Representing general theoretical concepts in structural equation models: the role of composite variables
Representing general theoretical concepts in structural equation models: the role of composite variables
复制标题
DOI：
10.1007/s10651-007-0047-7
复制
发表时间：
2008-06-01
影响因子：
3.8
通讯作者：
Bollen, Kenneth A.
中科院分区：
文献类型：
--
作者：
Grace, James B.;Bollen, Kenneth A.
结构方程模型 (SEM) 有望为自然科学家提供评估有关生态系统的复杂多元假设的能力。 SEM 以其前身路径分析和因子分析为基础，允许将观察到的和未观察到的（潜在）变量纳入基于理论的概率模型中。在本文中，我们讨论了 SEM 中理论和数据之间的接口以及附加变量类型（复合变量）的使用。简而言之，复合变量指定了其他变量集合的影响，有助于对生态学家通常感兴趣的异质概念进行建模。虽然复合变量长期以来被认为是 SEM 的潜在重要元素，但其使用非常有限，部分原因是缺乏理论考虑，而且还因为使用传统求解程序时参数估计中出现的困难。在本文中，我们提出了一个讨论复合材料的框架，并演示了使用部分简化形式模型如何帮助克服与包含复合材料的模型相关的一些参数估计和评估问题。生态文献中的一个例子说明了评估复合材料最合适和最有效使用的诊断程序。有人认为，将复合变量纳入结构方程模型的能力在自然系统的研究中可能特别有价值，因为自然系统的概念通常是多方面的，并且变量组的影响往往令人感兴趣。
Structural equation modeling (SEM) holds the promise of providing natural scientists the capacity to evaluate complex multivariate hypotheses about ecological systems. Building on its predecessors, path analysis and factor analysis, SEM allows for the incorporation of both observed and unobserved (latent) variables into theoretically-based probabilistic models. In this paper we discuss the interface between theory and data in SEM and the use of an additional variable type, the composite. In simple terms, composite variables specify the influences of collections of other variables and can be helpful in modeling heterogeneous concepts of the sort commonly of interest to ecologists. While long recognized as a potentially important element of SEM, composite variables have received very limited use, in part because of a lack of theoretical consideration, but also because of difficulties that arise in parameter estimation when using conventional solution procedures. In this paper we present a framework for discussing composites and demonstrate how the use of partially-reduced-form models can help to overcome some of the parameter estimation and evaluation problems associated with models containing composites. Diagnostic procedures for evaluating the most appropriate and effective use of composites are illustrated with an example from the ecological literature. It is argued that an ability to incorporate composite variables into structural equation models may be particularly valuable in the study of natural systems, where concepts are frequently multifaceted and the influence of suites of variables are often of interest.