Memory-type t charts with multiple auxiliary information for the process mean

Multiple auxiliary information-based (MAIB) memory-type charts are proposed with fixed and variable sampling intervals for an improved monitoring of the process mean, which include adaptive/nonadaptive cumulative sum (CUSUM) and exponentially weighted moving average (EWMA) charts. These control charts are constructed based on a unique uniformly minimum variance unbiased estimator of the process mean that requires information on a study variable as well as on several correlated auxiliary variables. The Monte Carlo simulation technique is used to compute the run length characteristics of the proposed charts when sampling from a multivariate normal distribution. The run length comparisons show that the proposed MAIB- charts outperform their existing auxiliary information based (AIB) and non-AIB charts, where the normalizing transformation is used for all considered charts in order to have uniformity in the comparisons. A real data application is also given to support the proposed theory.