A simple approach to uncertainty propagation in preprocessed multivariate calibration

A simple approach is described to estimate the confidence limit for the concentrations predicted by multivariate calibration when preprocessing techniques such as orthogonal signal correction or net analyte calculation are applied. It involves reconstructing the unpreprocessed data using the extracted spectral factors and those employed for prediction in order to correctly estimate the sample leverages. Monte Carlo simulations carried out by adding random noise to both concentrations and analytical signals for theoretical binary mixtures are in excellent agreement with the calculations. Experimental multicomponent examples were studied by a similar Monte Carlo approach, and the obtained variances are also in agreement with the calculated values. Implications concerning the limits of detection in the latter cases are also discussed. Copyright © 2002 John Wiley & Sons, Ltd.

[1]  Nicolaas M. Faber,et al.  Estimating the uncertainty in estimates of root mean square error of prediction: application to determining the size of an adequate test set in multivariate calibration , 1999 .

[2]  Terje V. Karstang,et al.  Estimation of prediction error for samples within the calibration range , 1992 .

[3]  I Itzkan,et al.  An enhanced algorithm for linear multivariate calibration. , 1998, Analytical chemistry.

[4]  A. Olivieri,et al.  Simultaneous spectrophotometric-multivariate calibration determination of several components of ophthalmic solutions: phenylephrine, chloramphenicol, antipyrine, methylparaben and thimerosal. , 2000, Talanta.

[5]  A. Olivieri,et al.  Determination of bromhexine in cough-cold syrups by absorption spectrophotometry and multivariate calibration using partial least-squares and hybrid linear analyses. Application of a novel method of wavelength selection. , 1999, Talanta.

[6]  A. Lorber.  Error propagation and figures of merit for quantification by solving matrix equations , 1986 .

[7]  Per Waaben Hansen.  Pre‐processing method minimizing the need for reference analyses , 2001 .

[8]  Joseph P. Romano,et al.  Bootstrap technology and applications , 1992 .

[9]  Age K. Smilde,et al.  Direct orthogonal signal correction , 2001 .

[10]  Desire L. Massart,et al.  Direct Orthogonalization: some case studies , 2001 .

[11]  Santiago Maspoch,et al.  Effect of orthogonal signal correction on the determination of compounds with very similar near infrared spectra , 2001 .

[12]  A. Höskuldsson.  PLS regression methods , 1988 .

[13]  F. E. Satterthwaite.  Synthesis of variance , 1941 .

[14]  F. Xavier Rius,et al.  Detection limits in classical multivariate calibration models , 2000 .

[15]  S. Wold,et al.  Orthogonal signal correction of near-infrared spectra , 1998 .

[16]  C. Ekman,et al.  Comments on construction of confidence intervals in connection with partial least squares , 1998 .

[17]  Bruce R. Kowalski,et al.  Propagation of measurement errors for the validation of predictions obtained by principal component regression and partial least squares , 1997 .

[18]  C. Andrew. Clayton,et al.  Detection limits with specified assurance probabilities , 1987 .

[19]  Israel Schechter,et al.  A Calibration Method Free of Optimum Factor Number Selection for Automated Multivariate Analysis. Experimental and Theoretical Study , 1997 .

[20]  Avraham Lorber,et al.  Net analyte signal calculation in multivariate calibration , 1997 .

[21]  Rasmus Bro,et al.  Orthogonal signal correction, wavelet analysis, and multivariate calibration of complicated process fluorescence data , 2000 .

[22]  W. Wegscheider,et al.  Limits of detection in multivariate calibration , 1991 .

[23]  Olof Svensson,et al.  An evaluation of orthogonal signal correction applied to calibration transfer of near infrared spectra , 1998 .

[24]  A. Olivieri,et al.  Enhanced synchronous spectrofluorometric determination of tetracycline in blood serum by chemometric analysis. Comparison of partial least-squares and hybrid linear analysis calibrations. , 1999, Analytical chemistry.

[25]  A. Muñoz de la Peña,et al.  Comparative study of partial least squares and a modification of hybrid linear analysis calibration in the simultaneous spectrophotometric determination of rifampicin, pyrazinamide and isoniazid , 2001 .

[26]  Alexander Penlidis,et al.  An approach to interval estimation in partial least squares regression , 1993 .

[27]  F. Xavier Rius,et al.  Estimating uncertainties of analytical results using information from the validation process , 1999 .

[28]  A. A. Eiroa,et al.  Error propagation as a factor in selection of measurement intervals for the determination of polycyclic aromatic hydrocarbons by second-derivative spectrofluorimetry. , 2000, Journal of AOAC International.

[29]  Alejandro C. Olivieri,et al.  A comparison of orthogonal signal correction and net analyte preprocessing methods. Theoretical and experimental study , 2001 .

[30]  Nicolaas M. Faber.  Response to ‘Comments on construction of confidence intervals in connection with partial least squares’ , 2000 .

[31]  H. R. Keller,et al.  Assessment of the Quality of Latent Variable Calibrations Based on Monte Carlo Simulations , 1994 .

[32]  R. Difoggio.  Guidelines for Applying Chemometrics to Spectra: Feasibility and Error Propagation , 2000 .

[33]  Nicolaas M. Faber,et al.  Comparison of two recently proposed expressions for partial least squares regression prediction error , 2000 .

[34]  Alejandro C. Olivieri,et al.  Net Analyte Preprocessing: A New and Versatile Multivariate Calibration Technique. Analysis of Mixtures of Rubber Antioxidants by NIR Spectroscopy , 2001 .

[35]  Tom Fearn,et al.  On orthogonal signal correction , 2000 .

[36]  Avraham Lorber,et al.  Estimation of prediction error for multivariate calibration , 1988 .