PRINCIPAL COMPONENT REGRESSION, RIDGE-REGRESSION AND RIDGE PRINCIPAL COMPONENT REGRESSION IN SPECTROSCOPY CALIBRATION

Ridge regression (RR) and principal component regression (PCR) are two popular methods intended to overcome the problem of multicollinearity which arises with spectral data The present study compares the perfor mances of RR and PCR in addition to ordinary least squares (OLS) and p artial least squares (PLS) on the basis of two data sets. An alternati ve procedure that combines both PCR and RR is also introduced and is s hown to perform well. Furthermore, the performance of the combination of RR and PCR is stable in so far as sufficient information is taken i nto account. This result suggests discarding those components that are unquestionably identified as noise, when the ridge constant tackles t he degeneracy caused by components with small variances. (C) 1997 by J ohn Wiley & Sons, Ltd.