Working Paper: CEPR ID: DP4401
Authors: M. Hashem Pesaran; Allan G. Timmermann
Abstract: This Paper develops a theoretical framework for the analysis of small sample properties of forecasts from general autoregressive models under structural breaks. Finite-sample results for the mean-squared forecast error of one-step-ahead forecasts are derived, both conditionally and unconditionally, and numerical results for different types of break specifications are presented. It is established that forecast errors are unconditionally unbiased even in the presence of breaks in the autoregressive coefficients and/or error variances so long as the unconditional mean of the process remains unchanged. Insights from the theoretical analysis are demonstrated in Monte Carlo simulations and on a range of macroeconomic time series from G7 countries. The results are used to draw practical recommendations for the choice of estimation window when forecasting from autoregressive models subject to breaks.
Keywords: Autoregression; MSFE; Rolling Window Estimator; Small Sample Properties of Forecasts; Structural Breaks
JEL Codes: C22; C53
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Forecast errors are unconditionally unbiased (C51) | Forecast errors are unconditionally unbiased in the presence of structural breaks (C51) |
| Size and direction of structural breaks (C22) | Optimal estimation window minimizes RMSFE (C51) |
| Including pre-break data (Y10) | Reduces bias and variance of forecast errors (C53) |
| Using pre-break data (Y10) | Decline in RMSFE (C22) |
| Expanding window methods (C59) | Outperform rolling window methods (C22) |
| Including pre-break data (Y10) | Optimize forecasting performance (C53) |