Using conjoint analysis to determine the relative importance of service attributes measured in customer satisfaction surveys

Determining the relative importance of service attributes is one of the most important objectives of customer satisfaction measurement. Two popular methods that are currently used are "gap analysis" of expectations minus performance and linear regression of the overall satisfaction rating on the ratings for the attributes. Unfortunately, both these methods have shortcomings, so we develop a new method which is based on a conjoint analysis of nine hypothetical service scenarios. This information is used to fit a satisfaction response model as a function of the component service attributes. In turn, the current service level is plotted on the response surface and the "path of steepest ascent" in the direction of maximum customer satisfaction gives the best "direction" for management to plan a quality improvement program. We compare the proposed method with those currently being used and find it is more responsive to changes in attribute performance as a firm's quality improvement strategy evolves.