paper

Empirical process of long-range dependent sequences when parameters are estimated

arXiv:math/0702089

Abstract

In this paper we study the asymptotic behaviour of empirical processes when parameters are estimated, assuming that the underlying sequence of random variables is long-range dependent. We show completely different phenomena compared to i.i.d. situation, as well as compared to ordinary empirical processes of long range dependent sequences. Applications include Kolmogorov-Smirnov and Cramer-Smirnov-von Mises goodness-of-fit statistics.

12 pages

Empirical process of long-range dependent sequences when parameters are estimated · wovepaper