|
Activity Number:
|
381
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Quality and Productivity
|
| Abstract - #304001 |
|
Title:
|
A Double Multivariate Exponentially Weighted Moving Average Control Chart
|
|
Author(s):
|
Jay Schaffer and Saad Alkahtani*+
|
|
Companies:
|
University of Northern Colorado and University of Northern Colorado
|
|
Address:
|
Applied Statistics & Research Methods, Greeley, CO, 80639,
|
|
Keywords:
|
Average run length ; double EWMA ; Hotelling's T2 ; Multivariate EWMA
|
|
Abstract:
|
A multivariate extension of the double exponentially weighted moving average control chart is presented. This proposed multivariate control scheme for monitoring and detecting shifts in the process mean vector is referred to as a double multivariate exponentially weighted moving average (dMEWMA) control chart. Using the simulations method, the performance of the dMEWMA chart based on the average run length (ARL) property will be investigated. In addition, the efficiency in terms of ARL of this control chart will be compared to the two most widely used competitive multivariate control charts, Hotelling's X2 and MEWMA. A numerical example of multivariate observations will be given to illustrate the use and performance of the proposed control chart.
|
