The predictive validity of survey instruments and psychometric tests is a measure of agreement between results obtained by the evaluated instrument and results obtained from more direct and objective measurements. The predictive validity is often quantified by the correlation coefficient between the two sets of measurements obtained for the same target population.
For example, a job performance test has been developed that is supposed to assess the ability of individuals to particular job tasks. The test is supposed to be used in recruiting new employees. A group of 50 applicants, who passed the interview successfully, have been tested. Three months later, job skills of the 50 new employees have been assessed by their bosses and colleagues using a quantitative scale.
Thus, there are 50 pairs of scores at hand – one pair for each employee: a score obtained by the test before starting the job and the scores of the real skills (as assessed by competent experts after 3 months). The value of the correlation coefficient between the two sets of scores is a reasonable quantitative measure of predictive validity of the new test.
The predictive validity is a form of the criterion validity .