Multivariate process control charts based on the <i>L</i> ^<i>p</i> depth

Abstract Even if large historical dataset could be available for monitoring key quality features of a process via multivariate control charts, previous knowledge may not enough to reliably identify or adopt unique model all the variables. When no specific parametric turns out appropriate, some alternative solutions should adopted and exploiting non‐parametric methods build chart appears reasonable choice. Among possible statistical techniques, data depth functions are gaining growing interest in control. Within literature, several notions effective this purpose, even case deviation from normality assumption. However, use L p constructing charts has been surprisingly neglected so far. Hence, goal work is investigate behavior compare its performances those Mahalanobis depth, which often depth‐based charts.