Can anybody provide reliability estimates of Cattell's Culture Fair Intelligence Test (CFIT, 1973), preferably in terms of internal-consistency or split-half reliability? We would be interested in obtaining full CFIT as well as scale-specific reliability estimates.
Thanks to everybody who considers this question.
Nenty and Dinero (1981) quote Alpha as .77, KR-21 as .81, and Spearman-Brown as .79. You can find a copy in the attached link.
https://conservancy.umn.edu/bitstream/handle/11299/100409/v05n3p355.pdf?sequence=1
You're most welcome. It's worth pointing out that those figures are for Scale 2 Form A. The other figures should be in the source quoted in N&D's paper.
The question indicates a very frequent misunderstanding of reliability: A test does not "have" any reliabilty, reliability is not a "characteristic" of a test. Reliability is always the result of a test administered in the given situation to the sample under study. Thus the reliabilty may vary from study to study.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Probability
- Probability Theory
- Reliability