Design and analysis of reliability studies

Abstract

This review covers the design and analysis of essentially two types of reliability study: method comparison studies and generalizability (including inter-rater reliability) experiments. Likelihood-based methods of inference (confirmatory factor analysis and REML estimation of variance components, for example) are advocated, partly because of their ease of use but, primarily as a stimulus to the use of more ambitious designs for the investigation of the quality of measurements. The more sophisticated approaches are not intended to replace the simpler traditional methods, however, but are expected to be used to supplement them.