Detection of gross errors in process data using studentized residuals

Abstract

For the detection of gross errors in process data, various tests have been proposed which are based on complete knowledge of the variance and covariance of the measurement errors. In this note, we propose a new test based on externally studentized residuals—because these require no knowledge of the variance of the measurement errors and have the property to make an outlier stand out more clearly. The advantages of studentized residuals are demonstrated by application to mass flow measurement data from a high vacuum distillation unit.