Working Paper: NBER ID: w11538
Authors: Andrew Ang; Geert Bekaert; Min Wei
Abstract: Surveys do! We examine the forecasting power of four alternative methods of forecasting U.S. inflation out-of-sample: time series ARIMA models; regressions using real activity measures motivated from the Phillips curve; term structure models that include linear, non-linear, and arbitrage-free specifications; and survey-based measures. We also investigate several optimal methods of combining forecasts. Our results show that surveys outperform the other forecasting methods and that the term structure specifications perform relatively poorly. We find little evidence that combining forecasts using means or medians, or using optimal weights with prior information produces superior forecasts to survey information alone. When combining forecasts, the data consistently places the highest weights on survey information.
Keywords: No keywords provided
JEL Codes: E31; E37; E43; E44
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| survey forecasts (G17) | improved forecasting accuracy (C53) |
| term structure information (Y20) | inferior predictions (C52) |
| combining forecasts (C53) | weak forecasting accuracy (C53) |