|
Activity Number:
|
429
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 12, 2004 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Quality and Productivity
|
| Abstract - #300490 |
|
Title:
|
A Comparison of Spectral Control Charts
|
|
Author(s):
|
Laura A. McSweeney*+
|
|
Companies:
|
Fairfield University
|
|
Address:
|
Math and CS Department, Fairfield, CT, 06824,
|
|
Keywords:
|
spectral control chart ; periodogram ; average run length ; Monte Carlo simulations ; statistical process control
|
|
Abstract:
|
Statistical process control is used in industrial settings to improve productivity and the quality of goods. Extensions of the popular Shewhart control chart have been developed, and of interest are the spectral control charts used for the detection of new behavior that is periodic in nature. The first spectral control chart developed for detecting periodic behavior was proposed by Beneke, Leemis, Schlegel and Foote (1988). This control chart is based on Fisher's test statistic and as such the chart has difficulty detecting cyclic behavior corresponding to a frequency in between Fourier frequencies. Tatum (1996) introduced a modified control chart which showed improvement over the first spectral control chart. Two additional spectral control charts will be constructed based on the periodogram tests developed by Siegel (1980) and Bolviken (1983). The results of comparisons of these four control charts using Monte Carlo simulations to determine estimates of the average run lengths to detect the introduction of cyclic behavior will be presented for various conditions like simple vs. compound periodicities or Fourier frequencies vs. non-Fourier frequencies.
|
- 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 2004 program |
