The fixed-event forecasting setup is common in economic policy. It involves a sequence of forecasts of the same (’fixed’) predictand, so that the difficulty of the forecasting problem decreases over time. For example, forecasting the annual inflation rate for 2022 was a very difficult task in January 2021, but a rather easy task in November 2022. In practice, fixed-event point forecasts are typically published without a quantitative measure of uncertainty. To construct such a measure, we consider forecast postprocessing techniques tailored to the fixed-event case. We propose parametric and nonparametric regression methods that are motivated by the problem at hand, and use these methods to construct prediction intervals for economic growth and inflation in Germany and the US. Joint paper with Hendrik Plett.
- Fabian Krüger (Karlsruhe Institute of Technology)
1018 WB Amsterdam