4 Reliability Coefficients and Generalizability Theory

Abstract

Publisher Summary This chapter discusses reliability coefficients as developed in the framework of the classical test theory (CTT) and describes the way the conception and estimation of reliability has been broadened in generalizability theory (G). It also discusses the foundations of CTT and focuses on the traditional methods of estimating reliability. It reviews generalizability theory, its applications, and recent theoretical contributions. In addition to computational procedures, G theory provides a conceptual framework and notational system for characterizing alternative intended universes of generalization, distinguishing fixed versus random facets, and designing efficient measurement procedures. G theory has also clarified the use and interpretation of coefficients and estimated standard errors from CTT. This is of value because, despite the greater sophistication of G theory and the important applications, CTT remains the dominant tool for estimating reliability. However, reliability is just one consideration in the responsible use and interpretation of tests, and not the most important consideration.