Standard error of prediction in parallel factor analysis of three-way data

A simple approach is described to calculate sample-specific standard errors for the concentrations predicted by a three-way parallel factor (PARAFAC) analysis model. It involves a first-order error propagation equation in which the correct sensitivity and leverage values are introduced. A comparison is made with a related unidimensional partial least-squares (PLS) model, specifically as regards the required leverage values. Monte Carlo simulation results obtained by adding random noise to both concentrations and instrumental signals for theoretical binary mixtures are in good agreement with the proposed approach. An experimental multicomponent example was studied by a similar Monte Carlo approach, and the obtained standard errors are also in agreement with the calculated values. Implications concerning the limit of detection are discussed.

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

[2]  B. Efron,et al.  A Leisurely Look at the Bootstrap, the Jackknife, and , 1983 .

[3]  Bruce R. Kowalski,et al.  Generalized rank annihilation factor analysis , 1986 .

[4]  S. Leurgans,et al.  Multilinear Models: Applications in Spectroscopy , 1992 .

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

[6]  R. Boqué,et al.  Iteratively reweighted generalized rank annihilation method 2. Least squares property and variance expressions , 2001 .

[7]  F. Xavier Rius,et al.  Limit of detection estimator for second-order bilinear calibration , 2002 .

[8]  P. Paatero.  A weighted non-negative least squares algorithm for three-way ‘PARAFAC’ factor analysis , 1997 .

[9]  Rasmus Bro,et al.  Standard error of prediction for multiway PLS 1 : background and a simulation study , 2002 .

[10]  G. Ewing.  Instrumental methods of chemical analysis , 1954 .

[11]  Julian Morris,et al.  Prediction intervals for non-linear projection to latent structures regression models , 2002 .

[12]  Alejandro C. Olivieri,et al.  A simple approach to uncertainty propagation in preprocessed multivariate calibration , 2002 .

[13]  Rasmus Bro,et al.  Jack-knife technique for outlier detection and estimation of standard errors in PARAFAC models , 2003 .

[14]  Lloyd A. Currie,et al.  Nomenclature in evaluation of analytical methods including detection and quantification capabilities1: (IUPAC Recommendations 1995) , 1999 .

[15]  A. Lorber,et al.  Curve resolution and figures of merit estimation for determination of trace elements in geological materials by inductively coupled plasma atomic emission spectrometry , 1987 .

[16]  Nikos D. Sidiropoulos,et al.  Cramer-Rao lower bounds for low-rank decomposition of multidimensional arrays , 2001, IEEE Trans. Signal Process..

[17]  P. Paatero.  The Multilinear Engine—A Table-Driven, Least Squares Program for Solving Multilinear Problems, Including the n-Way Parallel Factor Analysis Model , 1999 .

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

[19]  Rolf Sundberg,et al.  Precision of prediction in second‐order calibration, with focus on bilinear regression methods , 2002 .

[20]  N. M. Faber,et al.  Uncertainty estimation for multivariate regression coefficients , 2002 .

[21]  Rasmus Bro,et al.  The N-way Toolbox for MATLAB , 2000 .

[22]  R. Bro.  PARAFAC. Tutorial and applications , 1997 .

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