Assessing predictive accuracy in panel data models with long-range dependence

This paper proposes tests of the null hypothesis that model-based forecasts are uninformative in panels, allowing for individual and interactive fixed effects that control for cross-sectional dependence, endogenous predictors, and both short-range and long-range dependence. We consider a Diebold-Mariano style test based on comparison of the model-based forecast and a nested nopredictability benchmark, an encompassing style test of the same null, and a test of pooled uninformativeness in the entire panel. A simulation study shows that the encompassing style test is reasonably sized in finite samples, whereas the Diebold-Mariano style test is oversized. Both tests have non-trivial local power. The methods are applied to the predictive relation between economic policy uncertainty and future stock market volatility in a multi-country analysis.