The present article reviews issues regarding test reliability, which is psychometric terminology, and score reliability, which is score-centric terminology. These issues have arisen, in part, due to some EPM editorial policies and Vacha-Haase’s “reliability generalization” proposal. The article includes (a) a brief historical review of reliability terminology, (b) discussion on the emergence of datametrics (loosely defined as the application of psychometry to scores as opposed to an instrument) including a review of textbook authors’uses of psychometric versus datametric terminology, (c) discussion of problems with datametrics, and (d) a critique of Vacha-Haase’s proposed meta-analytic reliability generalization via dummy-coded regression. The article concludes with a brief summary that presents several suggestions.
No takes yet. Share an insight, caveat, or question.
Shlomo S. Sawilowsky (2000) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: