Which property asks whether an instrument measures what it is intended to measure?

Which property asks whether an instrument measures what it is intended to measure?

• A. Validity of measures
• B. Reliability of measures
• C. Generalizability
• D. Specificity

Answer: (A)

Validity is the degree to which an instrument actually measures the construct it is meant to assess. It asks whether the scores reflect the intended concept, not something else. To establish validity, we look for evidence across several angles: content validity checks that items cover all facets of the construct, criterion validity shows how well the instrument correlates with external standards or outcomes, and construct validity examines whether the relationships with other measures align with theoretical expectations about the construct. Reliability, in contrast, is about consistency—getting similar results across repeated administrations or items. A test can be reliable (stable results) without being valid (it may not measure the intended construct at all). Generalizability concerns how well findings extend beyond the original sample or setting, and specificity relates to diagnostic accuracy in correctly identifying true negatives, not to whether the instrument measures the intended construct.

Validity is the degree to which an instrument actually measures the construct it is meant to assess. It asks whether the scores reflect the intended concept, not something else. To establish validity, we look for evidence across several angles: content validity checks that items cover all facets of the construct, criterion validity shows how well the instrument correlates with external standards or outcomes, and construct validity examines whether the relationships with other measures align with theoretical expectations about the construct.

Reliability, in contrast, is about consistency—getting similar results across repeated administrations or items. A test can be reliable (stable results) without being valid (it may not measure the intended construct at all). Generalizability concerns how well findings extend beyond the original sample or setting, and specificity relates to diagnostic accuracy in correctly identifying true negatives, not to whether the instrument measures the intended construct.