I am on my way today to give a talk in the department of Quantitative Economics at the University of Maastricht. This is joint work with two coauthors, Sophocles Mavroeidis (from Oxford University) and Zhaoguo Zhan from Tsinghua University in Beijing.
This paper focuses on the identification scheme known as "long-run restrictions", proposed by Blanchard & Quah (1989. This assumes that certain shocks (e.g. "demand" shocks) have no permanent effect on certain economic variables (e.g., output). Long-run restrictions are a popular identification scheme for some empirical economic models (so called SVARs), because they seemto be less contentious than short-run identifying restrictions, see e.g., Christiano, Eichenbaum and Vigfusson (2007) and the associated comments and
However, it is well-known that long-run restrictions can lead to weak identification, i.e. the model cannot be estimated, and there is presently no method of inference that is fully robust to this problem. The main
difficulty is that the features that make identification weak in this context also work to generate strong persistence. Therefore, all the available weak identification robust methods of inference, are inapplicable because they rely on stationary asymptotics.
In this paper, we develop a method of inference that is robust to weak identification as well as near non-stationarity and we are able to settle vexed debates on the impact of technology or productivity shocks on employment.