This paper introduces model specifications that can be used to explain
response incentive effects that might occur with discrete response co
ntingent valuation data when follow-up responses are collected. The mo
dels allow for possible random response shocks, structural shifts in w
illingness to pay between payment questions and heteroskedasticity bet
ween and within responses. Three well-known contingent valuation surve
y datasets that include follow-up payment questions are used to empiri
cally test the models.