|
Activity Number:
|
316
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 11, 2004 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Quality and Productivity
|
| Abstract - #300130 |
|
Title:
|
A Changepoint Method Based on Linear Profile Data
|
|
Author(s):
|
Mahmoud A. Mahmoud*+ and William H. Woodall
|
|
Companies:
|
Virginia Polytechnic Institute and State University and Virginia Polytechnic Institute and State University
|
|
Address:
|
Dept. of Statistics, Blacksburg, VA, 24061-0439,
|
|
Keywords:
|
calibration ; panel data ; likelihood ratio ; simple linear regression ; statistical process control ; two-phase regression
|
|
Abstract:
|
We propose a changepoint method for testing the constancy of the regression parameters in a linear profile dataset. Each sample collected over time in the historical data set consists of several bivariate observations for which a simple linear regression model is appropriate. The proposed method is based on the likelihood ratio test for a change in one or more regression parameters. We compare the performance of our proposed method to that of the most effective phase I linear profile control chart approaches using a simulation study. The advantages of our proposed method over the existing methods are greatly improved detection of sustained step changes in the process parameters and improved diagnostic tools to determine the sources of profile variation and the location(s) of the changepoint(s). Also, we give an approximation for appropriate thresholds for the test statistic. The use of our method is demonstrated using a dataset from a calibration application at National Aeronautics and Space Administration (NASA) Langley Research Center.
|
