SMABS 2004 Jena University
SMABS 2004 Home Organization About Jena Sponsors Links Imprint / Contact SMABS Home

European Association of Methodology

Department of methodology and evaluation research

Jena University

Contributions: Abstract

In search of the meaning of method factors in MTMM models

Katrin Kraus Dag Sörbom
Uppsala University
Sweden

During the last years analyzing multitrait multimethod (MTMM) data by Structural Equation Modeling (SEM) has become one of the major parts of research in behavioral sciences. Hence, the idea of including method factors in Structural Equation Models has been well known and widely used among researchers. But in practice there are still some basic problems left. Often, MTMM models are not globally identified and sometimes the method factors may be quite hard to interpret.

Firstly, different models for analyzing multitrait- multimethod data are presented. After describing some of the most common difficulties in identification and interpretation, a model that overcomes some of these problems is introduced.An example is provided and the interpretability of this model is illustrated. Finally, the example data will be analyzed with the different models described. Identification and the interpretation of the method factors will be discussed.

References

Eid, M., Lischetzke, T., Nussbeck, F.W., & Trierweiler, L. (2003). Separating trait effects from trait-specific method effects in multitrait-multimethod models: A multiple-indicator CT-C(M-1) model. Psychological Methods, 8, 38-60.

Kenny, D.A., & Kashy, D.A. (1992). The analysis of the multitrait-multimethod matrix by confirmatory factor analysis. Psychological Bulletin, 112, 165-172.

Marsh, H.W., & Grayson, D. (1995). Latent variable models of multitrait-multimethod data. In R.H. Hoyle (Ed.), Structural equation modelling. Concepts, issues, and applications (pp.177-198). Thousands Oaks, CA: Sage.