×

A canonical definition of shape. (English) Zbl 1283.62124

Summary: Very general concepts of scatter, extending the traditional notion of covariance matrices, have become classical tools in robust multivariate analysis. In many problems of practical importance (principal components, canonical correlation, testing for sphericity), only homogeneous functions of the scatter matrix are of interest. In line with this fact, scatter functionals often are only defined up to a positive scalar factor, yielding a family of scatter matrices rather than a uniquely defined one. In such families, it is natural to single out one representative by imposing a normalization constraint: this normalized scatter is called a shape matrix. In the particular case of elliptical families, this constraint in turn induces a concept of \(scale\); along with a location center and a standardized radial density, the shape and scale parameters entirely characterize an elliptical density. In this paper, we show that one and only one normalization has the additional properties that (i) the resulting Fisher information matrices for shape and scale, in locally asymptotically normal (LAN) elliptical families, are block-diagonal, and that (ii) the semiparametric elliptical families indexed by location, shape, and completely unspecified radial densities are adaptive. This particular normalization, which imposes the condition that the determinant of the shape matrix should be equal to one, therefore can be considered canonical.

MSC:

62H20 Measures of association (correlation, canonical correlation, etc.)

Software:

robustbase
PDF BibTeX XML Cite
Full Text: DOI Link

References:

[1] Bickel, P.J., On adaptive estimation, Ann. statist., 10, 647-671, (1982) · Zbl 0489.62033
[2] Bickel, P.J.; Klaassen, C.A.J.; Ritov, Y.; Wellner, J.A., Efficient and adaptive estimation for semiparametric models, (1993), Johns Hopkins University Press Baltimore · Zbl 0786.62001
[3] Bilodeau, M.; Brenner, D., Theory of multivariate analysis, (1999), Springer-Verlag New York
[4] Croux, C.; Haesbroeck, G., Principal component analysis based on robust estimators of the covariance or correlation matrix: influence functions and efficiencies, Biometrika, 87, 603-618, (2000) · Zbl 0956.62047
[5] Dümbgen, L.; Tyler, D.E., On the breakdown properties of some multivariate M-functionals, Scand. J. statist., 32, 247-264, (2005) · Zbl 1089.62056
[6] Dümbgen, L., On tyler’s M-functional of scatter in high dimension, Ann. inst. statist. math., 50, 471-491, (1998) · Zbl 0912.62061
[7] Hallin, M.; Paindaveine, D., Semiparametrically efficient rank-based inference for shape. I. optimal rank-based tests for sphericity, Ann. statist., 34, 2707-2756, (2006) · Zbl 1114.62066
[8] Hallin, M.; Paindaveine, D., Parametric and semiparametric inference for shape: the role of the scale functional, Statist. decisions, 24, 327-350, (2006) · Zbl 1111.62002
[9] Hallin, M.; Oja, H.; Paindaveine, D., Semiparametrically efficient rank-based inference for shape. II. optimal R-estimation of shape, Ann. statist., 34, 2757-2789, (2006) · Zbl 1115.62059
[10] Hallin, M., Paindaveine, D., 2008. Optimal rank-based tests for homogeneity of scatter. Ann. Statist. (in press) · Zbl 1360.62288
[11] Hallin, M., Paindaveine, D., 2008. Optimal tests for homogeneity of covariance, scale, and shape (submitted for publication) · Zbl 1294.62216
[12] Hallin, M.; Werker, B.J.M., Semiparametric efficiency, distribution-freeness, and invariance, Bernoulli, 9, 137-165, (2003) · Zbl 1020.62042
[13] Hettmansperger, T.P.; Randles, R.H., A practical affine equivariant multivariate Median, Biometrika, 89, 851-860, (2002) · Zbl 1036.62045
[14] Le Cam, L., Asymptotic methods in statistical decision theory, (1986), Springer-Verlag New York · Zbl 0605.62002
[15] Maronna, R.; Martin, D.; Yohai, V., Robust statistics. theory and methods, (2006), Wiley New York · Zbl 1094.62040
[16] Ollila, E., Hettmansperger, T.P., Oja, H., 2004. Affine equivariant multivariate sign methods. University of Jyväskylä. Preprint · Zbl 1090.62052
[17] Randles, R.H., A simpler, affine-invariant, multivariate, distribution-free sign test, J. amer. statist. assoc., 95, 1263-1268, (2000) · Zbl 1009.62047
[18] Salibian-Barrera, M.; Van Aelst, S.; Willems, G., Principal components analysis based on multivariate MM-estimators with fast and robust bootstrap, J. amer. statist. assoc., 101, 1198-1211, (2006) · Zbl 1120.62319
[19] Taskinen, S.; Croux, C.; Kankainen, A.; Ollila, E.; Oja, H., Influence functions and efficiencies of the canonical correlation and vector estimates based on scatter and shape matrices, J. multivariate anal., 97, 359-384, (2006) · Zbl 1085.62078
[20] Tatsuoka, K.S.; Tyler, D.E., On the uniqueness of S-functionals and M-functionals under nonelliptical distributions, Ann. statist., 28, 1219-1243, (2000) · Zbl 1105.62347
[21] Tyler, D.E., Robustness and efficiency properties of scatter matrices, Biometrika, 70, 411-420, (1983) · Zbl 0536.62042
[22] Tyler, D.E., A distribution-free M-estimator of multivariate scatter, Ann. statist., 15, 234-251, (1987) · Zbl 0628.62053
[23] Zuo, Y., Robust location and scatter estimators in multivariate analysis, (), 467-490 · Zbl 1119.62051
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.