Distance or dissimilarity matrices are widely used in applications. We study the relationships between the eigenvalues of the distance matrices and outliers and show that outliers affect the pairwise distances and inflate the eigenvalues. We obtain the eigenvalues of a distance matrix that is affected by outliers and compare them to the eigenvalues of a distance matrix with a constant structure. We show a discrepancy in the sizes of the eigenvalues of a distance matrix that is contaminated with outliers, present an algorithm and offer a new outlier detection method based on the eigenvalues of the distance matrix. We compare the new distance-based outlier technique with several existing methods under five distributions. The methods are applied to a study of public utility companies and gene expression data.
AlonU.BarkaiN.NottermanD.A.GishK.YbarraS.MackD.LevineA.J., Broad patterns of gene expression revealed by clustering of tumor and normal colon tissues probed by oligonucleotide arrays, Proc Natl Acad Sci USA96(1) (1999), 6745–6750.
2.
AzzaliniA.ValleA.D., The Multivariate Skew-normal Distribution, Biometrika83(4) (1996), 715–726.
3.
AzzaliniA., The Skew-Normal and Related Distributions Such as the Skew-t, Package “sn”, (2020), http//azzalini.stat.unipd.it/SN.
4.
BarnettV.LewisT., Outliers in Statistical Data, John Wiley & Sons, London, (1994).
5.
BreunigM.M.KriegelH.P.NgR.T.SanderJ., LOF: identifying density-based local outliers, In ACM Sigmod Record29 (2000), 93–104.
6.
CabanaE.LilloR.E.LaniadoH., Multivariate outlier detection based on a robust Mahalanobis distance with shrinkage estimators, Statistical Papers62(2) (2021), 1583–1609.
7.
FilzmoserP.MaronnaR.WernerM., Outlier identification in high dimensions, Computational Statistics and Data Analysis52 (2008), 1694–1711.
HahslerM.PiekenbrockM.DoranD., “dbscan” R package, https://cran.r-project.org/web/packages/dbscan/index.html, (2022).
13.
HubertM.Van der VeekenS., Outlier detection for skewed data, Journal of Chemometrics, Special Issue: Conferentia Chemometrica22(3-4) (2007), 235–246.
14.
JohnsonR.A.WichernD.W., Applied Multivariate Statistical Analysis, New Jersey: Prentice Hall (2007).
15.
KnorrM.NgR.T., A Unified Approach for Mining Outliers, In Conf. of the Centre for Advanced Studies on Collaborative Research (CASCON), Toronto, Canada, (1997), 236–248, doi: 10.1145/782010.782021.
16.
LüdeckeD.Ben-ShacharM.S.PatilI.WaggonerP.MakowskiD., “performance”, An R package for assessment, comparison and testing of statistical models, Journal of Open Source Software6(60) (2021), 31–39, doi: 10.21105/joss.03139.
17.
MadsenJ.H., “DDoutlier” R package, (2022), https://github.com/jhmadsen/DDoutlier.
18.
MahalanobisP.C., On the Generalised Distance in statistics, Proceedings of the National Institute of Sciences of India2 (1936), 49–55.
ModarresR., Graphical Comparison of High Dimensional Distributions, International Statistical Review88(3) (2020), 698–714.
21.
ModarresR.SongY., Interpoint Distances: Applications, Properties and Visualization, Applied Stochastic Models in Business and Industry36(6) (2020), 1147–1168.
22.
ModarresR., Outlier Tests of High Dimensional Observations, Journal of nonparametric Statistics34 (2022), 206–227.
23.
ModarresR., A High Dimensional Dissimilarity Measure, Computational Statistics and Data Analysis, (2022), doi: 10.1016/j.csda.2022.107560.
RousseeuwP.J., Multivariate Estimation with High Breakdown Point, In:GrossmannW.PflugG.VinczeI.WertzW., eds, Mathematical Statistics and Applications, Volume B. Dordrecht: Reidel Publishing Company, 1985, pp. 283–297.
26.
RousseeuwP.J.van DriessenK., A fast algorithm for the minimum covariance determinant estimator, Technometrics41 (1999), 212–223.
27.
ShuryginA.M., Using interpoint distances for pattern recognition, Pattern Recognition and Image Analysis16(4) (2006), 726–729.
