A Multivariate Discriminator for Process Drift

Abstract

Multivariate Exponentially Weighted Moving Average (MEWMA) chart is a control chart under multivariate process based on the idea of EWMA that rapidly detects small dispersion with a trend. the MEWMA chart was first time discussed by Woodall. However, in his study the correlativity among the multivariate was not considered for the selection of the constant of the diagonal matrix (the smooth parameter λ). In this paper, the EWMA chart with a generalized smooth parameter matrix has been discussed which is believed to have a better fitness for practical production processes than Woodall’s approach.

Citation

Liu, Y., Xu, J. and Akpolat, H. (2002), "A Multivariate Discriminator for Process Drift", Asian Journal on Quality, Vol. 3 No. 1, pp. 119-128. https://doi.org/10.1108/15982688200200011