Testing Macroeconomic Policies with Sufficient Statistics


The evaluation of macroeconomic policy decisions has traditionally relied on the formulation of a specific economic model. In this work, we present a framework to assess policy decisions with minimal assumptions on the underlying structure of the economy. Given a policy maker's loss function, we propose a statistic -the Optimal Policy Perturbation (OPP)- to (i) test whether a policy choice is optimal, i.e. whether it minimizes the loss function, and (ii) test whether the policy maker's reaction function is optimal, i.e. whether the policy maker systematically under- or over-reacted to some variables or shocks. The OPP statistic does not require specifying an underlying model, as the OPP can be computed from a few sufficient statistics. We illustrate our policy evaluation framework by studying US monetary policy decisions.