THE IN-CONTROL PERFORMANCE OF THE ROBUST MULTIVARIATE SYNTHETIC CONTROL CHARTS FOR MONITORING MEAN SHIFT

Multivariate synthetic control chart enables monitoring of multiple process variable simultaneously and hence, negate the inflation of false alarm rates as can be seen in an individual statistical chart. A robust version of the synthetic chart is necessary to mitigate the issue faces by the traditional multivariate synthetic chart, which is unable to produce reliable parameter estimates when Phase I data are contaminated. Therefore, this study proposed three new robust multivariate synthetic control charts (CMRCD, CWS and CWP) which were constructed via minimum regularized covariance determinant (MRCD) and winsorized modified one-step M-estimator (WMOM) for efficient process monitoring. The effectiveness of the proposed robust charts was evaluated in terms of false alarm rates by comparing their in-control performances to the traditional multivariate synthetic chart, Cmean, which is based on the sample mean. Via extensive simulation studies, the findings indicate that the proposed robust control charts outperform the traditional chart regardless of the dimensions or the level of contaminations in the dataset. The real data study further validates that the CMRCD, CWS and CWP perform better than the Cmean. Specifically, the three robust control charts show significant observations, illustrating better capability in monitoring river water quality when compared to the Cmean, i.e., the traditional multivariate synthetic chart.