What best describes construct validity?

What best describes construct validity?

• A. It refers to whether a test measures the theoretical construct.
• B. It refers to reliability of a measure over time.
• C. It refers to how well a test correlates with dissimilar constructs.
• D. It refers to inter-rater reliability.

Answer: (B)

Construct validity asks whether a test actually measures the theoretical construct it claims to measure. It’s about the meaning of the test scores and whether they reflect the intended concept, not about how consistent the scores are over time or how many different people score the test. Evidence for construct validity comes from showing the test relates to other measures in expected ways (convergent validity) and does not relate to measures it shouldn’t relate to (discriminant validity). Reliability over time (test-retest) is about stability, not validity. Inter-rater reliability is about agreement between scorers, not whether the test measures the right construct. If a test correlates strongly with dissimilar constructs, that would undermine validity, not support it. So the best description is that construct validity concerns whether the test truly measures the theoretical construct it’s intended to measure.

Construct validity asks whether a test actually measures the theoretical construct it claims to measure. It’s about the meaning of the test scores and whether they reflect the intended concept, not about how consistent the scores are over time or how many different people score the test. Evidence for construct validity comes from showing the test relates to other measures in expected ways (convergent validity) and does not relate to measures it shouldn’t relate to (discriminant validity).

Reliability over time (test-retest) is about stability, not validity. Inter-rater reliability is about agreement between scorers, not whether the test measures the right construct. If a test correlates strongly with dissimilar constructs, that would undermine validity, not support it. So the best description is that construct validity concerns whether the test truly measures the theoretical construct it’s intended to measure.