Representing general theoretical concepts in structural equation models: The role of composite variables

Environmental and Ecological Statistics
By:  and 



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. ?? Springer Science+Business Media, LLC 2007.
Publication type Article
Publication Subtype Journal Article
Title Representing general theoretical concepts in structural equation models: The role of composite variables
Series title Environmental and Ecological Statistics
DOI 10.1007/s10651-007-0047-7
Volume 15
Issue 2
Year Published 2008
Language English
Larger Work Type Article
Larger Work Subtype Journal Article
Larger Work Title Environmental and Ecological Statistics
First page 191
Last page 213
Google Analytic Metrics Metrics page
Additional publication details