Specification of the utility function in discrete choice experiments

BACKGROUND: The specification of the utility function has received limited attention within the discrete choice experiment (DCE) literature. This lack of investigation is surprising given that evidence from the contingent valuation literature suggests that welfare estimates are sensitive to different specifications of the utility function. OBJECTIVE: This study investigates the effect of different specifications of the utility function on results within a DCE. METHODS: The DCE elicited the public's preferences for waiting time for hip and knee replacement and estimated willingness to wait (WTW). RESULTS: The results showed that the WTW for the different patient profiles varied considerably across the three different specifications of the utility function. Assuming a linear utility function led to much higher estimates of marginal rates of substitution (WTWs) than with nonlinear specifications. The goodness-of-fit measures indicated that nonlinear specifications were superior.