Working Papers

• What Can We Gain from Pooling VAR and Local Projection Impulse Response Functions?

(Job Market Paper)

Abstract: I show that pooling Vector Autoregression (VAR) and Local Projection (LP) impulse response functions (IRFs) may address the bias-variance trade-off in IRF estimation. I also propose a "sequence-of-block bootstrap" method, designed to construct confidence intervals for the pooled IRFs. I document three key findings: (i) Monte Carlo exercises suggest that the pooling method outperforms both VAR and LP in terms of root mean squared error.  (ii) The sequence-of-block bootstrap method yields confidence intervals that tend to be more accurate than standard residual-based bootstrap intervals. (iii) Finally, the pooling and sequence of block bootstrap approaches produce sensible results in a monetary policy application.