1
$\begingroup$

Let's say, I have an intelligence test made of 60 questions (items) which produces results for two intelligence constructs on a 0-100 scale (for instance crystallised and fluid intelligence).

I only have respondent's final scores on the two constructs. So, I don't have answers to single items. In such a scenario, I cannot calculate Cronbach's Alpha as a measure of internal consistency, because I don't have single items' scores.

Is there any reliable alternative measure of reliability that I could use, only having final test scores?

$\endgroup$
1
$\begingroup$

If you have two administrations of each test on the same people, you could compute test retest reliability.

If all you have is one score on each construct for each person, then there is no measure of reliability you can calculate; however, there may be some measures of validity. If you believe (from prior research, for example) that the two types of intelligence ought to be correlated, you can find that. Or if you have scores on other measures, you may be able to calculate some other kind of validity.

| cite | improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.