The Inverse Least-Squares Model
The first and simplest inverse least-squares calibration model, also called multiple linear regression, is discussed in detail. Advantages and disadvantages are discussed for a model which today is still in use for some applications. Proposals are given for developing advanced calibration models.
KeywordsInverse least-squares Matrix inversion Calibration and validation Advantages and limitations Successive projections algorithm Ridge regression
- Chung, H., Lee, H., Jun, C.H.: Determination of research octane number using NIR spectral data and ridge regression. Bull. Kor. Chem. Soc. 22, 37–42 (2001)Google Scholar
- Massart, D.L., Vandeginste, B.G.M., Buydens, L.M.C., De Jong, S., Lewi, P.J., Smeyers-Verbeke, J.: Handbook of Chemometrics and Qualimetrics. Elsevier, Amsterdam (1997)., Chaps. 17 and 36Google Scholar
- Norris, K.H., Hart, J.R.: Direct spectrophotometric determination of moisture content of grain and seeds. In: Principles and Methods of Measuring Moisture in Liquids and Solids. Proceedings of the 1963 International Symposium on Humidity and Moisture, vol. 4, pp. 19–25. Reinhold Publishing Co., New York (1965)Google Scholar