Combining Predictive Densities Using Bayesian Filtering with Applications to Us Economics Data

Arbeitspapier

Using a Bayesian framework this paper provides a multivariate combination approach to prediction based on a distributional state space representation of predictive densities from alternative models. In the proposed approach the model set can be incomplete. Several multivariate time-varying combination strategies are introduced. In particular, a weight dynamics driven by the past performance of the predictive densities is considered and the use of learning mechanisms. The approach is assessed using statistical and utility-based performance measures forevaluating density forecasts of US macroeconomic time series and of surveys of stock market prices.

Angaben zum Objekt

• ISBN: 978-82-7553-586-1
• Sprache: Englisch

Verweise und Beziehungen

• Erschienen in: Series: Working Paper ; No. 2010/29

Klassifikation und Themen

• Klassifikation: Wirtschaft ; Bayesian Analysis: General ; Statistical Simulation Methods: General ; Forecasting Models; Simulation Methods ; Prices, Business Fluctuations, and Cycles: Forecasting and Simulation: Models and Applications
• Thema: Bayesian filtering ; sequential Monte Carlo ; density forecast combination ; survey forecast

Beteiligte, Orts- und Zeitangaben

• Ereignis: Geistige Schöpfung
• (wer): Billio, Monica ; Casarin, Roberto ; Ravazzolo, Francesco ; van Dijk, Herman K.
• Ereignis: Veröffentlichung
• (wer): Norges Bank
• (wo): Oslo
• (wann): 2010

Weitere Informationen

• Handle: http://hdl.handle.net/10419/209974
• Letzte Aktualisierung: 10.03.2025, 11:42 MEZ