When, Why, and How can we apply Partial Least Squares – Structural Equation Modeling (PLS-SEM) in academic research?
SEM is a statistical approach to analyze a hypothetical framework simultaneously. It allows a researcher to test and develop theories, and to test the relationships between latent variables on the conceptual model. There are two types of SEM; the covariance-based technique (CB-SEM) and the variance-based or partial least squares SEM (PLS-SEM). CB-SEM is confirmatory in nature, whereas PLS-SEM can handle theory development and prediction. The PLS-SEM is a variance-based approach and aims to maximize the explained variance of the dependent latent constructs; whereas the CB-SEM aims to reproduce the theoretical covariance matrix. Therefore the PLS-SEM is preferred when the researcher want to predict the construct and identify relationship between them. In addition, PLS-SEM can handle more complex model including formative, composite and reflective constructs. PLS-SEM has been applied in many studies in marketing, business, strategic management, and social science areas in recent years. Therefore, the objective of this talk is to discuss briefly:
- For what type of research can we apply PLS-SEM?
- How to justify the application of PLS-SEM?
- How to perform PLS-SEM?
- How to report the results using PLS-SEM in a rigorous way?
