Representing general theoretical concepts in structural equation models: the role of composite variables
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.
KeywordsComposites Constructs Construct models Latent variables Structural equation modeling Theoretical concepts
Unable to display preview. Download preview PDF.
- Blalock HM (1964). Causal inferences in nonexperimental research. University of North Carolina Press, Chapel Hill Google Scholar
- Bollen KA (1989). Structural equations with latent variables. John Wiley & Sons, New York Google Scholar
- Grace JB (2003). Examining the relationship between environmental variables and ordination axes using latent variables and structural equation modeling. Chap 7. In: Pugesek, BH and Tomer, A (eds) Structural equation modeling, pp 171–193. Cambridge University Press, Cambridge Google Scholar
- Grace JB (2006) Structural equation modeling and natural systems. Cambridge University PressGoogle Scholar
- Grace JB, Bollen KA (2006) The interface between theory and data in structural equation models. USGS Open-File Report. Available at www.nwrc.usgs.gov/about/web/j_grace.htm
- Levins R (1968). Evolution in changing environments. Princeton University Press, Princeton Google Scholar
- Muthén LK and Muthén BO (2004). Mplus user’s guide. Muthén and Muthén, Los Angeles Google Scholar
- Pugesek BH, Tomer A and Eye A (2003). Structural equation modeling. Cambridge University Press, Cambridge Google Scholar
- Shipley B (2000). Cause and correlation in biology. Cambridge University Press, Cambridge Google Scholar
- Spirtes P, Glymour C and Scheines R (1993). Causation, prediction, and Search. Springer-Verlag, New York Google Scholar
- Wright S (1921). Correlation and causation. J Agr Res 10: 557–585 Google Scholar
- Wright S (1968). Evolution and the genetics of populations, vol. 1: genetic and biometric foundations. University of Chicago Press, Chicago Google Scholar