← Search

The Review of Economics and Statistics Vol. 96 No. 4 2014

A Flexible Finite-Horizon Alternative to Long-Run Restrictions with an Application to Technology Shocks

Neville Francis1; Michael T. Owyang2; Jennifer E. Roush3; Riccardo DiCecio2

1 University of North Carolina · 2 Federal Reserve Bank of St. Louis · 3 Federal Reserve

Abstract

Recent studies using long-run restrictions question the validity of the technology-driven real business cycle hypothesis. We propose an alternative identification that maximizes the contribution of technology shocks to the forecast-error variance of labor productivity at a long but finite horizon. In small-sample Monte Carlo experiments, our identification outperforms standard long-run restrictions by significantly reducing the bias in the short-run impulse responses and raising their estimation precision. Unlike its long-run restriction counterpart, when our Max Share identification technique is applied to U.S. data, it delivers the robust result that hours worked responds negatively to positive technology shocks.

DOI
10.1162/rest_a_00406
Volume
96
Issue
4
Pages
638-647
Language
en
Sources
openalex crossref

Cite