Monte Carlo Benchmarks for Discrete Response Valuation Methods

Abstract

This paper argues that the widespread belief that discrete contingent valuation (CV) questions yield substantially larger estimates of the mean (and the median) willingness to pay (WTP) for nonmarket environmental resources in comparison to estimates from open-ended CV questions is unfounded. A set of Monte Carlo experiments estimate the factors influencing the performance of WTP estimates based on discrete response models. Most of the error in the WTP estimates arises from the specification errors that are common in most of the empirical models used in the literature. These experiments suggest models based on choices where WTP is dominated by non use (or passive use) values are likely to have smaller errors than where large use values influence these decisions.

Empirical implications of response acquiescence in discrete‐choice contingent valuation

“…This study echoes the conclusion of Huang and Smith's Monte Carlo exercise [25], which found Artificial DC c adjusted for anchoring that even small misspecification of functional forms and the error terms could be translated into large differences in WTP estimates. However, in relation to the literature on comparing different elicitation formats, Huang and Smith's conclusion was based on the assumption that values elicited from the OE format represent 'true' WTP values.…”

“…However, while these sorts of explanations may support the view that the difference in WTP computed from OE and DC data may be attributable to the different elicitation techniques, recent comparisons have also focused on the effect of statistical treatment in this issue [17,25,26]. In the health literature, DC responses are typically estimated using a parametric econometric model, which requires distributional assumptions to be made [11,12,27].…”

Designing a forest-energy policy to reduce forest fires in Galicia (Spain): A contingent valuation application

“…4 Huang and Smith (1998) argue that the conclusions about the WTP obtained using the dichotomous-choice and openended formats are still premature, given that there still is not enough empirical evidence. and knowledge of electricity rates and taxes for homes) and understanding of electricity production (knowledge of the structure of electricity production, household electricity consumption rates compared to the electricity for industrial users, identification of renewable and non-renewable energy sources and knowledge of problems associated with electricity production).…”

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

“…While there have been numerous comparisons of welfare estimates from dichotomous-choice and open-ended questions (see Huang and Smith 1998), there are reasons to compare these question formats in other dimensions. It has been argued that dichotomous-choice questions are incentive compatible and that this is not the case for open-ended questions (Carson et al 2000).…”