Process monitoring using quantiles control charts

Quantiles are more useful descriptive statistics than mean and other moments related statistics because they are less susceptible to long-tailed distributions and outliers. In this study, an auxiliary information based set of Shewhart-type control charts are suggested for an efficient monitoring of process quantiles under simple random sampling and double sampling schemes. The performance of these charting structures is evaluated under bivariate normal and gamma process environments using Average Time to Signal (ATS), Average Extra Quadratic Loss (AEQL) and Average Ratio to ATS (ARATS) as performance measures. We have also examined the effects of contaminated environments on the ATS performance of different quantile based charting structures. Illustrative examples on some selective quantile-type control structures are also provided for procedural details. Finally we have closed with concluding remarks about this study.