top banner top banner
index
RegularArticles
ReplicationStudies
EditorialBoard
Instructions4Authors
JournalGuidelines
Messages
Submission

Search publications

Partial least squares regression in the social sciences

Full text PDF
Bibliographic information: BibTEX format RIS format XML format APA style
Cited references information: BibTEX format APA style
Doi: 10.20982/tqmp.11.2.p052

Sawatsky, Megan L. , Clyde, Matthew , Meek, Fiona
52-62
Keywords: Partial least squares regression , latent variable , extraction method
Tools: JMP, SAS
(no sample data)   (no appendix)

Partial least square regression (PLSR) is a statistical modeling technique that extracts latent factors to explain both predictor and response variation. PLSR is particularly useful as a data exploration technique because it is highly flexible (e.g., there are few assumptions, variables can be highly collinear). While gaining importance across a diverse number of fields, its application in the social sciences has been limited. Here, we provide a brief introduction to PLSR, directed towards a novice audience with limited exposure to the technique; demonstrate its utility as an alternative to more classic approaches (multiple linear regression, principal component regression); and apply the technique to a hypothetical dataset using JMP statistical software (with references to SAS software).


Pages © TQMP;
Template last modified: 2017-27-09.
Page consulted on .
Be informed of the upcoming issues with RSS feed: RSS icon RSS