STRONG APPROXIMATIONS OF BIVARIATE UNIFORM EMPIRICAL PROCESSES

Citation
N. Castelle et F. Laurentbonvalot, STRONG APPROXIMATIONS OF BIVARIATE UNIFORM EMPIRICAL PROCESSES, Annales de l'I.H.P. Probabilites et statistiques, 34(4), 1998, pp. 425-480
Citations number
20
Categorie Soggetti
Statistic & Probability","Statistic & Probability
ISSN journal
02460203
Volume
34
Issue
4
Year of publication
1998
Pages
425 - 480
Database
ISI
SICI code
0246-0203(1998)34:4<425:SAOBUE>2.0.ZU;2-B
Abstract
In 1975, Komlos, Major and Tusnady constructed a strong approximation of the uniform empirical process {alpha(n)(t), n greater than or equal to 1, t is an element of [0, 1]} by a Gaussian Kiefer process. We sho w that the global error bound provided by Komlos, Major and Tusnady ma y be improved by considering only local approximation. Moreover we pro vide explicit constants. We also prove a local refinement for Tusnady' s Gaussian strong approximation of the bidimensional uniform empirical process. The main technical tool we use is a non asymptotic normal ap proximation of the hypergeometric distribution. (C) Elsevier, Paris.