Enhancing the face validity of choice experiments: A simple diagnostic check
提出一个基于成本属性最高水平的阈值来检验选择实验中支付意愿估计是否合理的简单方法，并通过对304个观察值的分析发现65%的估计值超出阈值，表明支付意愿高估现象普遍存在。
We propose a simple diagnostic check for face validity assessment of willingness to pay (WTP) estimates derived from choice experiments (CEs). The check is based on a threshold value for WTP that is related to the highest cost attribute level, which can be used to assess plausibility of estimated WTP. If the threshold value is exceeded, WTP estimates are considered to overshoot. This may be due to issues with (i) the design of the CE and/or (ii) respondents' behavior deviating from assumptions underpinning CEs. Applying the check to a sample of publications, this paper provides evidence on the incidence and magnitude of overshooting of WTP in the agricultural and environmental CE literature. Based on a random sample of publications including 304 observations representing individual studies and population samples, the results show that overshooting of WTP is widespread, with 65% of observations exceeding the overshooting threshold value. An exploratory analysis to identify factors associated with overshooting of WTP across studies reveals that study design factors, and in particular the design of the cost attribute, play an important role. We recommend that researchers apply the diagnostic check for the design of choice experiments and to motivate further scrutiny of choice experiment results.