Mean square forecast error loss implies a bias–variance trade-off that suggests that structural breaks of small magnitude should be ignored. In this paper, we provide a test to determine whether modeling a structural break improves forecast accuracy. The test is near optimal even when the date of a local-to-zero break is not consistently estimable. The results extend to forecast combinations that weight the post-break sample and the full sample forecasts by our test statistic. In a large number of macroeconomic time series, we find that structural breaks that are relevant for forecasting occur much less frequently than existing tests indicate.

Additional Metadata
Keywords Forecasting, Squared error loss, Structural break test
JEL Hypothesis Testing (jel C12), Forecasting and Other Model Applications (jel C53)
Persistent URL dx.doi.org/10.1016/j.jeconom.2019.07.007, hdl.handle.net/1765/119740
Journal Journal of Econometrics
Citation
Boot, T. (Tom), & Pick, A. (2019). Does modeling a structural break improve forecast accuracy?. Journal of Econometrics. doi:10.1016/j.jeconom.2019.07.007