Standard error of prediction for multiway PLS 1 : background and a simulation study

While a multitude of expressions has been proposed for calculating sample-specific standard errors of prediction when using partial least squares (PLS) regression for the calibration of first-order data, potential generalisations to multiway data are lacking to date. We have examined the adequacy of two approximate expressions when using unfold- or tri-PLS for the calibration of second-order data. The first expression is derived under the assumption that the errors in the predictor variables are homoscedastic, i.e., of constant variance. In contrast, the second expression is designed to also work in the heteroscedastic case. The adequacy of the approximations is tested using extensive Monte Carlo simulations while the practical utility is demonstrated in Part 2 of this series.

[1]  Ole Christian Lingjærde,et al.  Shrinkage Structure of Partial Least Squares , 2000 .

[2]  S. Wold,et al.  Multi‐way principal components‐and PLS‐analysis , 1987 .

[3]  J. Kalivas,et al.  Selectivity and Related Measures for nth-Order Data. , 1996, Analytical chemistry.

[4]  Michael C. Denham,et al.  Prediction intervals in partial least squares , 1997 .

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

[6]  Bruce R. Kowalski,et al.  Improved Prediction Error Estimates for Multivariate Calibration by Correcting for the Measurement Error in the Reference Values , 1997 .

[7]  N. M. Faber,et al.  Characterizing the Uncertainty in Near-Infrared Spectroscopic Prediction of Mixed-Oxygenate Concentrations in Gasoline: Sample-Specific Prediction Intervals , 1998 .

[8]  Age K. Smilde,et al.  Comments on multilinear PLS , 1997 .

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

[10]  R. Bro.  Multiway calibration. Multilinear PLS , 1996 .

[11]  Rasmus Bro,et al.  Enzymatic browning of vegetables. Calibration and analysis of variance by multiway methods , 1996 .

[12]  Classical versus multivariate calibration for a beta emitter (14C) activity determination by liquid scintillation counting , 1996 .

[13]  Darren T. Andrews,et al.  Maximum likelihood principal component analysis , 1997 .

[14]  Michael S. Feld,et al.  Analytical Method of Estimating Chemometric Prediction Error , 1997 .

[15]  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 .

[16]  Harald Martens,et al.  REVIEW OF PARTIAL LEAST SQUARES REGRESSION PREDICTION ERROR IN UNSCRAMBLER , 1998 .

[17]  P. G. Moore,et al.  Data Uncertainties and Least Squares Regression , 1972 .

[18]  Sijmen de Jong,et al.  Regression coefficients in multilinear PLS , 1998 .

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

[20]  P. Paatero,et al.  THREE-WAY (PARAFAC) FACTOR ANALYSIS : EXAMINATION AND COMPARISON OF ALTERNATIVE COMPUTATIONAL METHODS AS APPLIED TO ILL-CONDITIONED DATA , 1998 .

[21]  H. Zha,et al.  The restricted total least squares problem: formulation, algorithm, and properties , 1991 .

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

[23]  T. Næs,et al.  Principal component regression in NIR analysis: Viewpoints, background details and selection of components , 1988 .

[24]  Bruce R. Kowalski,et al.  PREDICTION ERROR IN LEAST SQUARES REGRESSION : FURTHER CRITIQUE ON THE DEVIATION USED IN THE UNSCRAMBLER , 1996 .

[25]  E. R. Malinowski,et al.  Rank Annihilation Factor Analysis of Unresolved LC Peaks , 1983 .

[26]  Gary D. Christian,et al.  Application of the method of rank annihilation to fluorescent multicomponent mixtures of polynuclear aromatic hydrocarbons , 1980 .

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

[28]  Michael C. Denham,et al.  Choosing the number of factors in partial least squares regression: estimating and minimizing the mean squared error­ of prediction , 2000 .

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

[30]  F. P. Zscheile,et al.  Instability of Linear Systems Derived from Spectrophotometric Analysis of Multicomponent Systems. , 1962 .

[31]  Avraham Lorber,et al.  Analytical figures of merit for tensorial calibration , 1997 .

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

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

[34]  C. Braak,et al.  Prediction error in partial least squares regression: a critique on the deviation used in The Unscrambler , 1995 .

[35]  Sabine Van Huffel,et al.  The total least squares problem , 1993 .

[36]  Mikael Kubista,et al.  A new method for the analysis of correlated data using procrustes rotation which is suitable for spectral analysis , 1990 .

[37]  Rocco DiFoggio,et al.  Examination of Some Misconceptions about Near-Infrared Analysis , 1995 .

[38]  Philip K. Hopke,et al.  Estimation of the heteroscedastic noise in large data arrays , 2000 .

[39]  Shelby J. Haberman,et al.  The Analysis of Nonadditivity in Two-Way Analysis of Variance , 1990 .

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

[41]  Rolf Sundberg,et al.  Second-order calibration: bilinear least squares regression and a simple alternative , 1998 .

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

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

[44]  Nicolaas (Klaas) M. Faber,et al.  Comment on a recently proposed resampling method , 2001 .

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

[46]  Sijmen de Jong,et al.  Multiway calibration in 3D QSAR , 1997 .

[47]  Nicolaas (KLAAS) M. Faber,et al.  A closer look at the bias–variance trade‐off in multivariate calibration , 1999 .

[48]  Philip K. Hopke,et al.  Source apportionment of gasoline and diesel by multivariate calibration based on single particle mass spectral data , 2001 .

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