Exclusive Content & Downloads from ASQ
False Discovery Rate-Adjusted Charting Schemes
Summary: [This abstract is based on the authors' abstract.] A problem of multistage process monitoring and fault identification that is formulated as a multiple hypothesis testing problem is investigated. Since the detection power of multiple hypothesis testing methods that attempt to control type I error decreases as the number of stages increases, a false discovery rate control approach is used, and the distribution of the CUSUM statistics are obtained based on Markov chain theory and Brownian motion with drift models. Results show that the approaches are better at identifying the faulty stage than the type I error rate control approach, especially when multiple out-of-control stages are present.
Other Ways to Access content:
- Topics: Statistics, Statistical Process Control (SPC)
- Keywords: Cumulative sum control chart (CUSUM), False alarm rate (FAR), Multiple comparisons, Monitoring
- Author: Li, Yanting; Tsung, Fugee
- Journal: Technometrics