and

We apply a semi-nonparametric distribution-free estimator for binary discrete response data to the estimation of a dichotomous choice contingent valuation model. Using this estimator, mean and median compensating and equivalent variation can be consistently estimated without making nontheoretically motivated assumptions on consumer ' preferences. The approach is illustrated using a contingent valuation survey of willingness to pay for reduction of risk of premature death due to exposure to hazardous waste. We find that a conventional parametric estimator and the proposed estimator give similar estimates of unconditional WTP, but that conditional on explanatory variables the estimates are quite different. Q 1997 Academic Press This paper deals with the estimation of compensating and equivalent variation .for changes in environmental quality using dichotomous choice or referendum contingent valuation models. Such models are commonly based upon explicit distributional and functional form assumptions. Alternatively, it has been clear for some time that such assumptions are not necessary for consistent estimation of w xwelfare measures, and that nonparametric estimation, as in Kristrom 13 is