On the Charting Procedures: T2 Chart and DD-Diagram

Multivariate analysis is increasingly used to include all dimensions of quality concept, inlight of rapid development of customer requirements. With the recent advances in informationtechnology and in recording, large amounts of multivariate data are now needed to be analyzed.Many charting procedures are based on Mahalanobis distance, but their applicability relies heavilyon the requirement of normality and their performance is related to the choice of a type Ierror rate. An alternative charting scheme based on data depth is pursued and its performanceis assessed through a real example. This performance and that of a T2 chart for individualobservations are discussed. Using the centre-outward ranking, this new method named DD-diagramis used to detect any multivariate quality datum that one of its components exceedsits limiting variation interval. For a given error-free sample, the DD-diagram can be used tosignal out any point of another observed sample taken from a multivariate quality process. Thisnew scheme based on data depth uses a properly chosen limiting variation line or Lvalue inorder to evaluate the outlyingness of every point in the observed sample in all directions of theconsidered P-variates of quality process