Exact nonparametric tests of orthogonality and random walk in the presence of a drift parameter

In this paper, finite-sample nonparametric tests of conditional independence and random walk are extended to allow for an unknown drift parameter. The tests proposed are based on simultaneous inference methods and remain exact in the presence of general forms of feedback, nonnormality and heteroskedasticity. Further, in two simulation studies we confirm that the nonparametric procedures are reliable, and find that they display power comparable or superior to that of conventional tests.