Leandre R. Fabrigar

The problem of equivalent models in applications of covariance structure analysis

For any given covariance structure model, there will often be alternative models that are indistinguishable from the original model in terms of goodness of fit to data. The existence of such equivalent models is almost universally ignored in empirical studies. A study of 53 published applications showed that equivalent models exist routinely, often in large numbers. Detailed study of three applications showed that equivalent models may often offer substantively meaningful alternative explanations of data. The importance of the equivalent model phenomenon and recommendations for managing and confronting the problem in practice are discussed.

Handbook of Research Methods in Social and Personality Psychology: Exploring Causal and Noncausal Hypotheses in Nonexperimental Data

This chapter provides an overview of behavioral observation, including the contexts researchers use when observing, the forms in which they record behaviors for analysis (e.g., coding), the methods available to document that different observers coded behaviors similarly (i.e., interrater agreement, an element of reliability), the necessity of establishing other forms of reliability as well as validity, and methods of analyzing behavioral observation data. Observational settings exist along a continuum of researcher influence ranging from unfettered natural environments to tightly controlled experimental situations. Behavioral observation coding systems are of two types: topographical coding systems and dimensional coding systems. The chapter discusses the most common interrater agreement statistics, as well as some useful alternatives. When analyzing behavioral data, one must consider both how the behavior is measured and how often it is measured. The chapter describes recent analytic developments for observational data that will likely be of interest to many social-psychological researchers.