“Validity”

Validity is defined by Samuel Messick as an integrated, evaluative judgment of the degree to which empirical evidence and theoretical rationales support the adequacy and appropriateness of inferences and actions based on test scores or other modes of assessment. This definition opens Messick’s chapter, “Validity,” in the third edition of Educational Measurement, which is a benchmark publication in the field. Although Messick’s conception of validity has generated some debate, this chapter has arguably provided the dominant scholarly representation of validity in educational measurement since its publication in 1989. Like the validity chapters in the preceding (1950, 1971) and subsequent (2006) editions of Educational Measurement (by Edward E. Cureton, Lee J. Cronbach, and Michael J. Kane, respectively), it is intended to provide guidance to those who develop and use tests or other assessments, as well as philosophical grounding for validity scholars. Key elements in Messick’s representation of validity, which are elaborated in the following discussion, include its tie to scientific hypothesis testing and theory building, the need to address two general threats to validity with two general types of evidence (convergent and discriminant), and the importance of attending to several aspects of validity that illuminate sets of issues and sources of evidence. Issues surrounding Messick’s conception of validity include his incorporation of consequences of testing as an aspect of validity and the extent to which his representation provides sufficient guidance for practitioners. This entry also discusses current issues regarding validity.