Skip to main content
U.S. flag

An official website of the United States government

The Interface Between Theory and Data in Structural Equation Models

January 1, 2006

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, for representing general concepts. In simple terms, composite variables specify the influences of collections of other variables and can be helpful in modeling general relationships 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 influences of suites of variables are often of interest.

Publication Year 2006
Title The Interface Between Theory and Data in Structural Equation Models
DOI 10.3133/ofr20061363
Authors James B. Grace, Kenneth A. Bollen
Publication Type Report
Publication Subtype USGS Numbered Series
Series Title Open-File Report
Series Number 2006-1363
Index ID ofr20061363
Record Source USGS Publications Warehouse