A Bayesian Approach to Counterfactual Analysis of Structural Change

In this paper, we develop a Bayesian approach to counterfactual analysis of structural change. Contrary to previous analysis based on classical point estimates, this approach provides a straightforward measure of estimation uncertainty for the counterfactual quantity of interest. We apply the Bayesian counterfactual analysis to examine the sources of the volatility reduction in U.S. real GDP growth in the 1980s. Using a structural VAR model of output growth and the unemployment rate, we find strong statistical support for the idea that a counterfactual change in the size of structural shocks only, with no corresponding change in propagation, would have produced the same overall volatility reduction that actually occurred. Looking deeper, we find evidence that a counterfactual change in the size of aggregate supply shocks only would have generated a larger volatility reduction than a counterfactual change in the size of aggregate demand shocks only. We show that these results are consistent with a standard monetary VAR, for which counterfactual analysis also suggests the importance of shocks in generating the volatility reduction, but with the counterfactual change in monetary shocks only generating a small reduction in volatility