Preference measurement using conjoint methods: An empirical investigation of reliability

The application of conjoint measurement to the field of health economics is relatively new, although there is growing interest and there have been a n umber of studies undertaken recently. Wider acceptance of the technique req uires methodological issues concerning both reliability and validity to be addressed. This paper reports an empirical investigation of the test-retest reliability of the discrete choice conjoint measurement approach in health care. This investigation of conjoint reliability was framed using the clin ical context of investigation and treatment of knee injuries. A high level of reliability at both the input data and results levels was demonstrated. Copyright (C) 2000 John Wiley & Sons, Ltd.