In this article, we establish the almost sure convergence of a family of recursive estimators when the data are censored checking widely orthant dependence (WOD). The dependence hypothesis gives this work a certain originality because most often, the study of censored data is done with an independence hypothesis and in reality the real data are often dependent.

density, kernel estimator, widely orthant dependent, almost sure convergence

Received: August 14, 2024; Accepted: October 23, 2024; Published: November 11, 2024

How to cite this article: Mouhamed Mar and Saliou DIOUF, On the convergence of recursive kernel density estimators for widely orthant dependent and censored data, Far East Journal of Theoretical Statistics 69(1) (2025), 39‑54. https://doi.org/10.17654/0972086325002

This Open Access Article is Licensed under Creative Commons Attribution 4.0 International License

References:
[1] P. Deheuvels and J. Einmahl, Functional limit laws for the increments of Kaplan-Meier product limit processes and applications, Ann. Probab. 28 (2000), 1301-1335.
[2] M. Duflo, Random iterative models, Collection Applications of Mathematics, Springer-Verlag, Berlin, Heidelberg, Vol. 34, 1997.
DOI: 10.1007/978-3-662-12880-0.
[3] A. Jmaei, Y. Slaoui and W. Dellagi, Recursive distribution estimators defined by stochastic approximation method using Bernstein polynomials, J. Nonparametr. Stat. 29 (2017), 792-805. DOI 10.1080/10485252.2017.1369538.
[4] E. L. Kaplan and P. Meier, Non parametric estimation from incomplete observations, J. Amer. Statist. Assoc. 53 (1958), 457-481.
[5] H. Robbins and S. Monro, A stochastic approximation method, Ann. Math. Stat. 22(2) (1951), 400-407.
[6] Y. Slaoui, Smoothing parameters for recursive kernel density estimators under censoring, Communications on Stochastic Analysis 13(2) (2019), Article 2.
[7] B. Tsybakov, Recursive estimation of the mode of a multivariate distribution, Problems Inform. Transmission 26(1) (1990), 31-37.
[8] Y. Li, Y. Zhou and C. Liu, On the convergence rates of kernel estimator and hazard estimator for widely dependent samples, J. Inequal. Appl. 2018 (2018), Article number 71. https://doi.org/10.1186/s13660-018-1659-1.