Recent literature has questioned statistical inference in predictive regression with persistent regressors, suggesting a possible explanation for puzzles such as the forward premium anomaly.We therefore revisit this puzzle using three alternative econometric methods known to provide reliable inference in the presence of persistent conditioning variables. While they provide less evidence against forward rate unbiasedness than traditional predictive regression tests, we still reject using at least one method for all six currencies. Thus, while the econometric problems inherent in predictive regression likely play a role in this anomaly, we are left with an economic puzzle even after accounting for their influence.
JEL classification: F31, C22