New Methods for Phase II Monitoring of Multivariate Multiple Linear Profiles

The quality of a process or product in some statistical process control applications is characterized by two or more regression profiles in a structure known as "multivariate multiple linear profile," whereby response variables are correlated to and regressed on two or more explanatory variables. This work presents three innovative ways for monitoring the multivariate multiple linear profile in Phase II using the multivariate homogeneously weighted moving average (MHWMA) control chart. The performance of proposed methods is evaluated due to zero- and steady-state average run length (ARL) metrics and extensive comparisons are made between present methods and the ones proposed herein with regard to their performances. The results reveal the superiority of the proposed methods. The research also includes a sensitivity analysis to examine the impact of the calculated parameters. A practical use of the novel control chart is shown via an actual case study.