Optimal stopping times for detecting changes in distributions

By George V. Moustakides. 1986

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

The structure of optimal private tests for simple hypotheses (2018, background): “Change-point detection has a long history in statistics and information theory (e.g. [She31, Pag54, Pag55, Shi63, Lor71, Pol85, Mou86, Pol87, Lai95, Kul01, Mei06, VB14]).”
Control Charts for Poisson Count Data with Varying Sample Sizes (2010, methodology): “Also, Moustakides (1986) proved this method, which is based on a likelihood-ratio approach, to have optimality properties in detecting a change in distribution.”
Efficient scalable schemes for monitoring a large number of data streams (2010, background): “Moreover, it is well known that T (k1,...,km )CM (a) in (6) is exactly the optimal scheme to detect the change when (k1, . . . , km) is indeed the subset of actual affected data streams; see Moustakides (1986).”
Sequential Classification in Point Clouds of Urban Scenes (2010, background): “It is also known to enjoy very strong optimality properties as later proved in [9].”
CUSUM and EWMA multi-charts for detecting a range of mean shifts (2007, methodology): “For example, it has been shown by Moustakides (1986) and Ritov (1990) that the performance in detecting the mean shift of the one-sided CUSUM control chart with the reference value δ is optimal in terms of average run length (ARL) if the actual mean shift is δ. Srivastava and Wu (1993, 1997) and Wu…”
The Use of Control Charts in Health-Care and Public-Health Surveillance (2006, methodology): “The sets methods do not use all of the information in the data and the performance of CUSUM charts has optimality properties as discussed by Moustakides (1986) and Hawkins and Olwell (1998, pp. 138–139).”
Quickest detection of drift change for Brownian motion in generalized Bayesian and minimax settings (2006, methodology): “O th e r u s e is o n ly a llo w e d w ith w ritte n p e rm is s io n b y th e c o p y rig h t h o ld e r. 470 Feinberg -- Shiryaev [11] G. V. Moustakides.”
Optimality of the CUSUM procedure in continuous time (2003, methodology): “We will show this fact following similar steps as in Moustakides (1986).”
Optimal sequential detection in multi-stream data (2015, background): “[14] Moustakides, G. (1986).”
Optimal Design of a CUSUM Chart for a Mean Shift of Unknown Size (2010, methodology): “The numerical results show that various CUSUM-based charts, including the CUSUM chart, the WCUSUM chart, and the multi-CUSUM chart, can be improved using our optimization approach under various settings.”
A unified framework for stochastic optimization (2019, background): “Moustakides (1986) describes an application to identiying when a stochastic process has changed, such as the increase f incidence in a disease or a drop in quality on a production line. eng and Gallego (1995) uses optimal stopping to determine when o start end-of-season sales on seasonal items.”
EWMA Charts for the Weibull Shape Parameter (2010, background): “Moustakides (1986) proved that PCUSUM is indeed optimal in the sense that it has the best worst-case scenario among all chart schemes with the same incontrol ARL. See Moustakides (1986) for a formal discussion of the problem.”
Optimal and Asymptotically Optimal CUSUM Rules for Change Point Detection in the Brownian Motion Model with Multiple Alternatives (2006, background): “It is easily seen that in seeking solutions to the above problem, as suggested in [ 7 ], we can restrict our attention to stopping times that satisfy the false alarm constraint with equality.”
The geometric CUSUM chart with sampling inspection for monitoring fraction defective (2001, background): “The work of Moustakides (1986) has shown that the SPRT-based choice of the reference value is optimal in a certain sense.”
Asymptotic Optimality of Change-Point Detection Schemes in General Continuous-Time Models (2006, methodology): “…in a minimax context with the constraint on the mean time to false alarm is well understood (see, e.g., Basseville and Nikiforov, 1993; Beibel, 1996; Moustakides, 1986; Pollak, 1987; Ritov, 1990; Shiryaev, 1996; Siegmund, 1985; Srivastava and Wu, 1993; Tartakovsky, 1991, 1994; Yakir, 1997).”