期刊
SEQUENTIAL ANALYSIS-DESIGN METHODS AND APPLICATIONS
卷 40, 期 3, 页码 405-426出版社
TAYLOR & FRANCIS INC
DOI: 10.1080/07474946.2021.1940501
关键词
ARL measures; change point; integral equation; Markov chain; quasistationary distribution
The average run length (ARL) is the prevailing performance measure for evaluating control charts, counting observations until a change is flagged. The steady-state ARL is used for fair comparison between competing designs, postulating the appearance of change after reaching a steady state, unlike the zero-state ARL assumption.
The average run length (ARL), with its various phenotypes, is the prevailing performance measure for evaluating control charts, or change-point detection schemes. Essentially, the ARL counts the number of observations until the corresponding procedure flags a change. To enable a fair comparison between competing designs, one frequently deploys the steady-state ARL. Differing from the older concept of the zero-state ARL (which assumes that the to-be-detected change occurs immediately at startup or never), the former measure postulates this change's appearance after reaching some steady state. Considering different notions (primarily conditional and cyclical ones) of the measure, we recapitulate its historical development; provide a critical discussion of its often-careless exploitation, including a few misconceptions; and derive some new mathematical characterizations that permit its easy calculation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据