Qualitative and quantitative analysis using multivariate analysis

Abstract

Multivariate analysis was applied to the determination of a mixed compound, and each component was accurately measured without a separation procedure. Two or more data from measuring one sample for analysis were used for a multivariable analysis. The qualitative analysis for identification is evaluated as follows. First, the principal component analysis is examined for removing the outlier samples. Next, the cluster analysis is examined for the formation of a cluster to unknown samples, or the determination of a belonging cluster of an unknown sample. Finally, the relations between the unknown samples are calculated by soft independent modeling of the class analogies method (SIMCA method) based on the result of the cluster analysis. The principal component analysis (PCS), the principal component regression analysis (PCR), and the different calculation method of regression analysis (DCR) were examined for quantitative analysis. When PCS or PCR were examined using two or more measured data, the accuracy of the determination improved as compared with the calibration-curve method. DCR was unnecessary for a calibration curve for the determination, and but was applied for a determining the content of each compound from samples in which three or more kinds of compounds had been mixed.