Models for sample selection bias in contingent valuation: Application to forest biodiversity

Abstract

In this article, we use two formats of contingent valuation (CV) questions to elicit willingness to pay (WTP) for maintaining biodiversity in forests: the dichotomous choice (DC) or referendum format and the open-ended (OE) question. A large population of French households were surveyed nationwide by phone. The sample of respondents was later divided into two subsamples: people who have recreational activities in forests and those who do not. This dichotomy potentially biases WTP as the decision to have recreational activities in forests is endogenous. We estimate a Probit model with sample selection to correct this bias in the DC question. With the OE question, a second source of selection bias related to non-random censoring is present: some respondents are unwilling to pay. We use an extension of Heckman's approach to the double selection problem. The empirical application shows that ARTICLE IN PRESS www.elsevier.de/jfe 1104-6899/$ -see front matter (S. Garcia).ignoring these sample selection problems leads to biased estimates of mean WTP for biodiversity in a national survey for France.

‘Been There Done That’: Disentangling Option Value Effects from User Heterogeneity When Valuing Natural Resources with a Use Component

“…Hence, the application of a separate probit model would lead to a loss of econometric efficiency. The simultaneous bivariate probit formulation applied in Garcia et al (2007), which resembles more our own analysis below than the one in Garcia et al (2008), shows efficiency gains in the estimation procedure but a relatively small correction of the mean WTP estimate.…”

“…As in Whitehead (2006), the loss in econometric efficiency was avoided by the simultaneous estimation of two equations: one for the WTP for the curbside recycling program and another one for decision whether or not to reduce the container size, as the authors detected endogeneity behind these two decisions. Garcia et al (2007Garcia et al ( , 2008 in their recent study of WTP for forest biodiversity preservation in France used a similar approach. In particular, these authors argue that the value a respondent places on biodiversity preservation may vary depending on whether the respondent is a forest visitor or not.…”

“…That is, the decision whether or not to participate in forest recreational activities might be correlated with the decision to pay to support forest biodiversity. Using a bivariate probit model, Garcia et al (2008) showed the significant dependence between these two decisions. Hence, the application of a separate probit model would lead to a loss of econometric efficiency.…”

Selected results of the survey focused on the economic assessment of forest ecosystem services

“…The contingent valuation method has been the focus of intensive study for several decades, resulting in a number of works describing theory and methods in relation to the valuation of natural resources, environmental amenities and public goods (see e.g. Bateman, Willis 2001;Champ et al 2003;Pearce et al 2006;Mayor et al 2007;Garcia et al 2009). …”

Pointwise Convergence of a Nonparametric Estimator of Regression in a Measurable Space Used in Contingent Valuation Method

“…Recently, several studies have underlined the significance of an individual's location on the WTP (Garcia et al 2009; Loomis et al 2000; Loureiro and Ojea 2008;Wang et al 2007). Beaumais et al (2008), evaluating preservation of the Seine Estuary wetlands, found significant differences in WTP between inhabitants in the rural countryside and those of large cities (who were ready to contribute more to protect the wetlands).…”