A multilevel modelling approach to triple-bounded dichotomous choice contingent valuation

The use of dichotomous choice (DC) questions in the elicitation of willingness to pay (WTP) in contingent valuation studies is common practice at the present time. Recent research has shown that double-bounded DC questions provide statistically superior results to single-bounded questions, given an appropriate sampling design. This paper uses a relatively new multilevel modelling technique to analyze a triple-bounded DC design, which in addition includes an initial non-monetary question on whether an individual accepts, in principle, a WTP some unspecified amount. The theoretical basis of the multilevel model used is described, and some of the possibilities of this potentially powerful and versatile technique are discussed. The practical operation of the multilevel model is demonstrated using data from a contingent valuation study conducted in the Norfolk Broads, England, an internationally important wetland resource.     

On the Asymmetry of the Vagueness Band in Willingness to Pay Answers

The NOAA panel for Contingent Valuation opened up the question of the possibility of using trichotomous choice discrete formats in CV studies. In this paper we show how the trichotomous choice format can be used for testing the successfulness of the project definition in the questionnaire. We shall define the vagueness band around the true outcome of the project to be valued and we allow it to be asymmetric. It is shown how this asymmetry can be modelled and estimated. We also show how these new models are generalisations of ordinary ordered probit/logit models.     

Comparing continuous and discrete contingent valuation questions

This paper explores two commonly used methods to elicit an individual's willingness to pay (WTP) for a public good in contingent valuation studies. Currently, the most preferred method is the take-it-or-leave valuation question, or discrete valuation question (DVQ), where the respondent accepts or rejects a suggested cost for the good. The traditional method, the continuous valuation question (CVQ), simply asks an individual to state his WTP for the suggested change in the provision of a public good like cleaner air. We introduce a simple way to compare the results from these two methods. We also test the anchoring behavior suggested in the psychological literature on choice under uncertainty. The results do not support the anchoring hypothesis, but suggest the hypothesis that people perceive the two tested valuation questions differently.I would like to thank Prof. Glenn Harrison, University of South Carolina, Prof. P-O Johansson, Stockholm School of Economics, Prof. Jason Shogren, Iowa State University, and two referees for helpful comments. The usual disclaimer applies.     

Joint estimation of contingent valuation survey responses

Hanemann's utility difference model for the dichotomous choice contingent valuation method is modified to account for interrelationships between responses to a set of contingent valuation questions. A nonlinear seemingly unrelated regression model is presented to jointly estimate the probit models and to derive WTP from the CV responses. The model is used to test and impose restrictions derived from economic theory on the utility difference model. Mean WTP estimates for three different types of changes in the quality of California deer hunting were uniformly lower for the joint response probit model compared to a set of independent probit models.     

Identifying inconsistent responses in dichotomous choice contingent valuation with follow-up questions

We develop a new but simple non-parametric method to diagnose inconsistency in double-bounded contingent valuation questions in the presence of both perfect and imperfect correlation between initial and follow-up response distributions. The proposed method can identify inconsistency in iterative responses at each bid interval. We apply this method to data from five well-known double-bounded contingent valuation surveys. The predictions of our model match closely with parametric outcomes. Further, we find that the inconsistency patterns generally vary for different data sets and different bid intervals within data sets. Therefore no single behavioral model can explain all latent inconsistency patterns either within or across data sets. In addition, we examine the impact of inconsistency in responses on bias and efficiency of the double-bounded format in the absence of correction for inconsistency. We conclude that the commonly cited benefits of the double-bounded format hold only in the special case of nearly perfect consistency between initial and follow-up response distributions. Our method provides a simple tool researchers can use to determine the similarity in response distributions between the initial and follow-up responses and whether incorporating collected follow-up responses are likely to actually increase efficiency without introducing bias.     

