<abstract xmlns="http://www.w3.org/1999/xhtml"><p>This paper deals with the methodology for practical application of nonparametric control charts. This topic is very important for two reasons: firstly nonparametric control charts are very effective instruments for the realization of the statistical process monitoring phase I due to their robustness against various deviations from the data assumptions that must be met when applying model-based control charts. Secondly nonparametric control charts have very weak SW support and also they are not taught in the frame of training courses not even of the university study programmes. For that reason the practitioners do not know them and do not use them. The paper offers the proposal how to practically apply these control charts which is based on the complex simulation study of various nonparametric control charts performance when various data assumptions have not been met. The study has covered these nonparametric control charts: Shewhart sign control chart, nonparametric EWMA and nonparametric CUSUM control charts, nonparametric progressive mean control chart, control chart based on Mood statistics and robust median absolute deviation control chart. All charts have been studied in condition of not normally distributed data, autocorrelated data and data with nonconstant distribution parameters. The simulations were realized for statistically stable (IC – in control) and also statistically unstable (OC – out of control) processes. For the evaluation of the control charts performance median run length, 0.05-quantile, and 0.95-quantile were used.</p></abstract>

This paper deals with the methodology for practical application of nonparametric control charts. This topic is very important for two reasons: firstly nonparametric control charts are very effective instruments for the realization of the statistical process monitoring phase I due to their robustness against various deviations from the data assumptions that must be met when applying model-based control charts. Secondly nonparametric control charts have very weak SW support and also they are not taught in the frame of training courses not even of the university study programmes. For that reason the practitioners do not know them and do not use them. The paper offers the proposal how to practically apply these control charts which is based on the complex simulation study of various nonparametric control charts performance when various data assumptions have not been met. The study has covered these nonparametric control charts: Shewhart sign control chart, nonparametric EWMA and nonparametric CUSUM control charts, nonparametric progressive mean control chart, control chart based on Mood statistics and robust median absolute deviation control chart. All charts have been studied in condition of not normally distributed data, autocorrelated data and data with nonconstant distribution parameters. The simulations were realized for statistically stable (IC – in control) and also statistically unstable (OC – out of control) processes. For the evaluation of the control charts performance median run length, 0.05-quantile, and 0.95-quantile were used.

Proposal of Methodology for Practical Application of Nonparametric Control Charts

Conference Quality Production Improvement – CQPI

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

This paper deals with the methodology for practical application of nonparametric control charts. This topic is very important for two reasons: firstly...

Proposal of Methodology for Practical Application of Nonparametric Control Charts

Published Online: Oct 08, 2019

Page range: 464 - 471

Received: May 06, 2019

Accepted: May 28, 2019

DOI: https://doi.org/10.2478/cqpi-2019-0063

Keywords
statistical process monitoring, nonparametric control charts, median run length, simulation, quantiles

© 2019 Darja Noskievičová et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Proposal of Methodology for Practical Application of Nonparametric Control Charts

Published Online: Oct 08, 2019

Page range: 464 - 471

Received: May 06, 2019

Accepted: May 28, 2019

DOI: https://doi.org/10.2478/cqpi-2019-0063

Keywordsstatistical process monitoring, nonparametric control charts, median run length, simulation, quantiles

© 2019 Darja Noskievičová et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Keywords
statistical process monitoring, nonparametric control charts, median run length, simulation, quantiles