No abstract

No abstract

In this contribution different methods for soft modeling data analysis are reviewed. Soft modeling approaches attempt the description of a system without the need of an a priori model postulation, physical and/or chemical. The goal of these methods is the explanation of data variance using the minimal or softer assumptions about data. Most of these soft modeling approaches are based on factor analysis (FA) decompositions of experimental data matrices. These decompositions are done by pure mathematical means and allow the identification of the number of data variance sources, their qualitative and, eventually, quantitative estimation. Results of soft modeling data analysis are useful to validate hard modeling results and also for investigation of complex chemical systems. In this contribution, the soft modeling data analysis methods described can be applied to one data matrix or to several data matrices (three‐way data sets). The purpose of these methods are mainly exploratory analysis and resolution of mixture data sets. Within the lattergroup, special attention is devoted to multivariate curve resolution (MCR) techniques and their extension to three‐way data analysis. Three examples of application are given covering the chromatographic coelution of mixtures of pesticides using liquid chromatography/diode‐array detection (LC/DAD), the infrared (IR) spectral data analysis from multiple runs of an industrial process and the interpretation of thermodynamic and conformational transitions of polynucleotides using spectrometric titrations.

No abstract

No abstract