JOB MARKET PAPER
Semiparametric Identification of SVAR Models with Zero Lower Bound
Abstract: The US federal funds rate was frequently constrained to zero after the Great Recession, and the Federal Reserve has since turned to unconventional monetary policy tools. This paper uses a structural vector autoregression with a Zero Lower Bound (SVAR-ZLB) model to characterize the censored nominal interest rate and the effect of unconventional monetary policy. The existing literature relies on the assumption of zero short-run effect of the unconventional monetary policy to identify this model, but this paper studies model identification without relying on this assumption. In the case of empirically relevant non-Gaussian shocks, this paper proposes a generic semiparametric identification scheme to prove point identification, without relying on the parametric form of the shock distribution. The key problem of model identification that this paper solves is to deal semiparametrically with the non-linearity arising from censoring of the nominal interest rate at zero. An efficient Bayesian inference routine is designed to facilitate model estimation in practice. The empirical results suggest that the unconventional monetary policy has a small and transitory effect.
Abstract: The US federal funds rate was frequently constrained to zero after the Great Recession, and the Federal Reserve has since turned to unconventional monetary policy tools. This paper uses a structural vector autoregression with a Zero Lower Bound (SVAR-ZLB) model to characterize the censored nominal interest rate and the effect of unconventional monetary policy. The existing literature relies on the assumption of zero short-run effect of the unconventional monetary policy to identify this model, but this paper studies model identification without relying on this assumption. In the case of empirically relevant non-Gaussian shocks, this paper proposes a generic semiparametric identification scheme to prove point identification, without relying on the parametric form of the shock distribution. The key problem of model identification that this paper solves is to deal semiparametrically with the non-linearity arising from censoring of the nominal interest rate at zero. An efficient Bayesian inference routine is designed to facilitate model estimation in practice. The empirical results suggest that the unconventional monetary policy has a small and transitory effect.
WORKING PAPER
Local Projections vs. VARs: Lessons From Thousands of DGPs (with Mikkel Plagborg-Møller and Christian K. Wolf)
arXiv Code
Abstract: We conduct a simulation study of Local Projection (LP) and Vector Autoregression (VAR) estimators of structural impulse responses across thousands of data generating processes (DGPs), designed to mimic the properties of the universe of U.S. macroeconomic data. Our analysis considers various structural identification schemes and several variants of LP and VAR estimators, and we pay particular attention to the role of the researcher’s loss function. A clear bias-variance trade-off emerges: Because our DGPs are not exactly finite-order VAR models, LPs have lower bias than VAR estimators; however, the variance of LPs is substantially higher than that of VARs at intermediate or long horizons. Unless researchers are overwhelmingly concerned with bias, shrinkage via Bayesian VARs or penalized LPs is attractive.
arXiv Code
Abstract: We conduct a simulation study of Local Projection (LP) and Vector Autoregression (VAR) estimators of structural impulse responses across thousands of data generating processes (DGPs), designed to mimic the properties of the universe of U.S. macroeconomic data. Our analysis considers various structural identification schemes and several variants of LP and VAR estimators, and we pay particular attention to the role of the researcher’s loss function. A clear bias-variance trade-off emerges: Because our DGPs are not exactly finite-order VAR models, LPs have lower bias than VAR estimators; however, the variance of LPs is substantially higher than that of VARs at intermediate or long horizons. Unless researchers are overwhelmingly concerned with bias, shrinkage via Bayesian VARs or penalized LPs is attractive.
WORK IN PROGRESS
International Evidence on Credit and Economic Activity (with Christopher A. Sims)
Abstract: This paper incorporates quarterly macroeconomic data on an international panel into a large Structural Vector Autoregression (SVAR) model, in order to uncover the different causal channels from credit aggregates to future GDP. We find evidence that the shock in the real estate sector mainly contributed to the unusual negative relationship between credit and GDP in the Great Recession.
Abstract: This paper incorporates quarterly macroeconomic data on an international panel into a large Structural Vector Autoregression (SVAR) model, in order to uncover the different causal channels from credit aggregates to future GDP. We find evidence that the shock in the real estate sector mainly contributed to the unusual negative relationship between credit and GDP in the Great Recession.