In this study, we employed multivariate control techniques to detect outliers in the determination of ethylene in impact polypropylene samples by near-infrared (NIR) spectroscopy and multivariate calibration
partial least-squares (PLS). We also applied an algorithm which identifies those spectral variables responsible for the outlier behavior and that can indicate the source of this behavior. The outliers in
the prediction step may be due to three possible situations: errors associated with the prediction of analyte concentrations in samples that have the same characteristics as the calibration set, but that
are beyond the concentration range; changes in the matrix composition; and instrumental errors. We show that the proposed techniques make it possible to detect whether or not an analyte belongs to the reference
set. In addition, we apply an algorithm that identifies the variables that cause outlier behavior and assigns them to a class.
The Society publishes the internationally recognized, peer reviewed journal, Applied Spectroscopy, which is available both in print and online. Subscriptions are included with membership or can be purchased by institutional or corporate organizations. Abstracts may be viewed free of charge. Previously published as Bulletin (Society for Applied Spectroscopy)