Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/107837
Authors: 
Claeskens, Gerda
Magnus, Jan
Vasnev, Andrey
Wang, Wendun
Year of Publication: 
2014
Series/Report no.: 
Tinbergen Institute Discussion Paper 14-127/III
Abstract: 
This papers offers a theoretical explanation for the stylized fact that forecast combinations with estimated optimal weights often perform poorly in applications. The properties of the forecast combination are typically derived under the assumption that the weights are fixed, while in practice they need to be estimated. If the fact that the weights are random rather than fixed is taken into account during the optimality derivation, then the forecast combination will be biased (even when the original forecasts are unbiased) and its variance is larger than in the fixed-weights case. In particular, there is no guarantee that the 'optimal' forecast combination will be better than the equal-weights case or even improve on the original forecasts. We provide the underlying theory, some special cases and an application in the context of model selection.
Subjects: 
forecast combination
optimal weights
model selection
JEL: 
C53
C52
Document Type: 
Working Paper

Files in This Item:
File
Size
137.95 kB





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