Using Univariate Linear Regression Calibration Software in the MATLAB Environment. Application to Chemistry Laboratory Practices

A useful software package for statistical analysis by univariate linear regression calibration is presented in this paper. In many chemistry laboratory experiments, a linear-regression calibration is needed to fit the experimental results to a linear model. An example of this is the common use of UV–visible molecular absorption spectroscopy and the application of the Lambert–Beer law, which establishes a linear relationship between the concentration of an absorbent analyte and its absorbance measured at a specific wavelength. A great number of commercial statistical software packages exist. We present here, a home-made one, developed with two principal aims: first, to show students how to create their own software to resolve a specific statistical calculation problem, and, second, to include in the same software package all of the major statistical methods useful to analytical chemistry students. All the calculations are performed with suitable routines written for the MATLAB programming environment. MATLAB allows the calculation and resolution of complex equations with very simple programming commands. An easy experiment is presented to show how to use the software. The experiments presented may be performed in an analytical chemistry course. They can be completed in four hours with the analysis of the data using the software package requiring an additional 4-hour computational class session.