Preference uncertainty in contingent valuation

In this paper, the results of empirical studies that applied two widely used methods - numerical certainty scale (NCS) and polychotmous choice (PC) - for estimating preference uncertainty adjusted willingness to pay (WTP) in contingent valuation (CV), are summarized. For this review, a number of conclusions are reached. First, there is a lack of consensus about which method is more appropriate for measuring preference uncertainty. Second, although preference uncertainty information has been found useful in detecting the incidence of hypothetical bias in CV studies, a consensus about a standard certainty threshold (or treatment mechanism) at which hypothetical behaviour converges to real behaviour is yet to emerge. Third, insufficient empirical evidence exists about the causal relationship between preference uncertainty scores and the theoretically expected explanatory variables. Finally, the preference uncertainty adjusted PC and NCS models fail to provide a consistent and more efficient welfare estimate compared to the conventional dichotomous choice certainty model.     

Valuing cultural heritage in developing countries: comparing and pooling contingent valuation and choice modelling estimates

A substantial part of the United Nation’s World Heritage Sites (WHSs) can be found in developing countries, but many of them are in a bad state. Thus, there is a need to document the social benefits of these global goods in order to justify the costs of restoration and preservation programmes (RPPs). This study adds to the scarce literature on economic benefits of WHSs in developing countries, and reduces the need to perform very uncertain benefit transfers from European or US valuation studies. We apply Contingent Valuation (CV) and Choice Modelling (CM) to estimate the social benefits of RPPs for the My Son world cultural heritage site in Vietnam; both to foreign visitors and the local residents. We then compare the estimates from the CV and CM methods, and pool the results from the two methods. The results show that both CV and CM are suited to estimating the economic benefits of preserving cultural heritage of My Son. The two methods produce very similar results, which can be interpreted as a test of convergence validity. The pooling results give evidence to show that the CV and CM models have the same underlying preference structures. Thus, these valuation models can be successfully used in cost-benefit analyses to assess the benefits to cultural heritage of measures to reduce air pollution, soil erosion, climate change and other causes to deterioration of cultural heritage sites.

A Bayesian Approach to Double Bounded Contingent Valuation

In this paper we propose a Bayesian approach to model double bounded contingent valuation data. The double bounded elicitation method is interpreted as a two tier iterated process in which the subject is allowed to have a second thought about his/her valuation for the environmental good. Prior information is modelled from the answers to the first dichotomous choice question. The model is Quasi-Bayesian (Q-B) in that the prior distribution refers to mean willingness to pay while the likelihood function refers to the proportions of a multinomial distribution. This model is applied to empirical data from a contingent valuation survey involving the valuation expressed by European tourists for access to natural areas in the Canary Islands. Results show that point estimate of consumer surplus computed with the Q-B model does not differ substantially from single bounded model estimation. In addition, double bounded seems to be quite robust to the choice of the prior model of willingness to pay responses. Comparison with open ended suggests that the Q-B model might be useful to control for strategic response and starting point biases.     

Costing the traffic barrier effect: A contingent valuation survey

When considering the environmental damage caused by road traffic, one traditionally focuses attention on the consequences of accidents, or on the impact of air and noise pollution. This somewhat narrow definition should be enlarged to capture other, more psychological nuisances. The barrier effect created by heavily travelled streets belongs to this group of nuisances, rarely described and never estimated in monetary terms. It particularly affects children, the disabled and elderly people for whom the street becomes too large to cross. In a survey carried out at Neuchâtel, Switzerland, a contingent market was proposed to suppress the barrier effect around the city centre. A valuation function to predict the bids is estimated and used to infer the annual cost of the nuisance.     

Construct Validity of Dichotomous and Polychotomous Choice Contingent Valuation Questions

In this note we conduct construct validity tests for dichotomous choice (DC) and polychotomous choice (PC) contingent valuation questions. Contrary to previous results, we find that DC and PC estimates of willingness to pay are theoretically valid, convergent valid, and similar in terms of statistical precision. Similar to previous results, PC respondents are less sensitive to information than DC respondents. We conclude that DC and PC valuation questions are construct valid for this study. Sequential PC valuation questions could be used in studies where obtaining information about the certainty or intensity of respondent preferences would be useful.     

