Working Paper: CEPR ID: DP13746
Authors: Allan Timmermann; Yinchu Zhu
Abstract: Abstract This paper develops new methods for testing equal predictive accuracy in panels of forecasts that exploit information in the time series and cross-sectional dimensions of the data. Using a common factor setup, we establish conditions on cross-sectional dependencies in forecast errors which allow us to conduct inference and compare performance on a single cross-section of forecasts. We consider both unconditional tests of equal predictive accuracy as well as tests that condition on the realization of common factors and show how to decompose forecast errors into exposures to common factors and an idiosyncratic variance component. Our tests are demonstrated in an empirical application that compares IMF forecasts of country-level real GDP growth and inflation to private-sector survey forecasts and forecasts from a simple time-series model
Keywords: Economic forecasting; Panel data; GDP growth; Inflation forecasts
JEL Codes: No JEL codes provided
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| IMF forecasts of real GDP growth and inflation (F37) | different levels of accuracy compared to private sector survey forecasts (H68) |
| common economic shocks (E39) | forecast accuracy (C53) |
| forecasts that adapt slowly to changing conditions (C53) | underperform compared to those that incorporate forward-looking information (G17) |
| idiosyncratic variance component of IMF GDP growth forecasts (F29) | declining relative to that of private sector forecasts (H68) |
| IMF's current-year inflation forecasts (E31) | generally more accurate than those from private sector surveys (C83) |