Can Long-Run Restrictions Identify Technology Shocks?

Publisher Website
Google Scholar
Abstract
Gal´i's innovative approach of imposing long-run restrictions on a vector autoregression (VAR) to iden- tify the eects of a technology shock has become widely utilized. In this paper, we investigate its reliability through Monte Carlo simulations using calibrated business cycle models. We find it encour- aging that the impulse responses derived from applying the Gal´i methodology to the artificial data generally have the same sign and qualitative pattern as the true responses. However, we find consid- erable estimation uncertainty about the quantitative impact of a technology shock on macroeconomic variables, and little precision in estimating the contribution of technology shocks to business cycle fluc- tuations. More generally, our analysis emphasizes that the conditions under which the methodology performs well appear considerably more restrictive than implied by the key identifying assumption, and depend on model structure, the nature of the underlying shocks, and variable selection in the VAR. This cautions against interpreting responses derived from this approach as model-independent stylized facts.