Inferring Attribute Non-attendance from Discrete Choice Experiments: Implications for Benefit Transfer

Abstract

Typical convergent validity tests of benefit transfer based on stated preference data assume that willingness to pay (WTP) estimates have been accurately measured, and that differences in WTP arise from differences in observable and unobservable characteristics between the study and the policy sites. In this paper, we conduct a convergent validity test assuming equality of underlying preferences, but allow for the possibility that transfer errors arise from differences in the way that respondents process information in the preference elicitation tasks. Using data from an identical survey instrument applied to the population of two river basins in Spain, we obtain marginal and total WTP estimates for ecological improvements of water bodies and the corresponding transfer errors across sites. Results of equality constrained latent class (ECLC) models that infer attribute non-attendance (AN-A) are compared to results from mixed logit (MXL) models in WTP space. We find large absolute and relative differences in marginal and total WTP between sites for the MXL models, and significantly reduced transfer errors for the ECLC models. This paper therefore provides further evidence that AN-A can significantly affect environmental values derived from attribute-based stated preference methods and is the first to investigate the implications for benefit transfer.