This paper develops bootstrap methods for testing whether, in a finite sample, competing out-of-sample forecasts from nested models are equally accurate. Most prior work on forecast tests for nested models has focused on a null hypothesis of equal accuracy in population — basically, whether coefficients on the extra variables in the larger, nesting model are zero. We instead use an asymptotic approximation that treats the coefficients as non-zero but small, such that, in a finite sample, forecasts from the small model are expected to be as accurate as forecasts from the large model. Under that approximation, we derive the limiting distributions of pairwise tests of equal mean square error, and develop bootstrap methods for estimating critical values. Monte Carlo experiments show that our proposed procedures have good size and power properties for the null of equal finite-sample forecast accuracy. We illustrate the use of the procedures with applications to forecasting stock returns and inflation.
follow @stlouisfed