Asymptotic theory for curve-crossing analysis

被引：3

作者：

Zhao, Zhibiao ^{[1
]}

Wu, Wei Biao ^{[1
]}

机构：

[1] Univ Chicago, Dept Stat, Chicago, IL 60637 USA

来源：

STOCHASTIC PROCESSES AND THEIR APPLICATIONS | 2007年 / 117卷 / 07期

基金：

美国国家科学基金会;

关键词：

central limit theorem; curve-crossing; linear processes; multiple Wiener-Ito integral; non-central limit theorem; nonlinear time series;

D O I：

10.1016/j.spa.2006.10.010

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

We consider asymptotic properties of curve-crossing counts of linear processes and nonlinear time series by curves. Central limit theorems are obtained for curve-crossing counts of short-range dependent PF processes. For the long-range dependence case, the asymptotic distributions are shown to be either multiple Wiener-lto integrals or integrals with respect to stable Levy processes, depending on the heaviness of tails of the underlying processes. (c) 2006 Elsevier B.V. All rights reserved.

引用

页码：862 / 877

页数：16

共 46 条

[1]

[Anonymous], COLLECTED WORKS COMM

[2]

[Anonymous], 1982, Lithuanian Math. J.

[3] THE EXPECTED MEASURE OF THE LEVEL SETS OF A REGULAR STATIONARY GAUSSIAN PROCESS [J].