Testing Kendall's τ for a large class of dependent sequences

Sinda Ammous (1)

1 MAP5 - UMR 8145 - Mathématiques Appliquées Paris 5

Let (X i , Y i) i∈Z be a stationary sequence of R 2-valued random variables. To test if X 1 and Y 1 are correlated in the sense of Kendall, we propose a robust correction of the usual Kendall test, valid for a large class of dependent sequences. We also show that the condition on the dependency coefficients is optimal in a certain sense, and we illustrate our results trough different sets of simulation.

Mots clés: U -statistics; Kendall's tau; hypothesis testing; bivariate dependent sequences; β-mixing sequences; Markov chains

Domaines: Théorie [stat.TH]

Sinda Ammous. Testing Kendall's τ for a large class of dependent sequences. 2019. ⟨hal-02320387⟩