Robust adjusted discriminant analysis based on shrinkage with application to geochemical and environmental fields.

A novel discriminant analysis (DA) method is proposed, based on the robust reweighted shrinkage estimators and a robust Mahalanobis distance with an adjusted quantile as threshold. A simulation study is done to evaluate the performance of the proposed approach in comparison with the classical DA and the other robust alternatives from the literature. The approach is also illustrated using real dataset examples: a geochemical and environmental dataset known as the Kola Project and a second data containing the spectra of different cultivars of a fruit. The results show the appropriateness of the method while being computationally efficient at the same time. Additional simulations are included to show the additional benefits in outlier detection. • The classical discriminant analysis rule is highly influenced by outliers. • The robust alternatives worsens its performance in high dimension. • The proposed RADAS approach have good performance while being computationally efficient. • The method shows advantages with real examples like the geochemical and environmental dataset known as the Kola Project. • There are additional benefits in outlier detection. [ABSTRACT FROM AUTHOR]