Ng, Peh Sang and Khoo, Michael Boon Chong and Yeong, Wai Chung and Lim, Sok Li (2020) A variable sampling interval EWMA (X)over-bar chart for the mean with auxiliary information. In: 6th International Conference on Computational Science and Technology (ICCST), 29-30 August 2019, Spatial Explorer, Kota Kinabalu, Sabah, Malaysia.
Full text not available from this repository.Abstract
It is a well-known fact that the exponentially weighted moving average (EWMA) type control chart is very effective in detecting small and moderate shifts. To further enhance the sensitivity of the EWMA control chart in shift detection, this paper proposes the variable sampling interval EWMA chart by using a single auxiliary variable (AI) ( abbreviated as VSI EWMA-AI) to monitor the process mean, where the statistic of the proposed chart is based on the information of the study and auxiliary variables. The performance of the proposed chart is evaluated by using the average time to signal (ATS) criterion, where the derivation of ATS formula is presented in this paper. Subsequently, the performance of the proposed chart is compared with the existing EWMA-AI chart in literature. The comparison shows that the VSI EWMA-AI chart has better detection ability in mean shifts than the EWMA-AI chart.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Funders: | UNSPECIFIED |
| Additional Information: | 6th International Conference on Computational Science and Technology (ICCST), Spatial Explorer, Kota Kinabalu, Malaysia, Aug 29-30, 2019 |
| Uncontrolled Keywords: | Average Time to Signal; Markov Chain; Variable Sampling Interval; Exponentially Weighted Moving Average Chart |
| Subjects: | Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Science > Institute of Mathematical Sciences |
| Depositing User: | Ms Zaharah Ramly |
| Date Deposited: | 29 May 2023 02:32 |
| Last Modified: | 29 May 2023 02:32 |
| URI: | http://eprints.um.edu.my/id/eprint/37129 |
Actions (login required)
 |
View Item |
