Title: On bivariate control charts for the mean of autocorrelated process

Authors: Vahideh Gorgin; Bahram Sadeghpour Gildeh; Majid Sarmad; Mohammad Amini

Addresses: Department of Statistics, Faculty of Mathematical Sciences, Ferdowsi University of Mashhad, Mashhad, Iran ' Department of Statistics, Faculty of Mathematical Sciences, Ferdowsi University of Mashhad, Mashhad, Iran ' Department of Statistics, Faculty of Mathematical Sciences, Ferdowsi University of Mashhad, Mashhad, Iran ' Department of Statistics, Faculty of Mathematical Sciences, Ferdowsi University of Mashhad, Mashhad, Iran

Abstract: The major problem in analysing control charts is to work with autocorrelated data. This problem can be solved by fitting a suitable model to data and using the control chart for the residuals. In most papers, the average run length (ARL) criterion has been used to evaluate the effect of autocorrelation on the performance of control chart. But, in this paper, we compare the efficiency of standardised and modified control charts with residuals charts in identifying changes in the mean process in the presence of autocorrelation using the false positive rate and the false negative rate criteria, and also the comparison between the results of this criterion and the results of ARL criterion is discussed.

Keywords: multivariate autocorrelated processes; process control; average run length; ARL; vector autoregressive; VAR.

DOI: 10.1504/IJPQM.2021.112010

International Journal of Productivity and Quality Management, 2021 Vol.32 No.1, pp.72 - 91

Received: 02 Jan 2019
Accepted: 24 Jul 2019
Published online: 22 Dec 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article