Detecting changes in a multivariate renewal process

被引：15

作者：

Steinebach, J

Eastwood, VR

机构：

[1] UNIV MARBURG,FACHBEREICH MATH,D-35032 MARBURG,GERMANY

[2] ACADIA UNIV,DEPT MATH & STAT,WOLFVILLE,NS B0P 1X0,CANADA

[3] UNIV AUCKLAND,DEPT STAT,AUCKLAND 1001,NEW ZEALAND

来源：

METRIKA | 1997年 / 46卷 / 01期

关键词：

D O I：

10.1007/BF02717162

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：

Some recent extreme value asymptotics for multivariate renewal processes are used to derive an asymptotic changepoint test. This test is proven to be consistent in the multivariate framework where we assume that at most one change (AMOC) occurrs in any of the component renewal processes. Since the actual covariance structure is often unknown, we also suggest an appropriate estimate.

引用

页码：1 / 19

页数：19

共 16 条

[1] ON EXTREMAL THEORY FOR STATIONARY-PROCESSES [J].