Abstract
Although chemometrics has become widely used recently for analyzing experimental chemical data, there exist in only a few instructions for the proper usage of chemometrics other than some introductory books. As the third step of chemometrics calculations with Microsoft Excel (Excel), the multiple regressions for quantitative analysis are performed on a worksheet. An Excel worksheet for generating absorption spectra is constructed. On other worksheets, quantitative analyses by two different multiple regression methods, which are based on the Lambert-Beer rule (in this paper, this method is called “Lambert-Beer analysis”: “LBA”) and on fundamental multiple linear regression (MLR), are executed using the generated spectra. The performances of quantitative analysis between these methods are compared. The obtained results indicating that LBA has higher performance for the spectra with noise, on the other hand MLR has higher performance for the spectra of samples including the unknown component.
