Constructing a conditional GDP fan chart with an application to French business survey data

Abstract

Interval confidence and density forecasts, notably in the form of “fan charts”, are useful tools to describe the uncertainty inherent to any point forecast. However, the existing techniques suffer from several drawbacks. We propose a new method to represent uncertainty in realtime that is conditional upon the economic outlook, non-parametric and reproducible. Moreover, we build a Forecasting Risk Index associated with our fan chart to measure the intrinsic difficulty of the forecasting exercise. Using balances of opinion of different business surveys carried out by the French statistical institute INSEE, our GDP fan chart efficiently captures the growth stall during the crisis on a real-time basis. Our Forecasting Risk Index has increased substantially in this period of turbulence, showing signs of growing uncertainty. Keywords: Density forecast, quantile regressions, business tendency surveys, fan charts JEL classification: E32, E37, E66, C22