About Local Projection Impulse Response Function Reliability

38 Pages Posted: 27 Aug 2018

See all articles by Luca Brugnolini

Luca Brugnolini

affiliation not provided to SSRN

Date Written: August 9, 2018


I compare the performance of the vector autoregressive (VAR) model impulse response function estimator with the Jordà (2005) local projection (LP) methodology. In a Monte Carlo experiment, I demonstrate that when the data generating process is a well-specified VAR, the standard impulse response function estimator is the best option. However, when the sample size is small, and the model lag-length is misspecified, I prove that the local projection estimator is a competitive alternative. Finally, I show how to improve the local projection performance by fixing the lag-length at each horizon.

Keywords: VAR, information criteria, lag-length, Monte Carlo

JEL Classification: C32, C52, C53, E52

Suggested Citation

Brugnolini, Luca, About Local Projection Impulse Response Function Reliability (August 9, 2018). CEIS Working Paper No. 440, Available at SSRN: https://ssrn.com/abstract=3229218 or http://dx.doi.org/10.2139/ssrn.3229218

Luca Brugnolini (Contact Author)

affiliation not provided to SSRN

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics