Combining Forecasts Based on Multiple Encompassing Tests in a Macroeconomic Core System

Mauro Costantini () and Robert M. Kunst ()

No 243, Economics Series from Institute for Advanced Studies

Abstract: We investigate whether and to what extent multiple encompassing tests may help determine weights for forecast averaging in a standard vector autoregressive setting. To this end we consider a new test-based procedure, which assigns non-zero weights to candidate models that add information not covered by other models. The potential benefits of this procedure are explored in extensive Monte Carlo simulations using realistic designs that are adapted to U.K. and to French macroeconomic data. The real economic growth rates of these two countries serve as the target series to be predicted. Generally, we find that the test-based averaging of forecasts yields a performance that is comparable to a simple uniform weighting of individual models. In one of our role-model economies, test-based averaging achieves some advantages in small samples. In larger samples, pure prediction models outperform forecast averages.

Keywords: Combining forecasts; encompassing tests; model selection; time series (search for similar items in EconPapers)
JEL-codes: C32 C53 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-cba, nep-ecm and nep-for
Date: 2009-09

Downloads: (external link)
http://www.ihs.ac.at/publications/eco/es-243.pdf First version, 2009 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:ihs:ihsesp:243

Ordering information: This working paper can be ordered from
Institute for Advanced Studies - Library, Stumpergasse 56, A-1060 Vienna, Austria

Access Statistics for this paper

More papers in Economics Series from Institute for Advanced Studies
Address: Stumpergasse 56, A-1060 Vienna, Austria
Contact information at EDIRC.
Series data maintained by Wolfgang Nessler ().