Uncertainty-dependent Confidence Intervals for WIFO Economic Outlooks

This paper proposes a methodology for constructing confidence intervals for macroeconomic forecasts that directly incorporate quantitative measures of uncertainty – such as survey-based indicators, stock market volatility, and economic policy uncertainty. As a result, the interval width systematically adjusts to the prevailing uncertainty conditions. Since the approach enables more informative and context-sensitive statements than traditional, static methods that rely solely on past forecast errors, it facilitates and improves the communication of forecast results. An empirical application to past WIFO Economic Outlooks demonstrates its added value.