis -- SEM -- SO‐PLS; Chemistry -- Mathematics -- Periodicals; Chemistry -- Statistical methods -- Periodicals; 542.85
• DOI: 10.1002/cem.3243
• Languages: English
• ISSNs: 0886-9383

Abstract

Abstract: This paper is about the use of the multiblock regression method sequential and orthogonalized partial least squares (SO‐PLS) for path modeling. The paper is a follow up of previously published papers on the same topic and presents a number of new results for the method. First of all, the paper discusses more thoroughly the aspect of how to incorporate blocks in the models and relates this to standard concepts in the area of graphical modeling. Second, the paper defines the concept of direct and indirect effects more precisely in terms of population parameters and shows how they are related to the additional effect in SO‐PLS modeling. The paper illustrates the theory by simple graphs, simulations, and a real example from process monitoring. Abstract : In Section 2 we describe basic concepts in graphical modelling and in Section 4 we show how these concepts are linked to SO‐ PLS, which is described in Section 3. Section 5 is devoted to direct and additional effects and in Sections 7 and 8 are presented two examples, one simulated and one from process modelling.