SAMPLE-SIZE AND OPTIMAL DESIGNS FOR RELIABILITY STUDIES

A method is developed to calculate the required number of subjects k i n a reliability study, where reliability is measured using the intracl ass correlation p. The method is based on a functional approximation t o earlier exact results. The approximation is shown to have excellent agreement with the exact results and one can use it easily without int ensive numerical computation. Optimal design configurations are also d iscussed; for reliability values of about 40 per cent or higher, use o f two or three observations per subject will minimize the total number of observations required. (C) 1998 John Wiley & Sons, Ltd.