Chemometric data analysis was applied to chromatographic data as a modeling tool to identify the presence of solvents in gasoline obtained at gas stations in the Minas Gerais state. As a training set, 75 samples were formulated by mixing pure gasolines with varying concentrations of four solvents and analyzed by gas chromatography–mass spectrometry. Selected chromatographic peak areas were used in chemometric analysis. Sample distribution patterns were investigated with principal component analysis (PCA). Score graphics revealed a clear sample agglomeration according to the solvents added. Classification models were created with linear discriminant analysis (LDA). Because gasoline presents a very complex profile and the chromatographic data contains too many variables, two approaches were tested to reduce the dimensionality of the data before LDA. Fisher weights were used as an exclusion criterion of lesser variables, and the original variables were substituted for a few principal components obtained from...