摘要：This article compares willingness-to-pay (WTP) estimates from an actual survey using a checklist question regarding WTP for groundwater quality improvements to WTP estimates that would have been obtained had a single-bounded referendum (SBR) or a double-bounded referendum (DBR) question been asked. Results indicate differences among estimates from the three types of question formats. There was a loss of statistical efficiency of parameter and WTP estimates when moving from the checklist and DBR formats to the SBR format. WTP estimates from the SBR question were more sensitive to sample size and model specification than the others.
