What is the difference between reliability (test-retest) and internal consistency?

• A. Test-retest reliability assesses stability over time; internal consistency assesses how well items measure the same construct.
• B. Test-retest measures validity; internal consistency measures stability.
• C. Test-retest assesses the average score; internal consistency assesses sample size.
• D. Test-retest and internal consistency are identical.

Answer: (A)

Reliability has different facets, each capturing a different aspect of measurement consistency. Test-retest reliability looks at stability over time: if you administer the same test to the same people on two occasions, the scores should be similar when the underlying trait isn’t expected to change and the measurement procedure is sound. Internal consistency, on the other hand, asks whether the items on a test all tap the same underlying construct; if the items are measuring the same thing, responses tend to correlate with one another (Cronbach’s alpha is a common way to quantify this).

This is why the statement that test-retest reliability assesses stability over time and internal consistency assesses how well items measure the same construct is the best description. The other ideas mix up concepts—reliability with validity, or with average scores or sample size—and aren’t accurate descriptions of what these forms of reliability measure.