For attribute data with (very) low rates of defectives, attractive control charts can be based on the maximum of subsequent groups of r failure times, for some suitable r≥1, like r=5. Such charts combine good performance with often highly needed robustness, as they allow a nonparametric adaptation already for Phase I samples of ordinary size. In the present paper we address the problem of extending this approach to the situation where two characteristics have to be monitored simultaneously. Generalization to the multivariate case is straightforward.
展开▼
