Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/297446 
Year of Publication: 
2023
Series/Report no.: 
Bank of Canada Staff Working Paper No. 2023-61
Publisher: 
Bank of Canada, Ottawa
Abstract: 
Bayesian predictive synthesis (BPS) is a method of combining predictive distributions based on agent opinion analysis theory, which encompasses many common approaches to combining density forecasts. The key ingredient in BPS is a synthesis function. This is typically specified parametrically as a dynamic linear regression. In this paper, we develop a nonparametric treatment of the synthesis function using regression trees. We show the advantages of our tree-based approach in two macroeconomic forecasting applications. The first uses density forecasts for GDP growth from the euro area's Survey of Professional Forecasters. The second combines density forecasts of US inflation produced by many regression models involving different predictors. Both applications demonstrate the benefits-in terms of improved forecast accuracy and interpretability-of modeling the synthesis function nonparametrically.
Subjects: 
Econometric and Statistical Methods
JEL: 
C11
C32
C53
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.