Representing general theoretical concepts in structural equation models: the role of composite variables |
| |
Authors: | James B Grace Kenneth A Bollen |
| |
Institution: | (1) U.S. Geological Survey, 700 Cajundome Blvd, Lafayette, LA 70506, USA;(2) Department of Sociology, Odum Institute for Research in Social Science, University of North Carolina, CB 3210 Hamilton Hall, Chapel Hill, NC 27599-3210, USA |
| |
Abstract: | 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. |
| |
Keywords: | Composites Constructs Construct models Latent variables Structural equation modeling Theoretical concepts |
本文献已被 SpringerLink 等数据库收录! |
|