Dynamic Identification Using System Projections on Instrumental Variables
Abstract: We propose System Projections on Instrumental Variables (SP-IV) to identify structural relationships using regressions of impulse responses from local projections or vector autoregressions. Relative to 2SLS with distributed lags as instruments, SP-IV weakens exogeneity requirements and can improve efficiency and effective instrument strength. We describe inference under strong and weak identification. The SP-IV estimator outperforms other estimators of Phillips Curve parameters in simulations. We estimate the Phillips Curve implied by the main business cycle shock of Angeletos et al. (2020) and find that the impulse responses are consistent with weak but also relatively strong cyclical connections between inflation and unemployment.