Abstract
A popular method for detecting changes in the probability distribution of a sequence of observations is CUSUM, which proceeds by sequentially evaluating a log-likelihood ratio test statistic and comparing it to a predefined threshold; a change point is detected as soon as the threshold is exceeded. It is desirable to choose the threshold such that the number of false alarms is kept to a specified level. Traditionally, the number of false alarms is measured by the average run length – the expected stopping time until the first false alarm. However, this is does not in general allow one to control the number of false alarms at every particular time instance. Thus, in this paper two stronger false alarm criteria are considered, for which approximation methods are investigated to facilitate the selection of a threshold.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Amram F (1985) Multivariate extreme value distributions for stationary Gaussian sequences. J Multivar Anal 16(2):237–240
Bahadur RR, Rao RR (1960) On deviations of the sample mean. Ann Math Statist 31:1015–1027
Basseville M, Nikiforov I (1993) Detection of Abrupt Changes:Theory and Application. Prentice Hall, Englewood Cliffs
Bucklew J (1985) Large Deviation Techniques in Decision, Simulation and Estimation. Wiley, New York
Dembo A, Zeitouni O (1998) Large Deviations Techniques and Applications, 2nd edn. Springer-Verlag, New York
Ellens W, Kuhn J, Mandjes M, żuraniewski P (2013) Changepoint detection for dependent Gaussian sequences. Work report, arXiv:1307.0938
Jirak M (2015) Uniform change point tests in high dimension. Ann Stat 43 (6):2451–2483
Kuhn J (2017) Monitoring and Control of Stochastic Systems. PhD thesis, University of Amsterdam & The University of Queensland, Australia. Retrievable from http://dare.uva.nl/search?identifier=7ea1bd7d-c372-47ad-8582-e9bcd0fbacce
Kuhn J, Mandjes M, Taimre T (2015) Mean shift detection for state space models. Proceedings of the 21st International Congress on Modelling and Simulation (MODSIM2015)
Lai TL (1998) Information bounds and quick detection of parameter changes in stochastic systems. IEEE Trans Inf Theory 44(7):2917–2929
Lorden G (1971) Procedures for reacting to a change in distribution. Ann Math Stat 42:1897–1908
Mei Y (2008) Is average run length to false alarm always an informative criterion?. Seq Anal 27:354–376
Page E (1954) Continuous inspection scheme. Biometrika 41:100–115
Pawlak M, Steland A (2013) Nonparametric sequential signal change detection under dependent noise. IEEE Trans Inf Theory 59(6):3514–3531
Pollak M (1985) Optimal detection of a change in distribution. Ann Stat 13:206–227
Pollak M, Tartakovsky AG (2009) Asymptotic exponentiality of the distribution of first exit times for a class of Markov processes with applications to quickest change detection. Theory Probab Appl 53(3):430–442
Roberts SW (1959) Control chart tests based on geometric moving averages. Technometrics 1(3):239–250
Siegmund D (1985) Sequential Analysis. Springer-Verlag, New York
Tartakovsky AG (2008) Discussion on “Is average run length to false alarm always an informative criterion?” by Yajun Mei. Seq Anal 27(4):396–405
Tartakovsky AG, Nikiforov I, Basseville M (2014) Sequential Analysis: Hypothesis Testing and Changepoint Detection. Monographs on Statistics & Applied Probability, vol 136. Chapman & Hall/CRC, Boca Raton
Withers CS, Nadarajah S (2014) The distribution of the maximum of the multivariate AR(p) and multivariate MA(p) processes. Stat Probab Lett 95:48–56
Acknowledgments
Julia Kuhn is supported by Australian Research Council (ARC) grant DP130100156. Michel Mandjes’ research is partly funded by the NWO Gravitation Project NETWORKS grant 024002003.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
About this article
Cite this article
Kuhn, J., Mandjes, M. & Taimre, T. Practical Aspects of False Alarm Control for Change Point Detection: Beyond Average Run Length. Methodol Comput Appl Probab 21, 25–42 (2019). https://doi.org/10.1007/s11009-018-9636-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11009-018-9636-1