Robust Multivariate Shewhart Control Chart Based on the Stahel-Donoho Robust Estimator and Mahalanobis Distance for Multivariate Outlier Detection

While researchers and practitioners may seamlessly develop methods of detecting outliers in control charts under a univariate setup, screening multivariate pose serious challenges. In this study, we propose robust chart based on the Stahel-Donoho estimator (SDRE), whilst process parameters are estimated from phase-I. Through intensive Monte-Carlo simulation, study presents how estimation presence affect efficacy Hotelling T2 chart, then proposed outlier detector brings back to normalcy by restoring its sensitivity. Run-length properties used as performance measures. The run length establish superiority scheme over default Shewhart charting scheme. applicability includes but is not limited manufacturing health industries. concludes with real-life application dataset extracted carbon fiber tubes.