A comparison of CUSUM, EWMA, and temporal scan statistics for detection of increases in poisson rates

Han, Sung Won; Tsui, Kwok Leung; Ariyajunya, Bancha; Kim, Seoung Bum

doi:10.1002/qre.1056

Cited by 64 publications

(44 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As such the results from Chen and Glaz can be used to get efficient starting estimates for the threshold used in the surveillance plan. For other literature on the SCAN plan see Tango (1995), Kulldorff and Nagarwalla (1995), Kulldorff (1997), and Kulldorff, M. (2001), Kulldorff et al (2005), Woodall et al (2008) and Han et al (2008). Fig.…”

Section: The Scan Statisticmentioning

confidence: 99%

“…This method is a spatio-temporal moving average plan that systematically scans the target space applying a test to all windows of data up to a given fixed size in time and space. This presents an intuitive approach but has received some criticisms by Woodall et al (2008) and Han et al (2008), including: firstly that it is not as efficient as the cumulative SUM (CUSUM) (see Raubertas, 1989, andYamada, 2004) for outbreak detection and secondly that its ability to detect outbreaks most effectively is dependent on the choice of shape and size of the scanning window. In addition, in some of the literature on the SCAN statistic, the focus is on whether diseases cluster rather than on early detection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatio-Temporal Disease Surveillance

Sparks¹,

Bolt²,

Okugami³

2012

Bioterrorism

View full text Add to dashboard Cite

Section: The Scan Statisticmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Spatio-Temporal Disease Surveillance

Sparks¹,

Bolt²,

Okugami³

2012

Bioterrorism

View full text Add to dashboard Cite

“…Pehlivan and Testik 4 and Ozsan 5 contributed important papers on the EWMA. Han et al 6 compared several methods for detecting increases in Poisson rates. This is an important problem in public health monitoring and syndromic surveillance as well as business and industry.…”

Section: Important Research Themes From Volume 26 2010mentioning

confidence: 99%

Important research themes from volume 26 2010

Montgomery¹

2011

Quality & Reliability Eng

View full text Add to dashboard Cite

Important Research Themes from Volume 26 2010The aim of this journal is to provide information on new developments in many aspects of the quality and reliability engineering field to professionals by publishing research articles, review papers, tutorials, and applications/case studies. It is appropriate to examine the most recent volume and identify some important themes, highlight some of the papers that contribute to those themes, and discuss what we hope to see in the future.Statistical Process Control and related topics continue to be an important area of research and applications. The journal published many noteworthy papers in this area, including papers on multivariate process monitoring by Kim and Adams 1 , methods for detecting special causes in integrated process control by Reynolds and Park 2 , and robust CUSUM methods for monitoring the mean and variance by Reynolds and Stoumbos 3 . Pehlivan and Testik 4 and Ozsan 5 contributed important papers on the EWMA. Han et al. 6 compared several methods for detecting increases in Poisson rates. This is an important problem in public health monitoring and syndromic surveillance as well as business and industry. Noorossana et al. 7 authored a paper on multivariate profile monitoring and provided an application in calibration. Perry 8 wrote on monitoring autocorrelated processes with polynomial drift.Designed experiments and robust design are an integral part of both product design and process improvement. The paper by Johnson and Montgomery 9 is a tutorial on constructing optimal designs for nonlinear models. Recent development in computing and applications in commercial software have made constructing Bayesian D-optimal designs for nonlinear models practical and these authors demonstrate the advantages of this approach relative to using standard designs for linear models in the nonlinear setting. Arda Vanli et al. 10 and Dehlendorff 11 provided papers on aspects of experiments with computer models. The use of computer models in engineering design and development is growing rapidly, and the design of experiments to efficiently and effectively use these models is an important topic. Ma et al. 12 presented a paper on three-level and mixed-level orthogonal arrays. Goh and Lam 13 wrote on problem-based learning and its applications in designed experiments. Gupta et al. 14 showed how experiments with signal-response systems could be analyzed using generalized linear mixed models. This paper appeared in our special issue on design for six sigma. Arnouts et al. 15 wrote an instructive paper on design and analysis of strip-plots experiments. This is an important paper because the strip-plot problem arises relatively often in industrial experimentation and is often not recognized by the experimenter. Hamada and Hamada 16 propose an algorithm for analyzing fractional factorial designs with complex aliasing. Nonregular designs such as Plackett-Burman designs and many orthogonal arrays have alias structures where either all or many effects are not completely confounded so ...

show abstract

“…In particular, in healthcare surveillance, interest is in detecting an increase in the mortality/incidence rates in primary care (Aylin et al 2003), and the number of cancer patients (Krieger 2008;Han et al 2010). …”

Section: Introductionmentioning

confidence: 99%

Self-Starting Monitoring Scheme for Poisson Count Data With Varying Population Sizes

et al. 2016

Self Cite

View full text Add to dashboard Cite

In this paper we consider the problem of monitoring Poisson rates when the population sizes are time-varying and the nominal value of the process parameter is unavailable. Almost all previous control schemes for the detection of increases in the Poisson rate in Phase II are constructed based on assumed knowledge of the process parameters, e.g., the expectation of the count of a rare event when the process of interest is in control. In practice, however, this parameter is usually unknown and not able to be estimated with a sufficiently large number of reference samples. A self-starting EWMA control scheme based on a parametric bootstrap method is proposed. The success of the proposed method lies in the use of probability control limits, which are determined based on the observations during rather than before monitoring.Simulation studies show that our proposed scheme has good in-control and out-of-control performance under various situations. In particular, our proposed scheme is useful in rare event studies during the start-up stage of a monitoring process.

show abstract

A comparison of CUSUM, EWMA, and temporal scan statistics for detection of increases in poisson rates

Cited by 64 publications

References 44 publications

Spatio-Temporal Disease Surveillance

Spatio-Temporal Disease Surveillance

Important research themes from volume 26 2010

Self-Starting Monitoring Scheme for Poisson Count Data With Varying Population Sizes

Contact Info

Product

Resources

About