Principal components in multivariate control charts
Conference
·
OSTI ID:5849669
Principal components have been used as a variable reduction technique. The principal component scores have desirable statistical properties when the original variables are distributed as multivariate normal. In this paper, three statistics derived from the PC scores and used to form multivariate control charts are examined. These statistics are outlined and their distributional properties reviewed. The effectiveness of control charts using the three statistics was examined through Monte Carlo simulations. Several parameters were varied including correlation pattern, size of changes in means and variances, number of means or variances changed, change in the correlation for one variable, and the number of PCs retained. 3 refs., 9 tabs.
- Research Organization:
- Pacific Northwest Lab., Richland, WA (USA)
- DOE Contract Number:
- AC06-76RL01830
- OSTI ID:
- 5849669
- Report Number(s):
- PNL-SA-17221; CONF-8908108-2; ON: DE89016828
- Country of Publication:
- United States
- Language:
- English
Similar Records
Statistical methods to monitor the West Valley off-gas system
Principal components analysis as a tool for Quaternary paleoclimatic research
Principal Component Analysis-Based Pattern Analysis of Dose-Volume Histograms and Influence on Rectal Toxicity
Conference
·
Mon Oct 01 00:00:00 EDT 1990
·
OSTI ID:5987358
Principal components analysis as a tool for Quaternary paleoclimatic research
Conference
·
Tue Dec 31 23:00:00 EST 1991
· Geological Society of America, Abstracts with Programs; (United States)
·
OSTI ID:5770650
Principal Component Analysis-Based Pattern Analysis of Dose-Volume Histograms and Influence on Rectal Toxicity
Journal Article
·
Sat Sep 01 00:00:00 EDT 2007
· International Journal of Radiation Oncology, Biology and Physics
·
OSTI ID:21036220