Key points are not available for this paper at this time.
Test-retest correlations often are reported as measures of the reliability of copy testing procedures with little or no attention to the conditions under which such an interpretation is meaningful. Some checks are suggested for assessing the consistency of test-retest data with certain requirements which should be met if a test-retest correlation is to serve as reliability index. Ambiguities and shortcomings of many available reliability estimates are discussed.
Alvin J. Silk (Tue,) studied this question.