Which validity type would most directly involve comparing a new measurement to a well-established standard to demonstrate accuracy?

Which validity type would most directly involve comparing a new measurement to a well-established standard to demonstrate accuracy?

• A. Face validity
• B. Content validity
• C. Criterion validity
• D. Measurement validity

Answer: (C)

When you want to show that a new measurement is accurate, you compare it to an established standard that already reflects the true construct. This approach is criterion validity: it tests how well the new measure aligns with a gold standard or criterion known to measure the same thing. If the new tool produces results that closely match the standard, it demonstrates accuracy; if not, it suggests the measure may be flawed or capturing something else. There are two common forms: concurrent validity, where the criterion and the new measurement are taken at roughly the same time, and predictive validity, where the criterion is something the measure should predict in the future. By contrast, face validity is about whether the test appears to measure what it should, and content validity is about whether the test covers all relevant aspects of the construct rather than its accuracy against a standard.

When you want to show that a new measurement is accurate, you compare it to an established standard that already reflects the true construct. This approach is criterion validity: it tests how well the new measure aligns with a gold standard or criterion known to measure the same thing. If the new tool produces results that closely match the standard, it demonstrates accuracy; if not, it suggests the measure may be flawed or capturing something else. There are two common forms: concurrent validity, where the criterion and the new measurement are taken at roughly the same time, and predictive validity, where the criterion is something the measure should predict in the future. By contrast, face validity is about whether the test appears to measure what it should, and content validity is about whether the test covers all relevant aspects of the construct rather than its accuracy against a standard.