|
Activity Number:
|
453
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Quality and Productivity
|
| Abstract - #300549 |
|
Title:
|
Monitoring Simultaneously the Mean Vector and Covariance Matrix in Process Industries
|
|
Author(s):
|
John C. Young*+ and Robert L. Mason+ and Youn-Min Chou
|
|
Companies:
|
McNeese State University and Southwest Research Institute and The University of Texas at San Antonio
|
|
Address:
|
1750 Bilbo St., Lake Charles, LA, 70601, 6220 Culebra Rd., San Antonio, TX, 78228-0510,
|
|
Keywords:
|
Generalized Variance ; Scatter Matrices ; T-Square Statistic ; Wilks Ratio Statistic
|
|
Abstract:
|
In this paper, we propose to simultaneously monitor the mean vector and covariance matrix of a multivariate normal process using two separate control statistics. One statistic checks for changes in the mean vector and the other for changes in the covariance matrix. The proposed procedure will readily detect the appropriate signal in three cases: (1) the mean vector shifts without a shift in the covariance matrix, (2) the covariance matrix shifts without a mean vector shift, and (3) both the mean vector and covariance matrix simultaneously shift as the result of a change in some key process variables. An advantage of this procedure is that it does not require that the number of new observations exceed the number of process variables.
|
