Which statement best defines validity in testing as described?

Which statement best defines validity in testing as described?

• A. Validity concerns whether a test measures what it intends to measure.
• B. Construct validity is the most comprehensive type that accumulates evidence.
• C. Reliability determines if a test is valid.
• D. A test can be valid without evidence.

Answer: (B)

Validity means the interpretations and uses of test scores are supported by evidence. Among the different forms, construct validity is the broadest framework because it brings together evidence from multiple sources—how well the content represents the construct, how the items relate to one another (internal structure), and how the test scores relate to other measures and theoretical expectations. This accumulation of diverse evidence across methods is what makes construct validity the most comprehensive way to demonstrate that a test measures the intended construct across its uses. While validity does involve measuring what you intend, that view is narrower; reliability is about consistency, not whether interpretations are warranted, and a test isn’t considered valid without the necessary supporting evidence.

Validity means the interpretations and uses of test scores are supported by evidence. Among the different forms, construct validity is the broadest framework because it brings together evidence from multiple sources—how well the content represents the construct, how the items relate to one another (internal structure), and how the test scores relate to other measures and theoretical expectations. This accumulation of diverse evidence across methods is what makes construct validity the most comprehensive way to demonstrate that a test measures the intended construct across its uses. While validity does involve measuring what you intend, that view is narrower; reliability is about consistency, not whether interpretations are warranted, and a test isn’t considered valid without the necessary supporting evidence.