Statistical quality control based on Ranked Set Sampling for Multiple Characteristics
Adisak Pongpullponsak* [a] Peerawut Sontisamran [a]* Author for corresponding; e-mail address: adisak.pon@kmutt.ac.th
Volume: Vol.40 No.3 (JULY 2013)
Research Article
DOI:
Received: 11 September 2012, Revised: -, Accepted: 18 July 2013, Published: -
Citation: Sontisamran A.P...P., Statistical quality control based on Ranked Set Sampling for Multiple Characteristics, Chiang Mai Journal of Science, 2013; 40(3): 485-498.
Abstract
Many quality control charts for mean have been developed from ranked set sampling (RSS), one of them, so-called ranked set sampling for multiple characteristics (RSSMC). This study is to compare a new chart based on RSSMC data with the control chart established from simple random sampling (SRS). The RSSMC control chart has better average run length (ARL) than the classical chart when a sustained shift in the process mean for error ranking characteristic by using other characteristics is added to help ranking data. To compare the RSSMC method with median ranked set sampling (MRSS), RSS, SRS, in term of out–of–control ARL performance, two characteristics of simulated data is used. It is found that the first data has error ranking, while the second data shows no error ranking when it is compared with the measuring data that is simulated. These data are subsequently used to build the corresponding control chart. All over the study, we use the data that is simulated to have a normal distribution with known mean and population variance.