Which type of reliability uses two versions of a test?

Which type of reliability uses two versions of a test?

• A. Inter-Rater
• B. Test-Retest
• C. Form Reliability
• D. Inter-item

Answer: (C)

Reliability of a test is about consistency across measurements. When you want to know if two different versions of the same test yield comparable results, you’re looking at form reliability, also called alternate-forms reliability. This involves creating two parallel tests that cover the same content and have similar difficulty, then administering them to comparable groups and checking how closely the scores line up (often via a correlation). This focuses on score equivalence across versions, not on how consistently raters judge an answer (inter-rater), not on stability of scores over time with the same form (test-retest), and not on internal consistency among items within one form (inter-item). So using two versions to establish consistency across forms is what form reliability measures.

Reliability of a test is about consistency across measurements. When you want to know if two different versions of the same test yield comparable results, you’re looking at form reliability, also called alternate-forms reliability. This involves creating two parallel tests that cover the same content and have similar difficulty, then administering them to comparable groups and checking how closely the scores line up (often via a correlation). This focuses on score equivalence across versions, not on how consistently raters judge an answer (inter-rater), not on stability of scores over time with the same form (test-retest), and not on internal consistency among items within one form (inter-item). So using two versions to establish consistency across forms is what form reliability measures.