ABSTRACT
The nonparametric control charts discussed in the previous chapter are for cases
when the quality characteristic in question is univariate. In practice, however, the
quality of a product is usually described by multiple quality characteristic variables,
as discussed at the beginning of Chapter 7. That is, most applications require multi-
variate, instead of univariate, SPCmethods. In multivariate cases, the assumption that
the multiple quality characteristic variables in question follow a normal distribution
is difficult to satisfy, because this assumption implies that all individual quality char-
acteristic variables follow normal distributions and all subsets of them follow joint
normal distributions (cf., (7.2) and the related discussion in Subsection 7.2.1), which
are difficult to satisfy in applications. Therefore, it is important to develop multi-
variate SPC control charts that are appropriate to use in cases when the normality
assumption is invalid.