A Note on Variance Decomposition with Local Projections

Working Paper: NBER ID: w23998

Authors: Yuriy Gorodnichenko; Byoungchan Lee

Abstract: We propose and study properties of several estimators of variance decomposition in the local-projections framework. We find for empirically relevant sample sizes that, after being bias corrected with bootstrap, our estimators perform well in simulations. We also illustrate the workings of our estimators empirically for monetary policy and productivity shocks.

Keywords: Variance Decomposition; Local Projections; Monetary Policy; Productivity Shocks

JEL Codes: C53; E37; E47


Causal Claims Network Graph

Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.


Causal Claims

CauseEffect
contractionary monetary policy shocks (E39)decrease in output (E23)
contractionary monetary policy shocks (E39)decrease in prices (E31)
positive total factor productivity shocks (O49)increase in output (E23)
positive total factor productivity shocks (O49)decrease in prices (E31)
monetary policy shocks (E39)variations in output (C67)
monetary policy shocks (E39)variations in inflation (E31)
total factor productivity shocks (O49)variations in output (C67)
total factor productivity shocks (O49)variations in inflation (E31)

Back to index