浅谈发出存货计价方法的选择

对存货计价问题的产生进行说明,详细介绍了5种发出存货计价方法,并且通过它们之间的比较,重点阐述了企业如何根据自己选择恰当的存货计价方法。这样,选择比较合理的发出存货计价方法,可以有效达到企业管理的目标。     

Treating respondent uncertainty in contingent valuation: A comparison of empirical treatments

This research examines the impact of uncertainty on contingent valuation responses using (1) a survey of Canadian landowners about willingness to accept compensation for converting cropland to forestry and (2) a survey of Swedish residents about willingness to pay for forest conservation. Five approaches from the literature for incorporating respondent uncertainty are used and compared to the traditional random utility model with assumed certainty. The results indicate that incorporating uncertainty has the potential to increase fit, but could introduce additional variance. While some methods for uncertainty can be an improvement over traditional approaches, it is imperative to exercise caution when making systematic judgments about the effect of uncertainty on contingent valuation responses.     

Willingness to pay for environmental goods in Norway: A contingent valuation study with real payment

The study seeks to determine the maximum willingness to pay (MWTP) among a random sample of Norwegians, for membership in the largest environmentalist association in Norway, Norges Naturvernforbund (NNV). The study includes three stages: (1) a contingent valuation study, testing hypothetical MWTP; (2) those whose stated MWTP is at or above the current membership fee are then asked to pay this fee; (3) those individuals who do not pay in stage 2 are interviewed, and asked to consider revising their MWTP statement. The study is seemingly the first of its kind in comparing hypothetical and actual MWTP by typing valuation of a public good (the environment) to the value of a private good (membership of the NNV). The results show a rather poor correspondence between hypothetical and actual MWTP, since only 6 out of 64 who stated that they were willing to pay the membership fee in stage 1, actually paid this voluntarily in stage 2. Possible reasons for this discrepancy are discussed, on the basis of data from the telephone interview in stage 3, and on information gathered in stage 1. The data indicate that a substantial part of this discrepancy is due to MWTP being overstated in stage 1, but that other reasons also are important.     

Economic valuation of environmental services sustained by water flows in the Yaqui River Delta

We attempted to estimate the economic value of environmental services provided by restored instream flows in the water-scarce Yaqui River Delta in Mexico. The Yaqui River begins near the U.S.-Mexico border and continues for 400 km before reaching the Oviachic dam, but has not reached the nearby Gulf of California for decades due to diversions for irrigation. These diversions have degraded the riparian ecosystem, coastal wetlands, and estuaries. Environmental services provided by restored flows in the Yaqui River would include healthy riverside vegetation, wetlands and estuaries, fish and wildlife habitats, non-use values, and recreation. A contingent valuation survey in 40 neighborhoods in the most populated Delta city, Ciudad Obregon, was administered to estimate non-market values of instream uses. Respondents were given a current and hypothetical Delta scenario (the latter assumed restored water flows in the River) and asked a willingness-to-pay (WTP) question regarding purchasing water for environmental flows through higher water bills. Results from 148 in-person interviews indicated that households would pay an average of 73 pesos monthly. WTP was found related to key variables suggested by economic theory and contingent valuation studies elsewhere: income, educational level, number of children in the household, and initial bid amount. These results will allow decision makers to compare the benefits generated by different water uses, including environmental services, and to manage scarce water resources under a long-term sustainable approach.     

Conservative dichotomous choice responses in the active policy setting: DC rejections below WTP

An important feature of a Contingent Value (CV) study is that researchers design a survey that guides respondents to answer dichotomous choice (DC) questions as if they represent once-and-for-all choices. Researchers frequently construct hypothetical markets to satisfy this condition; yet detractors assert that ‘hypotheticality’ leads inevitably to inflated DC responses. For active policy questions, however, some respondents may suspect that a CV informs an actual policy issue; so to reject a DC might induce the policy-maker to reintroduce the policy with a price reduction or a program improvement. With potential incentives to deflate a DC response when policies are active, we locate two types of respondents that represent two different incentives. One class is expected to be able to risk permanent rejection of a waiver from one automobile emissions inspection. This class more frequently rejects a DC value known to improve existing conditions. Another respondent class is expected to be risk averse to defeat of the program or to excessive delay. Predictably, these respondents more frequently accept a DC value that represents a known gain. Conservative DC responses have implications for the use of CV in active policy contexts, opening a role for theory to assist practitioners in these circumstances.      

