Comparison of two recently proposed expressions for partial least squares regression prediction error

Abstract Two recently proposed expressions for partial least squares (PLS) prediction error are compared. Using extensive Monte Carlo simulations, it is found that the expression based on the so-called errors-in-variables approach yields prediction intervals with coverage probabilities close to their nominal value, whereas the expression, which is implemented in the latest version of Unscrambler (7.0), is found to behave unsatisfactorily. The difference between the two approaches is illustrated on a real near-infrared data set taken from the literature.

[1]  M. C. Ortiz,et al.  Qualitative and quantitative aspects of the application of genetic algorithm-based variable selection in polarography and stripping voltammetry , 1999 .

[2]  T. Fearn.  A Misuse of Ridge Regression in the Calibration of a Near Infrared Reflectance Instrument , 1983 .

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

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

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

[6]  Pierre Dardenne,et al.  Validation and verification of regression in small data sets , 1998 .

[7]  William J. Egan,et al.  Measurement of Carboxyhemoglobin in Forensic Blood Samples Using UV-Visible Spectrometry and Improved Principal Component Regression , 1999 .

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

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

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

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

[12]  F. X. Rius,et al.  MULTIVARIATE DETECTION LIMITS WITH FIXED PROBABILITIES OF ERROR , 1999 .

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