|
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).
|