A simple mechanism to incentive-align conjoint experiments

Recent literature has established the importance of incentive-aligning research participants in conjoint analysis. Pertinent studies have also proposed and validated a fairly general incentive-aligning mechanism (willingness-to-pay, or WTP) that achieves incentive alignment by using respondents' data to determine their value for a reward product (Ding, 2007). This mechanism, however, requires an estimation of the value of money and is relatively difficult for the average respondent to understand. We propose an alternative mechanism based on inferred rank order for situations where conjoint practitioners have more than one version of real products. In an empirical test of choice-based conjoint, we show that the RankOrder mechanism leads to substantial improvement in predictive performance when compared to non-aligned hypothetical choices. A second test shows that both incentive-aligned mechanisms - RankOrder and WTP - produce very similar predictive performances. RankOrder, however, dominates the WTP mechanism in user preference, an outcome shown both by perceived understanding and by the incentive-aligned money that respondents are willing to pay to switch from one mechanism to the other.