Also known as criterion-related validity, ( includes predictive and concurrent validity) criterion validity is the general term to describe how well scores on one measure (i.e., a predictor) predict scores on another measure of interest (i.e., the criterion). In other words, a particular criterion or outcome measure is of interest to the researcher; examples could include (but are not limited to) ratings of job performance, grade point average (GPA) in school, a voting outcome, or a medical diagnosis. Criterion validity, then, refers to the strength of the relationship between measures intended to predict the ultimate criterion of interest and the criterion measure itself.
