Describe procedures for determining test-retest reliability as compared ?

Question

Describe procedures for determining test-retest reliability as compared to split-half reliability.

Answer 1

Test-retest reliability is a measure of the consistency of test scores.  The same test is administered to the same respondents on two different occasions, and the correlation is calculated for the scores at Time 1 and Time 2.

Split-half reliability is a measure of the internal consistency of test items.  One test is given to a group of respondents, and correlations are computed b/w the items. There are several ways of doing this (odd-even questions, first half of questions vs. second half), but computers have allowed more exact calculations, of which Cronbach's alpha is the most common measure.