Jean-Yves Pitarakis (University of Southampton)

Uncovering regimes in out of sample forecast errors from predictive regressions (with Anibal Emiliano Da Silva and Jesús Gonzalo)

Abstract:  We introduce a set of test statistics for assessing the presence of regimes in out of sample forecast errors produced by recursively estimated linear predictive regressions that can accommodate multiple highly persistent predictors. Our tests statistics are designed to be robust to the chosen starting window size, are shown to be consistent and to lead to null distributions that are free of nuisance parameters and hence robust to the degree of persistence of the predictors. Our method is subsequently applied to the predictability of the value premium and highlights the importance of state dependence in the dynamics of value stocks.