Strong consistency result of a non parametric conditional mode estimator under random censorship for functional regressors

Khardani Salah , Baba Thiam (1)

1 LEM - Lille économie management - UMR 9221

Let (T, C, X) be a vector of random variables (rvs) where T, C, and X are the interest variable, a right censoring rv, and a covariate, respectively. In this paper, we study the kernel conditional mode estimation when the covariate takes values in an infinite dimensional space and is α-mixing. Under some regularity conditions, the almost complete convergence of the estimate with rates is established.

Mots clés: Almost complete convergence; censored data; functional data; Kaplan–Meier estimator; kernel mode estimator; strong mixing condition

Domaines: Méthodes et statistiques

Khardani Salah, Baba Thiam. Strong consistency result of a non parametric conditional mode estimator under random censorship for functional regressors. Communications in Statistics - Theory and Methods, 2016, 45 (7), pp.1863--1875. ⟨10.1080/03610926.2013.867997⟩. ⟨hal-01526023⟩