Prediction intervals for economic fixed-event forecasts

TL;DR

This paper develops specialized regression-based prediction intervals for fixed-event economic forecasts, addressing the lack of uncertainty measures in typical point forecasts for GDP growth in Germany and the US.

Contribution

It introduces constraint-imposing regression methods tailored for fixed-event forecasting to construct meaningful prediction intervals.

Findings

Effective prediction intervals for GDP growth are constructed.

Methods are demonstrated on German and US economic data.

The approach improves uncertainty quantification in fixed-event forecasts.

Abstract

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. 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 develop regression methods that impose constraints motivated by the problem at hand, and use these methods to construct prediction intervals for gross domestic product (GDP) growth in Germany and the US.