Construct validity

Construct validity is the degree to which evidence supports interpreting a measure as representing its intended theoretical construct. It concerns the interpretation and use of scores, not a fixed property of a test.

Psychological construct: A theoretical attribute, such as anxiety or intelligence, inferred from patterns of behavior or responses. Construct validity asks whether measured scores adequately represent such an inferred attribute.
Content validity: Evidence that a measure's content adequately represents the domain it is intended to cover. Coverage of relevant content supports the interpretation that scores represent the intended construct.
Criterion validity: Evidence that scores relate to an external outcome or criterion in an expected way. Associations with relevant outcomes can support a construct-based interpretation for practical decisions.
Face validity: The apparent plausibility of a measure's content as an indicator of what it claims to assess. A measure can look appropriate without evidence that its scores represent the intended construct.
Validity argument: A reasoned chain linking evidence and assumptions to claims about score meaning and use. Construct validity is defended through explicit arguments connecting evidence to intended interpretations.
Operationalization: The process of translating an abstract concept into observable procedures, indicators, or measurements. A construct becomes measurable through operational choices that validity evidence must scrutinize.
Convergent validity: Evidence that measures intended to assess related constructs show the expected degree of association. Agreement with theoretically related measures supports a proposed score interpretation.
Predictive validity: The extent to which a measure forecasts a relevant outcome observed later. Future performance offers one form of evidence when a construct is used to predict outcomes.
Concurrent validity: The extent to which scores relate to a criterion measured at roughly the same time. A same-time criterion association is narrower than the broader evidence used to support construct interpretation.
Consequential validity: Consideration of the intended and unintended consequences of interpreting and using assessment scores. Score uses can produce consequences that matter when evaluating the adequacy of a validity argument.

Linked from 20 pages