Applications of Mean and Covariance Structure Analysis: Integrating Correlational and Experimental Approaches
介绍均值和协方差结构（MACS）分析，在一个框架内同时检验个体差异和组均值差异，适合了解验证性因子分析和结构方程模型但未接触均值结构的读者，并提供教程和多种新应用。
This article discusses mean and covariance structure (MACS) analysis as a mechanism for testing individual differences and group mean differences within a single integrated framework. The article is most appropriate for those with a basic understanding of confirmatory factor analysis and structural equation modeling but who have not been introduced to mean structures in either model. The article is both a tutorial and an extension of previous research. It is a tutorial because it introduces the MACS framework using more familiar regression terms, proposes a model-testing framework to be followed, provides numerous illustrations and applications, and discusses both conceptual and programming issues (as well as providing the code for the programming). It is also an extension of previous research because it illustrates several novel applications of MACS to organizational research questions, including how to (a) model mean differences across three independent groups, (b) conduct latent pairwise comparisons, (c) conduct latent contrasts, and (d) analyze repeated measures data. As these examples illustrate, applying MACS more frequently in those organizational research designs that call for it could perhaps improve theory testing by helping to integrate experimental and correlational research methods.