APPLICATION OF LATENT ROOT REGRESSION FOR CALIBRATION IN NEAR-INFRARED SPECTROSCOPY - COMPARISON WITH PRINCIPAL COMPONENT REGRESSION AND PARTIAL LEAST-SQUARES

Several analytical applications of spectroscopy are based on the asses sment of a linear model, linking laboratory values to spectral data. A mong various procedures, the following three methods have been used, i .e. principal component regression (PCR), partial least squares (PLS) and latent root regression (LRR). These methods can be applied in orde r to tackle the high collinearity commonly observed with spectral data . A collection of 99 near-infrared spectra, each including 351 data po ints, was used for the comparison of the 3 methods. The dependent vari able was the specific production of pelleting. The spectral collection was divided into 49 and 50 observations for calibration and validatio n, respectively. The main elements of comparison were the minimum erro r observed on the verification set, the number of regressors introduce d in the models and the stability of the errors around the minimum val ues. The minimum errors were 3.29, 3.13 and 3.07 for PCR, PLS and LRR, respectively. LRR required a large number of regressors in order to o btain the minimum error. Nevertheless, it gave very stable results, an d the errors were not markedly increased when an arbitrary large numbe r of regressors was introduced into the LRR model.