By Laura Veldkamp and Anna Orlik
For decades, macroeconomists have searched for shocks that are plausible drivers of business cycles. A recent advance in this quest has been to explore uncertainty shocks. Researchers use a variety of forecast and volatility data to justify heteroskedastic shocks in a model, which can then generate realistic cyclical uctuations. But the relevant measure of uncertainty in most models is the conditional variance of a forecast. When agents form such forecasts with state, parameter and model uncertainty, neither forecast dispersion nor innovation volatilities are good proxies for conditional forecast variance. We use observable data to select and estimate a forecasting model and then ask the model to inform us about what uncertainty shocks look like and why they arise.
There is a cottage industry trying to find ways to embed variable uncertainty into business cycle models. This paper differs in that it refines the measurement of uncertainty shocks by getting closer to how market participants form their expectations, in particular with model uncertainty, and then get surprised. This refinement is not inocuous, it allows agents to be uncertain about endogenous variables, not only exogenous ones like total factor productivity. The method can be extended to any forecasting rule used in business forecasting, for example.