Partial Least Squares (PLS) Structural Equation Modeling (SEM) for Building and Testing Behavioral Causal Theory: When to Choose It and How to Use It

IEEE Transactions on Professional Communication, vol. 57(2), pp. 123–146

57 Pages Posted: 19 Mar 2014 Last revised: 8 Jun 2014

See all articles by Paul Benjamin Lowry

Paul Benjamin Lowry

Virginia Polytechnic Institute & State University - Pamplin College of Business

James Gaskin

Brigham Young University - Marriott School; Case Western Reserve University - Department of Information Systems

Date Written: June 01, 2014

Abstract

Problem: Partial Least Squares (PLS), a form of structural equation modeling (SEM), can provide much value for causal inquiry in communication-related and behavioral research fields. Despite the wide availability of technical information on PLS, many behavioral and communication researchers often do not use PLS in situations in which it could provide unique theoretical insights. Moreover, complex models comprising formative (causal) and reflective (consequent) constructs are now common in behavioral research, but they are often mis-specified in statistical models, resulting in erroneous tests. Key concepts: First-generation techniques, such as correlations, regressions, or difference of means tests (e.g., ANOVA or t-tests), offer limited modeling capabilities, particularly in terms of causal modeling. In contrast, second-generation techniques (i.e., covariance-based SEM or PLS) offer extensive, scalable, and flexible causal-modeling capabilities. Second-generation techniques do not invalidate the need for first-generation techniques, however. The key point of second-generation techniques is that they are superior for the complex causal modeling that dominates recent communication and behavioral research. Key lessons: For exploratory work, or for studies that include formative constructs, PLS should be selected. For confirmatory work, either covariance-based SEM or PLS may be used. Despite claims that lower sampling requirements exist for PLS, inadequate sample sizes result in the same problems for either technique. Implications: SEM’s strength is in modeling. In particular, SEM allows for complex models that include latent (unobserved) variables, formative variables, chains of effects (mediation), and multiple group comparisons of these more complex relationships.

Keywords: Theory building; partial least squares (PLS); structural equation modeling (SEM); causal inquiry; first-generation statistical techniques; second-generation statistical techniques

Suggested Citation

Lowry, Paul Benjamin and Gaskin, James, Partial Least Squares (PLS) Structural Equation Modeling (SEM) for Building and Testing Behavioral Causal Theory: When to Choose It and How to Use It (June 01, 2014). IEEE Transactions on Professional Communication, vol. 57(2), pp. 123–146 , Available at SSRN: https://ssrn.com/abstract=2410803

Paul Benjamin Lowry (Contact Author)

Virginia Polytechnic Institute & State University - Pamplin College of Business ( email )

1016 Pamplin Hall
Blacksburg, VA 24061
United States

James Gaskin

Brigham Young University - Marriott School ( email )

United States

Case Western Reserve University - Department of Information Systems ( email )

United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
356
Abstract Views
1,843
rank
98,017
PlumX Metrics