A Sufficient Statistics Approach for Macro Policy Evaluation

The evaluation of macroeconomic policy decisions has traditionally relied on the formulation of a specific economic model. In this work, we show that two statistics are sufficient to detect, often even correct, non-optimal policies, i.e., policies that do not minimize the loss function. The two sufficient statistics are (i) forecasts for the policy objectives conditional on the policy choice, and (ii) the impulse responses of the policy objectives to policy shocks. Both statistics can be estimated without relying on a specific structural economic model. We illustrate the method by studying U.S. monetary policy decisions.