Problems, Common Beliefs and Procedures on the Use of Partial Least Squares Structural Equation Modeling in Business Research

Abstract

Partial least squares structural equation modeling (commonly referred to as PLS-SEM) was not developed without reason. PLS-SEM was developed as an alternative to covariance-based SEM, allowing researchers to conduct exploratory research. In addition, PLS-SEM is considered capable of providing flexibility related to data characteristics, model complexity, and model specifications. Undoubtedly, PLS-SEM is the most frequently used method in many fields of business research. However, many researchers use PLS-SEM incorrectly and even expect more without understanding the basic structural equation modeling method. For this reason, this article will discuss various types of problems and general beliefs about the use of PLS-SEM in business research. In addition, this article can be used as a reference to make it easier for applied researchers to decide what methods, techniques, and tools will be used to complete their research. In addition, at the end of this article, we will discuss how PLS-SEM can be applied to develop theory in business research through a series of technical introductions taking into account user needs. Subsequently, this article will be equipped with a systematic procedure that discusses the evaluation flow of each PLS-SEM test through illustrations with a notated model using SmartPLS.