Partial Least Squares Structural Equation Modeling: An Emerging Tool in Research

Categories: Quantitative, Tools and Resources


Partial least squares structural equation modeling (PLS-SEM) has recently gained increasing attention in research and practice across various disciplines such as management, marketing, information systems, medicine, engineering, psychology, political and environmental sciences.

PLS-SEM enables researchers to model and estimate complex cause-effects relationship models with both latent (graphically represented as circles) and observed variables (graphically represented as rectangles).

The latent variables embody unobserved (i.e., not directly measurable) phenomena such as perceptions, attitudes, and intentions. The observed variables (e.g., responses on a questionnaire or secondary data) are used to represent the latent variables in a statistical model. PLS-SEM estimates the relationships between the latent variables (i.e., their strengths) and determines how well the model explains the target constructs of interest.

The main reasons for the increasing popularity of PLS-SEM are its capability to estimate very complex models and its relaxed data requirements. The most popular applications are the estimation of technology acceptance models (TAM) and American Customer Satisfaction Index (ACSI) models. Each of these models has been published in thousands of different of studies.

The popularity of PLS-SEM also increased the analytical demands connected with the method. Hence, recent research presented numerous methodological extensions to provide researchers and practitioners with a broad portfolio of technical options to meet their analytical goals. These extensions include, for example, the importance-performance map, mediation, moderation, multi group, latent class segmentation, and predictive analyses.

To get to know the PLS-SEM method, the second edition of A Primer on Partial Least Squares Structural Equation Modeling (PLS-SEM) by Joe Hair, Thomas Hult, Christian Ringle, and Marko Sarstedt, and the Advanced Issues in Partial Least Squares Structural Equation Modeling by Hair, Sarstedt, Ringle, and Siegfried Gudergan, are practical guides that provide researchers with a shortcut to fully understand and competently use the rapidly emerging multivariate PLS-SEM technique.

While the primer offers an introduction to fundamental topics such as establishing, estimating and evaluating PLS path models and some additional topics such as mediation and moderation, the book on advanced issues fully focuses on complementary analyses such as testing nonlinear relationships, latent class segmentation, multigroup analyses, measurement invariance assessment, and higher-order models. Featuring the latest research, new examples analyzed with the SmartPLS 3 software, and expanded discussions throughout, these two books are designed to be easily understood by those want to exploit the analytical opportunities of PLS-SEM in research and practice.

There is also an associated website for the primer available here.

Leave a Reply