Presenter: Tatevik Sekhposyan
Affiliation: Texas A&M University, Department of Economics
Date: January 10, 2023
Time: 13:00 GMT (15:00 Israel Time)
Abstract: We propose to decompose uncertainty into several components, such as uncertainty about the probability distribution generating the data (broadly speaking, model-misspecification) and uncertainty about the odds of the outcomes when the probability distribution is known (risk). These components can be either estimated using past data (“ex-post measures”) or be forward-looking in nature (“ex-ante measures”). We use the U.S. Survey of Professional Forecaster’s (SPF) density forecasts to quantify overall uncertainty as well as the evolution of the different components of uncertainty over time and investigate their importance for macroeconomic fluctuations and for understanding several uncertainty indices proposed in the literature.