Abstract
Traditional control charts like Hotelling \(T^2\) are based on the assumption of multivariate normality and also inapplicable to high-dimensional data. A notion of data depth has been used to measure centrality of a given point in a given data cloud. The data depth inferences do not require multivariate normality and any constraint on the dimension of the data. Liu (J Am Stat Assoc 90(432):1380–1387, 1995) provided control charts for a multivariate processes based on data depth, and the performance of the chart is not reported. There exist few tests for the location parameter of multivariate distribution based on data depth. Using these tests, we proposed nonparametric control charts to detect a shift in the location parameter of the multivariate process. We investigate the performance of the proposed control charts using the average run-length measure for various distributions. Also, the control chart procedure is illustrated by using wine quality data.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call