Predicting Prescribing Intention and Assessing Drug Attribute Importance Using Conjoint Analysis

Conjoint analysis is an anal ical research tool for studying consumer preferences among multiattribute alternatives. This paper reviews the process of conducting conjoint analysis and illustrates it with a pilot stud in the area of physician prescribing. Hypothetical drugs were profiled (5 factors with 2 levels each) and distributed to physicians in a mail questionnaire (n=43; response rate 44%). Analyses, at the aggregate and individual levels, revealed the conjoint model to be useful in predicting physician prescribing intentions and in assessing the relative importance of various drug attributes.