Forecast Combinations in a DSGE-VAR Lab

Mauro Costantini, Ulrich Gunter, Robert Kunst

Publications: Contribution to journalArticlePeer Reviewed

Abstract

We explore the benefits of forecast combinations based on forecast-encompassing tests compared to simple averages and to Bates–Granger combinations. We also consider a new combination algorithm that fuses test-based and Bates–Granger weighting. For a realistic simulation design, we generate multivariate time series samples from a macroeconomic DSGE-VAR (dynamic stochastic general equilibrium–vector autoregressive) model. Results generally support Bates–Granger over uniform weighting, whereas benefits of test-based weights depend on the sample size and on the prediction horizon. In a corresponding application to real-world data, simple averaging performs best. Uniform averages may be the weighting scheme that is most robust to empirically observed irregularities.

Original languageEnglish
Pages (from-to)305-324
Number of pages20
JournalJournal of Forecasting
Volume36
Issue number3
Early online dateMay 2016
DOIs
Publication statusPublished - Apr 2017

Austrian Fields of Science 2012

  • 502025 Econometrics
  • 101018 Statistics
  • 502018 Macroeconomics

Keywords

  • SRA
  • VWL
  • TESTS
  • forecasting
  • BUSINESS CYCLES
  • model selection
  • time series
  • SHOCKS
  • FRICTIONS
  • GENERAL EQUILIBRIUM-MODELS
  • combining forecasts
  • US
  • encompassing tests

Cite this