Bayesian nonlinear meta regression for benefit transfer

Abstract

In recent years numerous meta-regression models for benefit transfer in the context of environmental quality changes have been proposed by the academic literature and used by government agencies for policy making. We examine a set of popular specifications in terms of consistency with some basic utility-theoretic considerations, including the adding-up condition that is currently under much scrutiny by benefit transfer practitioners. We also compare these models based on econometric fit with underlying data, and ability to generate meaningful and efficient benefit transfer distributions. We find that our preferred Bayesian Nonlinear Meta-Regression Model (BNL-MRM) satisfies all theoretical requirements. Using a built-in nonlinear model search algorithm we show that it produces benefit estimates that are comparable or superior in efficiency to those flowing from better fitting, but theoretically flawed linear models that do not satisfy adding-up.