Tukey-EWMA control chart with variable sampling intervals for process monitoring

Abstract

In this study, the Tukey-Exponential Weighted Moving Average control chart with variable sampling interval (VSI Tukey-EWMA) is proposed. The performance of the proposed control chart is investigated for several distributions and compared with Tukey-EWMA and VSI EWMA control charts. We show that the VSI Tukey-EWMA control chart outperforms the Tukey-EWMA control chart and it performs similarly to the VSI EWMA control chart. The average extra quadratic loss is calculated to examine the overall performance over the whole process shift range by using the Markov chain approach. Finally, the VSI Tukey-EWMA and Tukey-EWMA control charts are applied on real data.

Keywords:

• VSI
• Markov Chain
• non-normality
• average extra quadratic loss
• Tukey-EWMA

Acknowledgements

We are very grateful to the reviewers for their very valuable, helpful comments and suggestions which substantially improved this paper.

Availability of data and materials

The data analyzed during the current study is not publicly available due its implications associated with the proprietary technical knowledge of the company that provided the data.

Disclosure statement/competing interests

There are no conflicts of interest to this work.

Additional information

Notes on contributors

Selcem Adsız

Selcem Adsız is currently continuing Ph.D program in the Department of Statistics at Ege University. She obtained her BS from the Department of Statistics, Çukurova University in 2018. She received MSc degree in Statistics from Ege University in 2021. Her research interests include Statistical Process Control, and Control Charts.

Burcu Aytaçoğlu

Dr. Burcu Aytaçoğlu is an assistant professor in the Department of Statistics at Ege University, Izmir, Turkey. She received her BS from the Department of Statistics, Middle East Technical University (METU) and MSc degree both from the Department of Statistics and Department of Industrial Engineering, METU. After working as a production planning engineer in the automotive industry for about 6 years in Izmir, she received her PhD in Statistics from Ege University in 2013. Her research interests are Statistical Inference, Statistical Process Control, Process Capability, and Control Charts.