Drifts and Volatilities: Monetary Policies and Outcomes in the Post WWII U.S.

This paper extends the model of Cogley and Sargent to incorporate stochastic volatility and then estimates it for post World War II U.S. data in order to shed light on the following questions. Have aggregate time series responded through time-invariant linear impulse response functions to possibly heteroskedastic shocks? Or is it more likely that the impulse responses to shocks themselves have evolved over time because of drifting coefficients or other nonlinearities? Evidence is presented that shock variances evolved systematically over time, and so did the autoregressive coefficients of VARS. The conclusion is that much of our earlier evidence for drifting coefficients survives after we take stochastic volatility into account. This paper accumulates evidence inside an atheoretical statistical model. The patterns of time variation used revolve around whether it was bad monetary policy or bad luck that made inflation-unemployment outcomes worse in the 1970's than before or after.