Data Driven Rank Tests for Independence

摘要

In this paper, new rank tests for testing independence are introduced. The newtesting procedures are not only sensitive for grade linear correlation, but also for grade correlations of higher order polynomials. The number of polynomials involved is determined by the data. Model selection is combined with application of the score test in the selected model. The new tests have greater power-stability. Monte Carlo results clearly show this behavior. Theoretical support is obtained by proving consistency of the new tests.