OeNB-Freitagsseminar with Niko Hauzenberger

Nonparametrically combining SPF density forecasts for EA GDP growth

OeNB Freitagsseminar with Niko Hauzenberger, University of Strathclyde

Bayesian predictive synthesis (BPS) provides a method for combining multiple predictive distributions based on agent/expert opinion analysis theory and encompasses a range of existing density forecast pooling methods. 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.

Date
Friday, September 13, 2024 | Start: 11.00 a.m. | End: 12.30 p.m.

Venue
The event is planned both, online via Webex and onsite at the Oesterreichische Nationalbank, Otto-Wagner-Platz 3, 1090 Vienna, Veranstaltungssaal, Ground Floor. 

Please register by September 11, 2024, at the latest.