Identifying the New Keynesian Phillips Curve

Phillips curves are central to discussions of ination dynamics and monetary policy. New Keynesian Phillips curves describe how past ination, expected future ination, and a measure of real marginal cost or an output gap drive the current ination rate. This paper studies the (potential) weak identication of these curves under GMM and traces this syndrome to a lack of persistence in either exogenous variables or shocks. We employ analytic methods to understand the identication problem in several sta-tistical environments: under strict exogeneity, in a vector autoregression, and in the canonical three-equation, New Keynesian model. Given U.S., U.K., and Canadian data, we revisit the empirical evidence and construct tests and condence intervals based on exact and pivotal Anderson-Rubin statistics that are robust to weak identication. These tests nd little evidence of forward-looking ination dynamics. JEL classication: E31; C32