Asymptotically optimal ditiction of a change in a linear model

Abstract

For a change in the mean value parameters of a normal linear model,a class of detecting methods is proposed,which are asymptotically optimal in an appropriate sense. If there exists no nuisance parameters,the Cusum procedure is included in this class.

Keywords:

• stopping time
• detection of a change
• Cusum procedure
• one-sided sequential probability ratio test

Additional information

Notes on contributors

Qiwei Yao

Present address: Inst. of Math. & Statist., Univ. of Kent, Canterburry, Kent CT2 7NF, UK