Abstract
Measurement error is often occurred in statistical process control. The effect of a linearly covariate error model on the exponentially weighted moving average (EWMA) median and cumulative sum (CUSUM) median charts is investigated. The results indicate that the EWMA median and CUSUM median charts are significantly affected in the presence of measurement errors. We compared the performance of the EWMA median and CUSUM median charts by using Markov chain method in the average run length and the standard deviation of the run length. We concluded that the CUSUM median chart for small shifts and the EWMA median chart for larger shifts are recommended. Two examples are provided to illustrate the application of the EWMA and CUSUM median charts with measurement errors.
Original language | English |
---|---|
Pages (from-to) | 203-213 |
Number of pages | 11 |
Journal | Quality and Reliability Engineering International |
Volume | 34 |
Issue number | 2 |
DOIs | |
State | Published - 03 2018 |
Externally published | Yes |
Bibliographical note
Publisher Copyright:Copyright © 2017 John Wiley & Sons, Ltd.
Keywords
- CUSUM median chart
- EWMA median chart
- Markov chain method
- measurement errors