28 No. 3
Estimation and Figures of Merit for Multivariate Calibration
(IUPAC Technical Report)
Alejandro C. Olivieri, Nicolaas (Klaas) M. Faber, Joan Ferré,
Ricard Boqué, John H. Kalivas, and Howard Mark
Pure and Applied Chemistry
78, No. 3, pp. 633-661 (2006)
This report gives an introduction to multivariate calibration
from a chemometrics perspective and reviews the various proposals
to generalize the well-established univariate methodology
to the multivariate domain. Univariate calibration leads to
relatively simple models with a sound statistical underpinning.
The associated uncertainty estimation and figures of merit
are thoroughly covered in several official documents. However,
univariate model predictions for unknown samples are reliable
only if the signal is sufficiently selective for the analyte
of interest. By contrast, multivariate calibration methods
may produce valid predictions also from highly unselective
data. A case in point is quantification from near-infrared
spectra. With the ever-increasing sophistication of analytical
instruments inevitably comes a suite of multivariate calibration
methods, each with its own underlying assumptions and statistical
properties. As a result, uncertainty estimation and figures
of merit for multivariate calibration methods has become a
subject of active research, especially in the field of chemometrics.
of how a univariate model will lead to severely biased
predictions when unsuspected interferences give a variable
contribution to the signal, whereas multiple measurements
may permit accurate prediction in such a situation.
last modified 25 April 2007.
Copyright © 2003-2007 International Union of Pure and
Questions regarding the website, please contact email@example.com