Gower distance-based multivariate control charts for a mixture of continuous and categorical variables

• We propose new nonparametric multivariate process monitoring techniques.
• Proposed control charts can efficiently handle mixed data.
• Integration of Gower’s dissimilarity coefficient and Hotelling’s T2 control charts.
• We examine the performance under various simulation and real scenarios.
• Performance of the method improves as the number of categorical variable increases.

Processes characterized by high dimensional and mixture data challenge traditional statistical process control charts. In this study, we propose a multivariate control chart based on the Gower distance that can handle a mixture of continuous and categorical data. An extensive simulation study was conducted to examine the properties of the proposed control chart under various scenarios and compared it with some existing multivariate control charts. The simulation results revealed that the proposed control chart outperformed the existing charts when the number of categorical variables increases. Furthermore, we demonstrated the applicability and effectiveness of the proposed control charts through a real case study.