Design of Experiments > Predictive Validity
What is Predictive Validity?
A research study is useless unless it has some kind of predictive value. Predictive validity tells you how well a certain measure can predict future behavior. One of the most common uses for predictive validity is in University Admissions. Grade Point Average, SAT/ACT scores and other criterion are used to predict a student’s likely success in higher education. To test this theory, university students have been studied by their thousands and it’s been confirmed by hundreds of studies that there is a correlation between GPA/ACT/SAT and educational success. Therefore, the predictive validity is high for these measurements.
- A depression outcome scale is a tool to predict future behaviors of depressed people, such as social isolation, inability to hold down a job or maintain fulfilling relationships. Depressed patients can be followed to see if there is a correlation between their scores on a particular scale and their future behaviors.
- Ability in mathematics can predict future success in the sciences. This can be measured by giving tests to established scientists to see how they perform on math tests and whether there is a correlation between test scores and how well they do in their profession.
- Pre-employment tests can predict whether a person is likely to be successful in that career path. The pre-employment tests have often been tested for predictive validity by following employees after employment to see if a correlation exists between test scores and career success.
Predictive validity is a subset of criterion validity. Criterion validity is an umbrella term for measures of how variables can predict outcomes based on information from other variables. To measure the criterion validity of a test, the test is sometimes calibrated against a known standard. In other cases, the test is measured against itself.
National Institutes of Health. (2020). Examining the Predictive Validity of NIH Peer Review Scores.