In contingent valuation surveys the category of zero bidders refers to individuals that are not willing to pay anything for the programme under analysis. Specific questions can help to identify true zero values, coming from people that are indifferent to the programme, separately from protest responses: the latter are generally excluded from the analysis. This paper introduces a mixture-sample selection model that takes into account both zero values and protest responses in the estimates. The model is applied to the valuation of a traffic calming scheme aimed at reducing risks for residents in three villages in the north-east of England.

The dichotomous choice contingent valuation method can be used either in the single or double bound formulation. The former is easier to implement, while the latter is known to be more efficient. We analyse the bias of the ML estimates produced by either model, and the gain in efficiency associated to the double bound model, in different experimental settings. We find that there are no relevant differences in point estimates given by the two models, even for small sample size. The greater efficiency of the double bound is confirmed, although differences tend to reduce by increasing the sample size. Provided that a reliable pretest is conducted, and the sample size is large, use of the single rather than the double bound model is warranted.

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. We would like to thank Robin Keller for helpful suggestions to improve the exposition. Terms of use: Documents in AbstractRespondents of contingent valuation surveys may place a null value on the public good, for reasons that differ from a genuine indifference to the good, but that can be interpreted as a "protest": either against the interview, or the public management, or both. A good survey design can effectively reduce them, but protest votes can hardly be completely removed from the dataset, and, if there is sample selection bias, they lead to biased estimates for the wtp measure. We propose a survey design, and a sample selection model, that allows taking into account, and correcting, the possible bias due to protest votes. Since the asymptotic standard errors estimated by means of the inverse of the information matrix containing the sample selection parameter are not reliable, we use an alternative procedure based on the likelihood profile. It will be seen that sample selection models may present estimation problems because of the flatness of the likelihood function: in some cases confidence intervals around the sample selection coefficient are too wide to give evidence of presence or absence of sample selection bias. We maintain that even in these circumstances the 2 sample selection model with the protest votes should be preferred to the model without protest votes, since it takes into account the uncertainty about the estimates of the willingness to pay for the public good. Non technical abstractContingent valuation surveys are increasingly used to assess the value of public goods, and help public decision making. Sampled individuals' reservation prices for the public good, and other relevant variables, are modeled to estimate its value. Unfortunately, it can be often observed that respondents may seemingly place a null value on the public good, for reasons that differ from a genuine indifference to the good, but that can be interpreted as a "protest": either against the interview, or the public management, or both.A good survey design can effectively reduce them, but protest votes can hardly be completely removed from the dataset. The question is how to deal with them.Sometimes they are considered as true zero values, or, if a dichotomous choice method is used to elicit the reservation price, as if they were below the minimum bid offered to the individual.Obviously, if the unwillingness to pay reflects only protest and not a low or null valuati...

The Dichotomous Choice Contingent Valuation Method (DC-CVM), both in the single and the double bound formulation, has been in the last years the most popular technique among practitioners of contingent valuation, due to its simplicity of use in data collection. The single bound procedure is easier to implement than the double bound, especially in data collection and estimation. On the other hand, it is well known that the double bound is more efficient than the single bound estimator. It remains to analyze the bias of the ML estimates produced by either model, and the gain in efficiency associated to the double bound model, in different experimental settings. We find that there are no relevant differences in point estimates given by the two models, even for small sample size, so that neither estimator can be said to be less biased than the other. The greater efficiency of the double bound is confirmed, although it can be seen that the differences tend to reduce by increasing the sample size, and are often negligible for medium size samples. Provided that a reliable pre-test is conducted, and the sample size is large, our results warrant the use of the single rather than the double bound model. * We would like to thank Rossella Diana for her helpful assistance in the early stage of this research. IntroductionThe Dichotomous Choice Contingent Valuation Method (DC-CVM) has been in the last years the most popular technique among practitioners of contingent valuation, due to its simplicity of use in data collection. When this elicitation method is used, the respondent is only required to answer YES or NO when asked if she/he is willing to pay a given amount (bid) for the public good. The single bound model comprises only one such question, while in the double bound model the first question is followed by another specifying a lower amount, if the answer to the first question was negative, and higher otherwise. This procedure is certainly easier for respondents than other methods requiring long adjustment processes, like the bidding game; or a precise assessment of the individual's own reservation price based on introspective analysis, as it happens in the open ended elicitation method. The price to pay for this is the limited information arising from DC-CVM data: the only information available to the researcher after the interview is an interval of values containing the true willingness to pay (wtp) of the individual.In the single bound model the interval is bounded by the bid and the limit of the wtp distribution (the upper limit if the answer was positive, the lower limit otherwise). In the double bound model the interval is enclosed within two bids, if one answer to the two questions was positive and the other negative (double bound); otherwise, the interval is bounded by the second bid and the limit of the wtp distribution. In order to gather more information about the support of the true wtp distribution, the initial bids are varied among individuals.Hanemann, Loomis and Kanninen (1991) proved that the ...

No abstract