Reliability and sensitivity comparisons and average run lengths of CUSUM scale chart

The cumulative sum (CUSUM) control chart is considered one of the best methods used to detect process shifts. It has been observed that there are certain studies which focused on the analysis and description of the distribution of run-length of CUSUM charts under shifts in process variance. Keeping...

Full description

Saved in:
Bibliographic Details
Published in:Communications in statistics. Theory and methods 2019-05, Vol.48 (9), p.2147-2162
Main Authors: Rabia, Mahwish, Saeed, Nadia, Aslam, Muhammad
Format: Article
Language:English
Subjects:
Algorithms
and out-of control Average Run Length (ARL
Average Run Lengths (ARL)
Computer simulation
Control charts
CUSUM
CUSUM charts
In-Control Average Run Length (ARL
Reliability
Sensitivity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The cumulative sum (CUSUM) control chart is considered one of the best methods used to detect process shifts. It has been observed that there are certain studies which focused on the analysis and description of the distribution of run-length of CUSUM charts under shifts in process variance. Keeping this in view, an efficient and accurate algorithm based on the distribution of run length of CUSUM chart for examining the variance changes of normal process is developed in this research. Since one of the measures for evaluating the performance of control chart is average run length (ARL), therefore it is considered for comparing the reliability and sensitivity of CUSUM scale chart. Simulation studies have been carried out to generate the data through which both in-control and out-of-control ARLs are calculated by varying sample size, decision limits and reference values. The efficiency of the proposed control chart is shown in terms of ARLs. A numerical example is given to illustrate the practical application of the proposed scheme.
ISSN:0361-0926
1532-415X
DOI:10.1080/03610926.2018.1459712