The state of cumulative sum sequential changepoint testing 70 years after Page
Authors:
- 21 December 2023
- journal article
- research article
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 111 (2) , 367-391
Abstract
Quality control charts aim at raising an alarm as soon as sequentially obtained observations of an underlying random process no longer seem to be within stochastic fluctuations prescribed by an ‘in-control’ scenario. Such random processes can often be modelled using the concept of stationarity, or even independence as in most classical works. An important out-of-control scenario is the changepoint alternative, for which the distribution of the process changes at an unknown point in time. In his seminal 1954 Biometrika paper, E. S. Page introduced the famous cumulative sum control charts for changepoint monitoring. Innovatively, decision rules based on cumulative sum procedures took the full history of the process into account, whereas previous procedures were based only on a fixed and typically small number of the most recent observations. The extreme case of using only the most recent observation, often referred to as the Shewhart chart, is more akin to serial outlier than changepoint detection. Page’s cumulative sum approach, introduced seven decades ago, is ubiquitous in modern changepoint analysis, and his original paper has led to a multitude of follow-up papers in different research communities. This review is focused on a particular subfield of this research, namely nonparametric sequential, or online, changepoint tests which are constructed to maintain a desired Type 1 error as opposed to the more traditional approach seeking to minimize the average run length of the procedures. Such tests have originated at the intersection of econometrics and statistics. We trace the development of these tests and highlight their properties, mostly using a simple location model for clarity of exposition, but also review more complex situations such as regression and time series models.Keywords
This publication has 81 references indexed in Scilit:
- Sequential detection of parameter changes in dynamic conditional correlation modelsApplied Stochastic Models in Business and Industry, 2020
- Change-point methods for multivariate time-series: paired vectorial observationsStatistical Papers, 2020
- A multi-sensor robotic platform for ground mapping and estimation beyond the visible spectrumPrecision Agriculture, 2018
- Change Detection in INARCH Time Series of CountsSpringer Proceedings in Mathematics & Statistics, 2016
- State-of-the-Art in Sequential Change-Point DetectionMethodology and Computing in Applied Probability, 2011
- Monitoring parameter change in time series modelsStatistical Methods & Applications, 2011
- Bootstrapping sequential change-point tests for linear regressionMetrika, 2011
- Monitoring risk in a ruin model perturbed by diffusionMetrika, 2008
- Extreme value distribution of a recursive-type detector in a linear modelExtremes, 2008
- Monitoring structural change in dynamic econometric modelsJournal of Applied Econometrics, 2005