The Annals of Statistics

Dynamic sampling policy for detecting a change in distribution, with a probability bound on false alarm

Benjamin Yakir

Abstract

We show that if dynamic sampling is feasible, then there exist surveillance schemes that satisfy a probability constraint on false alarm. Procedures are suggested for detecting a change of a normal mean from 0 to a (unknown) positive value. These procedures are optimal (up to a constant term) when the post-change mean is known, and almost optimal [up to an $o(\log(1/\alpha))$ term when the post-change mean is unknown.

Article information

Source
Ann. Statist., Volume 24, Number 5 (1996), 2199-2214.

Dates
First available in Project Euclid: 20 November 2003

https://projecteuclid.org/euclid.aos/1069362317

Digital Object Identifier
doi:10.1214/aos/1069362317

Mathematical Reviews number (MathSciNet)
MR1421168

Zentralblatt MATH identifier
0880.62084

Subjects
Primary: 62L10: Sequential analysis
Secondary: 62N10

Citation

Yakir, Benjamin. Dynamic sampling policy for detecting a change in distribution, with a probability bound on false alarm. Ann. Statist. 24 (1996), no. 5, 2199--2214. doi:10.1214/aos/1069362317. https://projecteuclid.org/euclid.aos/1069362317