Reliability studies of psychiatric diagnosis. Theory and practice

Abstract

The existing literature on the reliability of psychiatric diagnosis falls into two periods, the earlier reporting low reliability and the latter reporting much higher figures. The reasons for this trend are examined in the context of a discussion of the design of diagnostic reliability studies. The problems of research design and execution in studies of diagnostic reliability are reviewed, and statistical problems are examined. Solutions to many of these problems ae suggested, including recommendations of appropriate reliability coefficients and data analyses.