An Alternative to the Bivariate Control Chart for Process Dispersion

ABSTRACT

In this article, we propose a Shewhart-type control chart for monitoring changes in the process variability of a bivariate process. The sample Gini mean differences based matrix is used as an estimate of the population variance–covariance matrix . The newly proposed control chart, denoted by -chart, is based on the generalized Gini mean differences . For the case of two correlated quality characteristics Y and X, the design structure of the proposed -chart is developed assuming bivariate normality of (Y, X). The performance of the proposed -chart is compared with that of the -chart (a sample generalized variance based control chart).

KEYWORDS:

• average run length
• control charts
• generalized variance
• non-normality
• normality
• process variability