Exclusive Content & Downloads from ASQ

Detection of Multiple Change Points From Clustering Individual Observations

Summary: [This abstract is based on the author's abstract.]
During preliminary analysis of statistical process control involving a large number of observations, it is common to encounter multiple shifts and/or outliers. It is demonstrated that the X-chart and CUSUM chart may fail to detect the presence of any shifts or outliers under these circumstances. A method is proposed that detects single or multiple shifts and/or outliers. The algorithm and an effective stopping rule to control the false detection rate are described, and procedures for reducing masking and for diagnosing the number of shifts or outliers present are suggested.

Please sign-in or register to download this information. Registration is FREE and gives you access to ASQ's articles, case studies and general information.