Contingent valuation of ill health caused by pollution: testing for context and ordering effects

Contingent valuation is being increasingly used to value episodes of ill health caused by environmental pollution. In contrast to studies that have used contingent valuation to value other types of non-market goods, health episode valuation studies have tended to 1) value several ill health episodes or symptoms in the same survey, and 2) be vague in the survey instrument about the cause of the ill health, how it would be avoided or how the improvement would be paid for. The resulting values are then combined with exposure-response functions to generate economic estimates of health damages from pollution. This study tests whether episode valuation responses are sensitive to two of these design features. In a five-country study using split sample treatments, neither episode ordering nor mention of the cause of the ill health influenced stated willingness to pay to avoid specific ill health episodes.JEL Classification: C42, I12, Q51 Correspondence to: Richard ReadyThis research was supported by the European Unions Environment and Climate Research Programme: Theme 4 - Human Dimensions of Environmental Change (contract no. ENV4-CT96-0234). Any views expressed in the paper are not necessarily the views of any of the authors employers.     

Are Korean consumers willing to pay a tax for a mandatory BSE testing programme?

The outbreaks of mad cow disease (BSE) have significantly increased the demand for food safety programs in the Korean beef market. Two issues that are getting much attention are about whether Korea should implement mandatory testing of slaughtered domestic cattle for BSE and whether consumers are willing to pay a tax for the programme. No study, however, has examined consumers’ willingness to pay (WTP) a tax for a BSE testing programme. We conducted a contingent valuation (CV) study using a double-bounded dichotomous choice approach to estimate Korean consumers’ valuation for a mandatory BSE testing programme on slaughtered domestic cattle that are 21 months or older. Our results show that the sample-population adjusted mean estimate of WTP a tax per year is 4482 KRW (US $4.01) per household. This suggests that Korean consumers have a strong preference for a mandatory testing of domestic cattle for BSE. This study also found that Korean consumers’ WTP for the programme is greater than estimated implementation costs of the programme. These results imply that implementing a mandatory BSE testing programme in Korea could confer positive consumer welfare.     

A comparison of empirical models used to infer the willingness to pay in contingent valuation

The essence of the contingent valuation method consists of creating a hypothetical market where respondents are asked about their willingness to pay (WTP) for a non-market good. Different empirical models can be formulated to estimate the expected WTP of a sample of respondents and, then, through aggregation, the social valuation of the good is inferred.This paper outlines the relevance of the distributional assumptions when estimating mean WTP. Several parametric and non-parametric methods are discussed and applied to calculate the existence value of a natural space. Results show that WTP is extremely sensitive to the empirical model used.First version received: November 2002 / Final version received: January 2004     

The effect of distance on willingness to pay values: a case study of wetlands and salmon in California

Most contingent valuation studies in the literature utilized a pre-determined geographic market area for their sample frame. In other words, they did not include variables that would measure the extent of the geographic areas over which to aggregate willingness to pay. These studies implicitly assumed that the effects of geographic distance were moot; an assumption that could have led to an understatement of the aggregate benefit values computed in these studies. The overall goal of this study was to determine if distance affects willingness to pay for public goods with large non-use values. The data used came from a contingent valuation study regarding the San Joaquin Valley, CA. Respondents were asked about their willingness to pay (WTP) for three proposed programs designed to reduce various environmental problems in the Valley. A logit model was used to examine the effects of geographic distance on respondents' willingness to pay for each of the three programs. Results indicate that distance affected WTP for two of the three programs (wetlands habitat and wildlife, and the wildlife contamination control programs). We calculate the underestimate in benefits if the geographic extent of the public good market is arbitrarily limited to one political jurisdiction.     

The Effect of Respondent Experience/Knowledge in the Elicitation of Contingent Values: An Investigation of Convergent Validity,Procedural Invariance and Reliability

Tests of convergent validity and procedural invariance were used to investigate whether individuals lacking direct experience with a commodity can provide valid responses to contingent-valuation questions eliciting ex post use values. Convergent validity between samples with and without experience was shown to hold for dichotomous-choice responses, but not for open-ended responses.