The Annals of Statistics
- Ann. Statist.
- Volume 36, Number 3 (2008), 1261-1298.
Optimal rank-based tests for homogeneity of scatter
We propose a class of locally and asymptotically optimal tests, based on multivariate ranks and signs for the homogeneity of scatter matrices in m elliptical populations. Contrary to the existing parametric procedures, these tests remain valid without any moment assumptions, and thus are perfectly robust against heavy-tailed distributions (validity robustness). Nevertheless, they reach semiparametric efficiency bounds at correctly specified elliptical densities and maintain high powers under all (efficiency robustness). In particular, their normal-score version outperforms traditional Gaussian likelihood ratio tests and their pseudo-Gaussian robustifications under a very broad range of non-Gaussian densities including, for instance, all multivariate Student and power-exponential distributions.
Ann. Statist., Volume 36, Number 3 (2008), 1261-1298.
First available in Project Euclid: 26 May 2008
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Hallin, Marc; Paindaveine, Davy. Optimal rank-based tests for homogeneity of scatter. Ann. Statist. 36 (2008), no. 3, 1261--1298. doi:10.1214/07-AOS508. https://projecteuclid.org/euclid.aos/1211819564