A one-sided MEWMA chart for health surveillance

作     者：Joner, Michael D., Jr. Woodall, William H. Reynolds, Marion R., Jr. Fricker, Ronald D., Jr. 

作者机构：Procter & Gamble Co Mason OH 45040 USA Virginia Polytech Inst & State Univ Dept Stat Blacksburg VA 24061 USA Virginia Polytech Inst & State Univ Dept Forestry Blacksburg VA 24061 USA USN Postgrad Sch Dept Operat Res Monterey CA 93943 USA 

出 版 物：《QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL》 (国际质量与可靠性工程)

年 卷 期：2008年第24卷第5期

页      面：503-518页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 

基　　金：NSF [DMI-0354859] Department of Statistics 

主　　题：disease surveillance one-sided control charts monitoring multivariate statistical process control spatial correlation 

摘      要：It is often important to rapidly detect all increase in the incidence rate of a given disease or other medical condition. It has been shown that when disease counts are sequentially available from a single region, a univariate control chart designed to detect rate increases, such as a one-sided cumulative sum chart, is very affective. When disease counts are available from several regions at corresponding times, the most efficient monitoring method is not readily apparent. Multivariate monitoring methods have been suggested for dealing with this detection problem. Some of these approaches have shortcomings that have been recently demonstrated in the quality control literature. We discuss these limitations and suggest an alternative multivariate exponentially weighted moving average chart. We compare the average run-length performance of this chart with that of competing methods. We also evaluate the statistical performance of these charts when the actual increase ill the disease count rate is different from the one that the chart was optimized to detect quickly. Copyright (C) 2008 John Wiley & Sons, Ltd.