Comments on the article “Marketing or methodology? Exposing the fallacies of PLS with simple demonstrations” and PLS-SEM in general
本文讨论了PLS-SEM的优缺点，包括偏差、一致性、R²最大化、信度和模型验证，并比较了其与协方差结构方程模型的优劣，适合研究方法论学者参考。
Purpose The purpose of this paper is to discuss the pros and cons of partial least squares approach to structural equation modeling (PLS-SEM). The topics include bias, consistency, maximization of R 2 , reliability and model validation. Design/methodology/approach The approach in this study is descriptive, and the method consists of logical arguments and analysis that are supported by results in references. Findings Several optimal properties of the PLS-SEM methodology are clarified. A proposal for transforming PLS-SEM mode A to mode B is highlighted, and the transformed mode possesses the desired properties of both modes A and B. Issues with the application of regression analysis using composite scores are also discussed. The strength of PLS-SEM is also compared against that of covariance-based SEM. Research limitations/implications Additional studies on PLS-SEM are needed when the population structure contains cross-loadings and/or correlated errors. Practical implications PLS-SEM may have inflated type I errors and R 2 values even with normally distributed data. Originality/value The content of this paper is new, and there does not exist such an in-depth discussion of the pros and cons of PLS-SEM methodology in the literature.