Four multivariate calibration-prediction techniques, classical least-squares, inverse least-squares, principal component regression and partial least-squares regression were applied to the spectrophotometric multicomponent analysis of a veterinary formulation containing oxfendazole (OXF) and oxyclozanide (OXC) without any separation step. The multivariate calibrations were constructed by measuring the absorbance values at 14 points in the 285-350 nm wavelength range and by using the training set of standard mixtures containing OXF and OXC in the different compositions. The validity of building multivariate calibrations was checked by using the synthetic mixtures of both drugs. The multivariate calibration models were successfully applied to the spectrophotometric determination of OXF and OXC in laboratory prepared mixtures and a veterinary formulation. The results obtained were statistically compared with each other. (C) 2002 Elsevier Science B.V. All rights reserved.