Boucher, Christophe; Maillet, Bertrand - Centre d'Économie de la Sorbonne, Université Paris 1 … - 2011
Researchers in finance very often rely on highly persistent Ñ nearly integrated Ñ explanatory variables to predict returns. This paper proposes to stand up to the usual problem of persistent regressor bias, by detrending the highly auto-correlated predictors. We find that the statistical...