CMStatistics 2022: Start Registration
View Submission - CFE
Title: Dynamic combination and calibration of forecasts Authors:  Dario Palumbo - Homerton College, University of Cambridge (Italy) [presenting]
Roberto Casarin - University Ca' Foscari of Venice (Italy)
Francesco Ravazzolo - Free University of Bozen-Bolzano (Italy)
Abstract: A density calibration and combination model is proposed that dynamically calibrates and combines predictive distributions. The time-varying calibration and combination weights are fitted by an observation-driven model with dynamics inferred by the score of the assumed conditional likelihood of the data-generating process. Through simulations, we show that the model is very flexible and can handle different shapes, instability and model uncertainty. An empirical application to short-term wind speed predictions documents the large instability of individual model performance and their calibration properties, favouring our model in terms of predictive accuracy.