We study the benefits of forecast combinations based on forecast-encompassing tests relative to uniformly weighted forecast averages across rival models. For a realistic simulation design, we generate multivariate time-series samples of size 40 to 200 from a macroeconomic DSGE-VAR model. Constituent forecasts of the combinations are formed from four linear autoregressive specifications, one of them a more sophisticated factor-augmented vector autoregression (FAVAR). The forecaster is assumed not to know the true data-generating model. Results depend on the prediction horizon. While one-step prediction fails to support test-based combinations at all sample sizes, the test-based procedure clearly dominates at prediction horizons greater than two.
combining forecasts encompassing tests model selection time series DGSE-VAR model