Monitoring the Mean Vector and the Covariance Matrix of Bivariate Processes

Abstract

This paper proposes the joint use of two charts based on the non-central chi-square statistic (NCS statistic) for monitoring the mean vector and the covariance matrix of bivariate processes, named as the joint NCS charts. The expression to compute the ARL, which is defined as the average number of samples the joint charts need to signal an out-of-control condition, is derived. The joint NCS charts might be more sensitive to changes in the mean vector or, alternatively, more sensitive to changes in the covariance matrix, accordingly to the values of their design parameters. In general, the joint NCS charts are faster than the combined T2 and |S| charts in signaling out-of-control conditions. Once the proposed scheme signals, the user can immediately identify the out-of-control variable. The risk of<br />misidentifying the out-of-control variable is small (less than 5.0%).