Modelling willingness to pay responses from dichotomous choice contingent valuation surveys with zero observations

Modelling household behaviour with the data from dichotomous choice conting ent valuation (DCCV) surveys is often complicated by zero willingness to pa y (WTP) responses ill the sample. To deal with the zero responses, a two-eq uation model is considered, which incorporates a two-level decision structu re, a decision on whether to participate in having WTP and a decision on th e WTP amount conditional on deciding to participate, and two separate stoch astic processes that determine the probability and conditional level of WTP are featured. The model is empirically applied to household survey data, i n which the DCCV questions concerned the benefits of air quality improvemen t in Korea. To put the issue of the two-equation model in perspective, this paper also experiments with economic and econometric specifications: utili ty theoretic restriction and heteroscedasticity. It is shown how failure to allow for the restriction distorts aggregate benefit estimates and the exi stence of heteroscedasticity in error term is found.