Two strategies for selection of samples based on spectral measurements on a large set of samples are tested and compared. A method based on cluster analysis appears to be the best. The same prediction results achieved with the whole calibration set of 114 samples were obtained with only 20 samples selected by this algorithm.
WilliamsP. C. and NorrisK. H, Near Infrared Technology in the Agricultural and Food Industries (American Association of Cereal Chemists, St. Paul, Minnesota, 1987).
2.
MartensH. and NæsT, Multivariate Calibration (John Wiley and Sons, Chichester, England1989).
3.
NæsT. and IsakssonT, Appl. Spectrosc.43, 328 (1989).
4.
NæsT., J. of Chemometrics1, 121 (1987).
5.
HonigsD. E.HieftjeG. M.MarkH. C. and HirschfeldT. B, Anal. Chem.57, 2299 (1985).
6.
JoliffeI. T., Principal Component Analysis (Springer-Verlag, New York, 1986).
7.
NæsT. and MartensH, J. of Chemometrics2, 155 (1988).
8.
IsakssonT. and NæsT, Appl. Spectrosc.42, 1273 (1988).
9.
GeladiP.MacDougallD. and MartensH, Appl. Spectrosc.39, 491 (1985).
10.
ZemrochP. J., Technometrics28, 39 (1986).
11.
RobertP.BertrandD.CrochonM. and SabinoJ, Appl. Spectrosc.43, 1045 (1989).
12.
NæsT.IsakssonT. and KowalskiB, Anal. Chem.62, 664 (1990).
13.
MardiaK. V.KentJ. T. and BibbyJ. M, Multivariate Analysis (Academic Press, London, 1979).
