Predictability Tests for the Expectations Hypothesis in the Presence of MA Disturbances

This paper develops new inference methods for testing the expectations hypothesis in a general econometric framework. In particular, we consider nonparametric tests of the predictability of excess returns in the presence of MA disturbances. We discuss several alternatives of aggregation and investigate their asymptotic and finite sample properties. We illustrate that the serial dependence tests can also provide valid information for identifying particular economic alternatives when testing the expectations hypothesis in foreign exchange markets