Efficient Semiparametric Estimation of the Willingness-To-Pay Distribution

The dichotomous choice contingent valuation has been one of the most popular method to estimate Willingness-To-Pay (WTP) for nonmarket goods, such as environmental resources. Standard estimation procedures rely upon fully parametric assumptions on the model. This paper provides a new semiparametric estimation of the WTP distribution, which consists of three steps: In the first step, a finite-dimensional slope parameter is estimated by existing methods. In the second step, an infinite dimensional parameter is estimated by the nonparametric maximum likelihood estimation (NP-MLE). In the final step, the distribution of the WTP is estimated based on the first two steps. Consistency and asymptotic normality of the estimator are proven. Furthermore, the method is shown to be semiparametirically efficient. JEL classification: C14; C25; C42; Q20