Understanding Error Structures and Exploiting Panel Data in Meta-analytic Benefit Transfers

A regression meta-analysis is a statistical summary of results from a set of empirical studies. While, a meta-analysis is typically used to drawn inferences regarding the collective insights from an empirical literature, a regression meta-analysis can also be used to predict outcomes as a substitute for the conduct of a new study. Within the nonmarket-valuation literature benefit transfers are a special case of prediction where value estimates collected for one purpose are used as a basis for predicting value for unstudied applications. Balancing against the prediction opportunities provided by a regression meta-analysis is the potential prediction error. This paper considers some of these issues in the estimation of a regression meta-analysis to support prediction of nonmarket values for applications where an original study does not exist. We do not purport to address all elements of the error structure and prediction issues, but to present a more coherent focus to enhance future research on the validity and reliability of benefit-function transfers, and ultimately assist in enhancing the credibility of benefit transfers to support policy analyses.