Changing conceptions of measurement validity

Abstract

This article presents an historical overview of the changes that have occurred during the past 50 years in the theory and estimation of measurement validity. Current views about the meaning of validity, centering on a unified definition of construct validity, are described. Also given are examples of types of validity evidence appropriate for various kinds of inferences to be drawn from scores on measures; included are inferences about the content of a measure, relationships with other variables, differences between groups, the factor structure of a measure, and consequences of its use. Finally, some of the new ways of thinking about the role of reliability are highlighted.