A Bayesian approach to counterfactual analysis with an application to the volatility reduction in U.S. real GDP

"In this paper, we develop a Bayesian approach to counterfactual analysis. Contrary to standard analysis based on classical point estimates, this approach provides a measure of estimation uncertainty for the counterfactual quantity of interest. We apply the counterfactual analysis to examine the sources of the recent volatility reduction in U.S. real GDP growth. For the application, we consider Blanchard and Quah's (1989) structural VAR model of output growth and unemployment that incorporates a long-run restriction to identify aggregate supply and aggregate demand shocks. We find strong evidence that the change in volatility since 1984 reflects a reduction in the size of structural shocks, rather than a change in the propagation of the shocks. Looking deeper, we find that aggregate supply shocks have played a larger role than aggregate demand shocks in the overall volatility reduction"--Federal Reserve Bank of St. Louis web site.