|
Activity Number:
|
102
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Quality and Productivity
|
| Abstract - #300550 |
|
Title:
|
A Distribution-Free, Shewhart-Type Quality Control Chart for Detecting a General Change in a Process
|
|
Author(s):
|
Saad T. Bakir*+
|
|
Companies:
|
Alabama State University
|
|
Address:
|
2405 Reston Place, Montgomery, AL, 36117,
|
|
Keywords:
|
Nonparametric ; average run length
|
|
Abstract:
|
A distribution-free (or nonparametric) Shewhart-type quality control chart for detecting a general change in the probability distribution of a process is proposed. The chart is based on the two-sample Kolmogorov-Smirnov statistic and it requires the availability of a reference (or training) sample of observations taken when the process was operating in-control. One advantage over the traditional distribution-based charts is that the proposed chart has the same in-control ARL and false alarm rate over the class of all continuous distributions. Therefore its control limits need not be adjusted according to the assumed underlying distribution. Simulation studies show that the proposed chart can be more efficient than the Shewhart X-bar chart when the process underlying distribution is not normal, especially when this distribution has heavy tails.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2008 program |
