Abstract
A single multivariate control chart referred to as the Max-MCUSUM chart that is capable of simultaneously detecting shifts in both mean vector and covariance matrix of a multivariate process is proposed. This chart is based on standardizing the sample mean vectors and covariance matrices and finding the sampling distribution of the standardized values. This chart is compared with the Max-MEWMA chart proposed by Xie [19]. The proposed chart performs better than the Max-MEWMA chart in detecting small shifts in the process spread and location.
Additional information
Notes on contributors
Smiley W. Cheng
Smiley Cheng He is Professor and Head of the Department of Statistics at the University of Manitoba. He has served as Associate Head and Acting Head of the Department in the past. He was the President of the International Chinese Statistical Association and the Managing Editor of Statistica Sinica. He is currently the Associate Editor or member of Editorial Board of five international statistics journals. Dr. Cheng is heavily involved in the research in statistical quality control (SQC), statistical inference, order statistics, and lottery. He is a Senior Member of American Society for Quality, a member of Statistical Society of Canada, American Statistical Association, International Chinese Statistical Association, and an Elected Member of the International Statistical Institute.
Keoagile Thaga
Keoagile Thaga He is a Lecturer and Coordinator of graduate studies in the Department of Statistics at the University of Botswana. He has a B.A. degree in Statistics, M.S. degree in Statistics, and Ph.D. degree in Statistics. Dr. Thaga is actively involved in the research in statistical quality control and is a member of International Biometrics Society.