Multigroup analysis of more than two groups in PLS-SEM: A review, illustration, and recommendations
综述了PLS-SEM中超过两组的多元组分析应用，指出常见问题如混淆总体差异检验与非参数距离检验、忽视族系误差和测量不变性，并通过实证示例提供实用指南。
Multigroup analysis (MGA) in partial least squares structural equation modeling (PLS-SEM) has grown considerably in the past few years in many different research fields, particularly in the business area. However, a close examination of MGA in PLS-SEM articles revealed much less research that compared more than two groups. Furthermore, research applying MGA in PLS-SEM with more than two groups has several constraints. For instance, most researchers need clarification about using either the omnibus test of group differences (OTG) or non-parametric distance-based tests (NDT) for an overall difference across the groups. Moreover, they do not handle family-wise error when comparing more than two groups, nor do they check for measurement invariance. This article uses an empirical illustration to fully understand multigroup analysis with more than two groups, providing valuable guidelines and comprehensible recommendations for researchers applying PLS-MGA.