Executing and interpreting applications of PLS-SEM: Updates for family business researchers

• Published in: Journal of family business strategy Vol. 12; no. 3; p. 100392
• Main Authors: Hair, Joseph F., Astrachan, Claudia Binz, Moisescu, Ovidiu I., Radomir, Lăcrămioara, Sarstedt, Marko, Vaithilingam, Santha, Ringle, Christian M.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.09.2021
• Subjects: Discrete choice modeling; Endogeneity; Model selection; Out-of-sample prediction; Partial least squares; PLS-SEM; PLSpredict; Structural equation modeling; Structural equation modeling; PLSpredict; Model selection; Discrete choice modeling; Out-of-sample prediction; Endogeneity; Partial least squares; PLS-SEM
• ISSN: 1877-8585; 1877-8593
• DOI: 10.1016/j.jfbs.2020.100392

•PLS-SEM has become a standard tool in family business research.•Methodological research has developed new model evaluation methods and metrics.•Recent extensions strengthen the method’s predictive capabilities.•Highlights state-of-the-art in PLS-SEM use.•Guidance for family business researchers for using new evaluation methods and metrics. The use of partial least squares structural equation modeling (PLS-SEM) has been gaining momentum in family business research. Since the publication of a PLS-SEM guidelines article in the Journal of Family Business Strategy’s special issue on “Innovative and Established Research Methods in Family Business” in 2014, methodological research has developed new model evaluation methods and metrics and sharpened our understanding of the method’s strengths and limitations. In light of these developments, we extend prior guidelines on PLS-SEM applications by discussing new model evaluation procedures (e.g., model selection) and metrics (e.g., PLSpredict). In addition, we highlight the usefulness of methodological extensions for discrete choice modeling and endogeneity assessment that considerably extend the scope of the PLS-SEM method, and emerging opportunities for the application of PLS-SEM with archival (secondary) data. PLS-SEM remains a valuable method in the context of family business research, especially when it comes to gaining a more sophisticated understanding of the drivers of family business behavior. Because of its properties, the PLS-SEM approach proves particularly valuable when the aim is to predict target variables (e.g., family firm performance) in the context of a causal model.