Multiple Indicators and Multiple Causes (MIMIC) Models as a Mixed-Modelling Technique: A Tutorial and an Annotated Example
Multiple Indicators and Multiple Causes (MIMIC) Models as a Mixed-Modelling Technique: A Tutorial and an Annotated Example
复制标题
作为混合建模技术的多指标和多原因 (MIMIC) 模型：教程和带注释的示例
DOI：
10.17705/1cais.03611
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
R. Bennett
中科院分区：
文献类型：
--
作者：
Clay Posey;T. Roberts;P. Lowry;R. Bennett
近年来，潜在构式的形成性建模引起了学者们的极大兴趣和讨论。然而，围绕研究人员验证这些模型的能力存在困惑，特别是基于协方差的结构方程建模（CB-SEM）技术。这份手稿有助于澄清这些问题，并解释如何形成建模的结构可以通过研究人员使用CB-SEM能力进行严格的评估。特别是，我们解释并提供了一个称为多指标和多原因（MIMIC）模型的混合建模技术的应用示例。利用这种方法，研究人员可以评估形成建模的结构作为结构模型中的最终、远端因变量，由于CB-SEM的数学识别规则，传统上不可能建模。此外，我们认为研究人员可以使用MIMIC模型来定量地评估一组形成性指标的内容有效性——这通常只从定性的角度来考虑。我们在本文中使用的涉及保护动机行为（PMBs）的研究示例详细介绍了MIMIC建模的整个过程，并为研究人员在开发模拟为MIMIC结构的新结构时提供了一套详细的指导方针。
Formative modelling of latent constructs has produced great interest and discussion among scholars in recent years. However, confusion exists surrounding the ability of researchers to validate these models especially with covariance-based structural equation modelling (CB-SEM) techniques. This manuscript helps to clarify these issues and explains how formatively modelled constructs can be assessed rigorously by researchers using CB-SEM capabilities. In particular, we explain and provide an applied example of a mixed-modelling technique termed multiple indicators and multiple causes (MIMIC) models. Using this approach, researchers can assess formatively modelled constructs as the final, distal dependent variable in structural models, which modelling is traditionally impossible due to the mathematical identification rules of CB-SEM. Moreover, we assert that researchers can use MIMIC models to assess the content validity of a set of formative indicators quantitatively — something considered conventionally only from a qualitative standpoint. Our research example used in this manuscript involving protection-motivated behaviors (PMBs) details the entire process of MIMIC modelling and provides a set of detailed guidelines for researchers to follow when developing new constructs modelled as MIMIC structures.