A1500
Title: Density forecast frequency transformation via copulas
Authors: Matteo Mogliani - Banque de France (France) [presenting]
Florens Odendahl - Banque de France (France)
Abstract: The popular choice of using a direct forecasting scheme implies that the individual predictions do not embed information on cross-horizon dependence. However, this dependence is needed if the forecaster has to construct based on direct forecasts. These predictive objects are functions of several horizons, such as obtaining the annual average from quarter-on-quarter growth rates. To address this issue, copulas are proposed to combine the individual h-step-ahead predictive distributions into a joint predictive distribution. A Monte Carlo study demonstrated that the approach leads to a better approximation of the true predictive densities than alternative approximation methods. An empirical example shows how the method can be used to construct annual average forecasts using the quarter-on-quarter direct forecasts of a prior study. The method particularly appeals to practitioners for whom changing the direct forecasting specification is too costly.
