MEWMA based control charts with runs rules for monitoring multivariate simple linear regression profiles in Phase II

Mohammad Hassan Ahmadi Karavigh | Amirhossein Amiri

---

URL :   http://research.shahed.ac.ir/WSR/WebPages/Report/PaperView.aspx?PaperID=159234
Date :  2022/02/03
Publish in :    Communications in Statistics Part B: Simulation and Computation
DOI :  https://doi.org/10.1080/03610918.2022.2028833
Link :  http://dx.doi.org/10.1080/03610918.2022.2028833
Keywords :Average run length (ARL); control charts; multivariate simple linear profile methodologies; runs rules schemes; multivariate exponentially weighted moving average (MEWMA)

Abstract :

---

In this article, three control charts including MEWMA, MEWMA/X2 and DMEWMA equipped with proposed runs rules schemes, are developed to improve the performance of existing control charts in monitoring multivariate simple linear profiles. Using five criteria of average run length, percentile of the run length, standard deviation of run length, relative mean index and relative standard deviation index the behavior of the suggested control schemes has been assessed. The results of our study demonstrate that the suggested schemes have a better performance compared to current charts for detecting shifts. Ultimately, using an actual calibration application case in the automotive industry, the suggested control charts applicability is depicted.