Kybernetika 61 no. 1, 1-17, 2025

Almost complete convergence of a recursive kernel estimator of the density with complete and censored independent data

Safia Leulmi, Sarra Leulmi, Kenza Assia Mezhoud and Soheir BelalouiDOI: 10.14736/kyb-2025-1-0001

Abstract:

In this paper, we firstly introduce a recursive kernel estimator of the density in the censored data case. Then, we establish its pointwise and uniform almost complete convergences, with rates, in both complete and censored independent data. Finally, we illustrate the accuracy of the proposed estimators throughout a simulation study.

Keywords:

rate of convergence, recursive kernel estimator, density, almost complete convergence, censored indepented data, right censored data

Classification:

62G20, 62N01, 62G05, 62G07

paper.pdf

References:

  1. A. Amiri: Rates of almost sure convergence of families of recursive kernel estimators. Ann. Inst. Stat. Univ. Paris LIV 3 (2010), 3-24.   CrossRef
  2. A. Amiri and M. El Machkouri: Recursive kernel density estimation for time series. IEEE Trans. 66, Issue: 10 (2020) 6378-6388.   DOI:10.1109/TIT.2020.3014797
  3. D. Bitouzé, B. Laurent and P. Massart: A dvoretzky-kiefer-wolfowitz type inequality for the Kaplan-Meier estimator. Ann. Inst. Henri Poincaré - Probab. Stat. 35 (1999), 735-63.   CrossRef
  4. Y. C. Chen: A tutorial on kernel density estimation and recent advances. Biostatist. Epidemiol. 1 (2017), 1, 161-187.   DOI:10.1080/24709360.2017.1396742
  5. P. Deheuvels: Sur l'estimation séquentielle de la densité. C. R. Acad. Sci. Paris Sér. A 276, (1973), 1119-1121.   CrossRef
  6. L. P. Devroye and T. J. Wagner: The strong uniform consistency of kernel density estimates in multivariate analysis - V. North-Holland Publishing Company 1980, pp. 59-77.   CrossRef
  7. Z. Guessoum and E. Ould-Said: On nonparametric estimation of the regression function under random censorship model. Stat. Decisions 26 (2008), 3, 159-177.   DOI:10.1524/stnd.2008.0919
  8. E. M. Kaplan and P. Meier: Nonparametric estimation from incomplete observations. J. Amer. Stat. Assoc. 53 (1958), 282, 457-481.   DOI:10.1080/01621459.1958.10501452
  9. S. Khardani and S. Semmar: Nonparametric conditional density estimation for censored data based on a recursive kernel. Electron. J. Stat. 8 (2014), 2541-2556.   DOI:10.1214/14-ejs960
  10. S. Khardani and Y. Slaoui: Adaptive recursive kernel conditional density estimators under censoring data. ALEA - Latin Amer. J. Probab. Math. Stat. 17 (2020), 389-417.   DOI:10.30757/ALEA.v17-16
  11. A. Kitouni, M. Boukeloua and F. Messaci: Rate of strong consistency for nonparametric estimators based on twice censored data. Stat. Probab. Lett. 96 (2015) , 255-261.   DOI:10.1016/j.spl.2014.10.005
  12. K. A. Mezhoud, Z. Mohdeb and S. Louhichi: Recursive kernel estimation of the density under $\eta$-weak dependence. J. Korean Stat. Soc. 33 (2014), 1065-1076.   DOI:10.1214/aoms/1177704472
  13. E. Parzen: On estimation of a probability density function and mode. Ann. Math. Stat. 33 (1962), 1065-1076.   DOI:10.1214/aoms/1177704472
  14. L. T. Tran: Recursive density estimation under dependence. IEEE Trans. Inform. Theory 35 (1989), 5, 1103-1108.   DOI:10.1109/18.42230
  15. E. J. Wegman and H. I. Davies: Remarks on some recursive estimators of a probability density. Ann. Stat. 7 (1979), 2, 316-327.   DOI:10.1214/aos/1176344616
  16. C. Wolverton and T. J. Wagner: Recursive estimates of probability densities. IEEE Trans. 5 (1969), 307-308.   DOI:10.1109/tssc.1969.300267
  17. W. Hoeffding: Probability inequalities for sums of bounded random variables. In: The Collected Works of Wassily Hoeffding, Springer 1994, pp. 409-426.   CrossRef