Working Paper: CEPR ID: DP9576
Authors: Refet S. Gürkaynak; Büri̇n Kısacıkoglu; Barbara Rossi
Abstract: Recently, it has been suggested that macroeconomic forecasts from estimated DSGE models tend to be more accurate out-of-sample than random walk forecasts or Bayesian VAR forecasts. Del Negro and Schorfheide(2013) in particular suggest that the DSGE model forecast should become the benchmark for forecasting horse races. We compare the real-time forecasting accuracy of the Smets and Wouters DSGE model with that of several reduced form time series models. We first demonstrate that none of the forecasting models is efficient. Our second finding is that there is no single best forecasting method. For example, typically simple AR models are most accurate at short horizons and DSGE models are most accurate at long horizons when forecasting output growth, while for inflation forecasts the results are reversed. Moreover, the relative accuracy of all models tends to evolve over time. Third, we show that there is no support the common practice of using large-scale Bayesian VAR models as the forecast benchmark when evaluating DSGE models. Indeed,low-dimensional unrestricted AR and VAR forecasts may forecast more accurately.
Keywords: Bayesian VAR; DSGE; Forecast Comparison; Forecast Optimality; Forecasting; Real-time Data
JEL Codes: C22; C52; C53
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| DSGE model (E13) | forecasting accuracy (output better than autoregressive methods at longer horizons) (C53) |
| DSGE model (E13) | forecasting accuracy (less accurate for inflation forecasts compared to simpler autoregressive models) (C53) |
| model complexity (C52) | forecasting performance (large Bayesian VAR models are over-parameterized) (C53) |
| forecasting method (C53) | forecasting accuracy (context-dependent performance) (C53) |