Meta-Analysis, Benefit Transfer, and Methodological Covariates: Implications for Transfer Error

摘要: Meta-regression models in the valuation literature demonstrate that willingness to pay estimates vary according methodological factors. Neither theory nor characteristics of policy sites dictate treatment associated covariates within benefit transfer, however, and provides few insights into potential impacts common empirical treatments. This paper introduces a method systematically characterize impact variables on transfer error. Using repeated leave-one-out convergent validity framework, analysis contrasts errors for hypothetical ideal case which correct covariate treatments are known realistic is unknown. Results indicate assumption mean values leads only modest increase error relative found case.