Advancing family business research through modeling nonlinear relationships: Comparing PLS-SEM and multiple regression

While nonlinear relationships play an important role in explaining distinct family business behaviors and out-comes, researchers rarely consider them in their theoretical and statistical models. To address this concern, this article introduces partial least squares structural equation modeling (PLS-SEM) as a suitable means for estimating nonlinear effects in latent variable models and describes its advantages vis-a-vis multiple (sum scores) regression. We conceptually compare and empirically illustrate the two methods by means of a family business research model. Based on our discussions, we provide family business researchers with a checklist of best practice rec-ommendations when applying PLS-SEM. The article adds new methodological instruments to the family business researchers' toolbox that enable them to explain and explore the mutual and often nonlinear interactions be-tween family and business. Thereby, this research contributes to more rigorous and meaningful family business science.

Automated summary

This article introduces partial least squares structural equation modeling (PLS-SEM) as a suitable tool for estimating nonlinear effects in latent variable models. It compares PLS-SEM with multiple regression and provides family business researchers with best practice recommendations. The research contributes to more rigorous and meaningful family business science by enabling researchers to explain and explore the nonlinear interactions between family and business.