Data evaluation in chromatography by principal component analysis

Abstract

The newest achievements in the employment of principal component analysis, a multivariate mathematical statistical method, in the evaluation of chromatographic retention data are compiled. The results obtained by various chromatographic technologies such as gas-liquid chromatography, thin-layer chromatography, high-performance liquid chromatography and electrically driven systems are compiled and briefly discussed.

Differentiation of Lard From Other Edible Fats and Oils by Means of Fourier Transform Infrared Spectroscopy and Chemometrics

“…PCA projects the original data in reduced dimensions defined by the principal components (PC). This technique is useful when there are correlations present among data [14]. In this study, PCA was accomplished using FTIR spectra absorbances of 17 evaluated fats and oils at 16 frequencies as shown in Table 2.…”

Differentiation of Lard, Chicken Fat, Beef Fat and Mutton Fat by GCMS and EA-IRMS Techniques

“…For instance, application of PCA to fatty acid data has been studied for authentication of commercial edible oils 8 and oils extracted from different peanut cultivars 7 . In a recent study, the fatty acid profiles of 119 oil samples were determined by GC and the correlation among peanut, soybean, rapeseed and palm oils were elucidated using PCA whereby computations proved that the samples form clusters according to the type of oil 9 .…”

Chemometric Strategies for the Extraction and Analysis Optimization of Herbicide Residues in Soil Samples

“…It allows the transformation and visualization of complex data sets into a new perspective in which the more relevant information is made more obvious. PCA extracts maximal information from large data matrices containing numerous columns and rows because it calculates the correlations between the columns of the data matrix and classifies the variables according to the coefficients of correlations (Cserháti;2010;Kaliszan, 1997;Mardia et al, 1979;Vandeginste et al, 1998). The original measurement variables are transformed into new conceptually meaningful variables called principal components which account for most of the variation providing reduction of the dimensionality of the dataset.…”

“…If the value is closer to 0, the axis for the variable is at a right angle to the component axis and does not influence it greatly. Due to its versatility and its easy-to-use multivariate mathematical-statistical procedure, PCA is frequently used in many fields of up-to date research, such as environmental protection studies (Cserháti;2010;Hildebrandt et al, 2008).…”