Abstract

Abstract Often referred to as a Shewhart‐type control chart , Hotelling's T 2 control chart is based on a multivariate generalization of the Student's t statistic for univariate observations. As is the case of the univariate Shewhart chart, Hotelling's T 2 chart is a good, general purpose tool that is sensitive to outliers and sustained shifts in the mean vector, although not effective in detecting quality improvements that might be reflected in decreased dispersion about the in‐control mean vector. Compared with the alternative of monitoring the measurement variables separately, this method takes into account the in‐control correlation among the measurements in detecting shifts in the mean vector resulting from special causes of variation, which is considered an advantage.

Full Text
Published version (Free)

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