Combining forecasts based on multiple encompassing tests in a macroeconomic core system

✍ Scribed by Mauro Costantini; Robert M. Kunst

• Publisher: John Wiley and Sons
• Year: 2010
• Tongue: English
• Weight: 154 KB
• Volume: 30
• Category: Article
• ISSN: 0277-6693
• DOI: 10.1002/for.1190

✦ Synopsis

This paper investigates 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 benefi ts of this procedure are explored in extensive Monte Carlo simulations using realistic designs that are adapted to UK and to French macroeconomic data, to which trivariate vector autoregressions (VAR) are fi tted. Thus simulations rely on potential data-generating mechanisms for macroeconomic data rather than on simple but artifi cial designs. We run two types of forecast 'competitions'. In the fi rst one, one of the model classes is the trivariate VAR, such that it contains the generating mechanism. In the second specifi cation, none of the competing models contains the true structure. The simulation results show that the performance of test-based averaging is comparable to uniform weighting of individual models. In one of our role model economies, test-based averaging achieves advantages in small samples. In larger samples, pure prediction models outperform forecast averages.