Statistical quality control based on ranked set sampling

Hassen A. Muttlak*, Walid S. Al-Sabah

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

104 Scopus citations

Abstract

Different quality control charts for the sample mean are developed using ranked set sampling (RSS), and two of its modifications, namely median ranked set sampling (MRSS) and extreme ranked set sampling (ERSS). These new charts are compared to the usual control charts based on simple random sampling (SRS) data. The charts based on RSS or one of its modifications are shown to have smaller average run length (ARL) than the classical chart when there is a sustained shift in the process mean. The MRSS and ERSS methods are compared with RSS and SRS data, it turns out that MRSS dominates all other methods in terms of the out-of-control ARL performance. Real data are collected using the RSS, MRSS, and ERSS in cases of perfect and imperfect ranking. These data sets are used to construct the corresponding control charts. These charts are compared to usual SRS chart. Throughout this study we are assuming that the underlying distribution is normal. A check of the normality for our example data set indicated that the normality assumption is reasonable.

Original languageEnglish
Pages (from-to)1055-1078
Number of pages24
JournalJournal of Applied Statistics
Volume30
Issue number9
DOIs
StatePublished - Nov 2003

Bibliographical note

Funding Information:
This work was supported by King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia under the fast track project #FT/2000-15. The authors would like to thank Ahmad Hamad Algosaibi & Bros. Company, Alkhobar, Saudi Arabia for helping the authors in implementing the new quality control charts and collecting a real data set using the Pepsi Cola production line.

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Fingerprint

Dive into the research topics of 'Statistical quality control based on ranked set sampling'. Together they form a unique fingerprint.

Cite this