Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/185582 
Year of Publication: 
2018
Series/Report no.: 
Tinbergen Institute Discussion Paper No. TI 2018-063/III
Publisher: 
Tinbergen Institute, Amsterdam and Rotterdam
Abstract: 
We suggest to extend the stacking procedure for a combination of predictive densities, proposed by Yao et al in the journal Bayesian Analysis to a setting where dynamic learning occurs about features of predictive densities of possibly misspecified models. This improves the averaging process of good and bad model forecasts. We summarise how this learning is done in economics and finance using mixtures. We also show that our proposal can be extended to combining forecasts and policies. The technical tools necessary for the implementation refer to filtering methods from nonlinear time series and we show their connection with machine learning. We illustrate our suggestion using results from Basturk et al based on financial data about US portfolios from 1928 until 2015.
Subjects: 
Bayesian learning
predictive density combinations
JEL: 
C11
C15
Document Type: 
Working Paper

Files in This Item:
File
Size
374.48 kB





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