Discriminant validity

Evidence that an assessment does NOT correlate strongly with measures of unrelated constructs.

Discriminant validity is evidence that an assessment is distinct from measures of unrelated or weakly related constructs. A scale claiming to measure social anxiety should correlate less strongly with extraversion or self-esteem than it does with other social anxiety measures.

Together with convergent validity, discriminant validity is the workhorse evidence for construct validity. Without it, a scale might just be picking up a general "negative affect" or response style factor rather than the specific construct of interest.

Validity — The extent to which a psychological assessment measures what it claims to measure.
Construct validity — Evidence that an assessment actually measures the abstract concept (construct) it claims to measure.
Convergent validity — Evidence that an assessment correlates strongly with other measures of the same construct.
Response style — Systematic ways respondents answer items that aren't driven by item content — patterns like agreeing-with-everything or always picking the middle.

Discriminant validity

Related terms