摘要：A recent study published by Murphy et al. (2005) reported results of a meta-analysis of hypothetical bias using 28 valuation studies. The authors found a median ratio of hypothetical to actual values of 1.35 but they did not investigate the ratio of scales of the hypothetical and actual value distributions, which is of great relevance in joint stated and revealed preference analysis. We propose an addendum to Murphy et al. (2005) to provide some insights on the distribution of the scale factor across 23 studies for which relevant data is available. We also describe a method to supply priors to future studies that use Bayesian approaches to model merged revealed and stated preference data.
