Measurement validity includes which types?

Measurement validity includes which types?

• A. Face validity only
• B. Construct validity only
• C. Face, content, criterion, and construct validity
• D. Content validity and test-retest reliability

Answer: (C)

Measurement validity is supported by multiple kinds of evidence. Face validity is the initial, surface-level judgment that the instrument appears to measure what it should, which influences acceptance but doesn’t prove accuracy. Content validity ensures the instrument covers all relevant aspects of the construct, typically by expert review so the items represent the domain fully. Criterion validity shows the instrument relates to an external criterion in the expected way, whether measured at the same time (concurrent) or in the future (predictive). Construct validity asks whether the instrument behaves according to theory, using patterns of relationships with other measures and the instrument’s internal structure (convergent and discriminant validity, factorial validity, etc.). Taken together, these sources form a robust picture of validity. So the best choice includes face, content, criterion, and construct validity. The other options are incomplete or mix in reliability (like test-retest reliability), which is about consistency over time rather than validity.

Measurement validity is supported by multiple kinds of evidence. Face validity is the initial, surface-level judgment that the instrument appears to measure what it should, which influences acceptance but doesn’t prove accuracy. Content validity ensures the instrument covers all relevant aspects of the construct, typically by expert review so the items represent the domain fully. Criterion validity shows the instrument relates to an external criterion in the expected way, whether measured at the same time (concurrent) or in the future (predictive). Construct validity asks whether the instrument behaves according to theory, using patterns of relationships with other measures and the instrument’s internal structure (convergent and discriminant validity, factorial validity, etc.). Taken together, these sources form a robust picture of validity.

So the best choice includes face, content, criterion, and construct validity. The other options are incomplete or mix in reliability (like test-retest reliability), which is about consistency over time rather than validity.