Alternative approaches to obtain optimal bid values in contingent valuation studies and to model protest zeros. Estimating the determinants of individuals' willingness to pay for home care services in day case surgery.

The use of day case surgery has increased rapidly as an alternative to inpatient surgery. Little is known, however, about the value of day case surgery to patients. The aim of this paper was to develop a contingent valuation survey to investigate how individuals value the costs of shifting from inpatient to day case surgery based on home care services. Using the willingness to pay (WTP) approach, two kinds of sequential experiments are compared: the maximum likelihood recursion (MLR) method and the C-optimal sequential procedure. The goal of sequential experimentation is to find bid values that provide the maximum possible information about the parameters of the WTP distribution, especially when the sample size is small. The C-optimal sequential procedure is shown to be an improvement, in terms of the statistical precision in small samples, over the MLR method. In addition, the paper presents a double hurdle (DH) approach for modelling the determinants of individuals' WTP. Using data from a contingent valuation survey conducted in 1996 on patients selected from the Day Case Surgery Unit in a hospital in the region of Catalonia, we argue that participation in the market offered and the level of consumption, that is, people's WTP, should be treated as individual choices. The results show that income and sex are related to WTP. Also, in this study, a clear presence of starting-point bias, introduced by the bid offered, was found. It is concluded that the WTP technique is potentially useful in evaluating health care programmes, although it is important to note that the criteria used to find an optimal design (in our model to minimize the asymptotic variance of the estimator used) may be restrictive from an economic point of view. Copyright 2001 John Wiley & Sons, Ltd.