Partial Least Squares Structural Equation Modelling using SMART-PLS4 course

Date(s) - 24/04/2023 - 25/04/2023 9:00 am - 11:00 am


Partial Least Squares Structural Equation Modelling using SMART-PLS4 course with Professor Christian Ringle and Dr Marko Sarstedt

This six-part online course introduces participants to the state-of-the-art of partial least squares structural equation modeling (PLS-SEM; Hair, Hult, Ringle, & Sarstedt, 2022; Hair, Sarstedt, Ringle, & Gudergan, 2018) using the SmartPLS 4 software (Ringle, Wende, & Becker, 2022). The first day of the course provides a profound introduction to PLS-SEM. Participants will learn the foundations of PLS-SEM and how to apply it by means of the SmartPLS 4 software. The course continues with advanced topics including mediation, moderation, higher-order models, and the importance-performance map analysis (IPMA). At the end of the course, a live (online) wrap-up session includes case study exercises, questions and answers, and an outlook on additional advanced topics.

PLS-SEM is a composite-based approach to SEM, which aims at maximizing the explained variance of dependent constructs in the path model. Researchers and practitioners use PLS-SEM especially when they conduct studies on success factors and the sources of competitive advantage.

Compared to other SEM techniques, PLS-SEM allows researchers to estimate very complex models with many constructs and indicator variables. Furthermore, PLS-SEM allows to estimate reflective and formative constructs and generally offers much flexibility in terms of data requirements. The goal of PLS-SEM is the explanation of variances (prediction-oriented character of the methodology) rather than explaining covariances (theory testing via covariance-based SEM, CB-SEM). The application of the PLS-SEM method is of high interest if the assumptions of CB-SEM are violated, and the proposed cause-and-effect relationships are not sufficiently explored. An additional advantage of the PLS-SEM method is the unrestricted inclusion of latent variables in small to very complex path models that draw on either/both reflective or formative measurements models. PLS-SEM has received considerable attention in a variety of disciplines (e.g., Ali, Rasoolimanesh, Sarstedt, Ringle, & Ryu, 2018; Khan et al., 2019; Nitzl & Chin, 2017; Ringle, Sarstedt, Mitchell, & Gudergan, 2020), which resulted in several highly cited publications (e.g., Web of Science).


This online course is designed to look at the stages of research question development and theorizing together with the subsequent methodological implementation using the multivariate analysis method PLS-SEM in business and management research. The learning objectives are to (1) contribute to theory by establishing a useful PLS path model, (2) develop an in-depth methodological appreciation of the PLS-SEM approach (the nature of theoretical modelling, analytical objectives, and related statistics), (3) acquire knowledge to evaluate measurement results, and (4) understand complementary analytical techniques.

Specifically, following the workshop participants will understand the following topics:

  • Model development and fundamentals of PLS-SEM.
  • PLS path model estimation.
  • Assessment and reporting of measurement and structural model results including Bootstrapping.
  • New criteria for model assessment such as HTMT for discriminant validity and goodness of fit (e.g., SRMR).
  • Prediction-oriented results analysis using PLSpredict.
  • Higher-order constructs (e.g., second-order models).
  • Mediating effects.
  • Moderating effects (interaction effects).
  • Importance-performance map analysis (IPMA) of PLS-SEM results.

In addition, the participants will be able to use the SmartPLS 4 software for their PLS-SEM analyses.


  • Begin the self-taught video-based online sessions as soon as possible and finish parts 1 to 5 before April 23
  • The live online sessions will take place on April 24 and 25, from 9-11 am

To register a place on this online course, please complete the following form as soon as possible: