Information Criteria for Impulse Response Function Matching Estimation of DSGE Models

Abstract

We propose a new information criterion for impulse response function matching estimators (IRFMEs) of the structural parameters of dynamic stochastic general equilibrium (DSGE) macroeconomic models. An advantage of our procedure is that it allows researchers to select the impulse responses that are most informative about DSGE model parameters and ignore the rest. The idea of tossing out superfluous impulse responses motivates our Redundant Impulse Response Selection Criterion (RIRSC). The RIRSC is general enough to apply to impulse responses estimated by VARs, local projections, and simulation methods. We show that our criterion significantly affects estimates and inference about key parameters of two well-known New Keynesian DSGE models. Monte Carlo evidence indicates that the RIRSC yields gains in terms of finite sample bias as well as offering tests statistics whose behavior is better approximated by first order asymptotic theory. Thus, RIRSC improves on existing methods used to implement IRFMEs.

Keywords: impulse response function, matching estimator, redundant selection criterion

JEL Classification: C32, E47, C52, C53