Another look at synthetic-type control charts

TL;DR

This paper critically examines synthetic-type control charts, questioning their claimed superior change point detection performance and highlighting the need for cautious application of these methods.

Contribution

It provides a critical review of recent variants of synthetic-type control charts, challenging their effectiveness and advocating for more careful consideration in their use.

Findings

Synthetic-type control charts have questionable detection performance.

Their simplicity does not guarantee effectiveness.

Recent variants do not significantly outperform traditional methods.

Abstract

During the last two decades, in statistical process monitoring plentiful new methods appeared with synthetic-type control charts being a prominent constituent. These charts became popular designs for several reasons. The two most important ones are simplicity and proclaimed excellent change point detection performance. Whereas there is no doubt about the former, we deal here with the latter. We will demonstrate that their performance is questionable. Expanding on some previous skeptical articles we want to critically reflect upon recently developed variants of synthetic-type charts in order to emphasize that there is little reason to apply and to push this special class of control charts.