Generalizing univariate signed rank statistics for testing and estimating a multivariate location parameter
- 1 January 1995
- journal article
- research article
- Published by Taylor & Francis in Journal of Nonparametric Statistics
- Vol. 4 (3) , 293-308
- https://doi.org/10.1080/10485259508832620
Abstract
We generalize signed rank statistics to dimensions higher than one. This results in a class of orthogonally invariant and distribution free tests that can be used for testing spherical symmetry/location parameter. The corresponding estimator is orthogonally equivariant. Both the test and estimator can be chosen with asymptotic efficiency 1. The breakdown point of the estimator depends only on the scores, not on the dimension of the data. For elliptical distributions, weobtain an affine invariant test with the same asymptotic properties, if the signed rank statisticis applied to standardized data. We also present a method for computing the estimator numerically, and consider a real data example and some simulations. Finally, an application to detection of time-varying signals in spherically symmetric noise is given.Keywords
This publication has 25 references indexed in Scilit:
- Generalizing univariate signed rank statistics for testing and estimating a multivariate location parameterJournal of Nonparametric Statistics, 1995
- Sign Tests in Multidimension: Inference Based on the Geometry of the Data CloudJournal of the American Statistical Association, 1993
- Multivariate Location Estimation Using Extension of $R$-Estimates Through $U$-Statistics Type ApproachThe Annals of Statistics, 1992
- On Certain Bivariate Sign Tests and MediansJournal of the American Statistical Association, 1992
- Asymptotic normality ofr-estimates in the linear modelStatistics, 1988
- Location of Several Outliers in Multiple-Regression Data Using Elemental SetsTechnometrics, 1984
- Weighted least-squares rank estimatesCommunications in Statistics - Theory and Methods, 1983
- Algorithm AS 143: The MediancentreJournal of the Royal Statistical Society Series C: Applied Statistics, 1979
- Robustness properties for a simple class of rank estimatesCommunications in Statistics - Theory and Methods, 1977
- Algorithm AS 78: The MediancentreJournal of the Royal Statistical Society Series C: Applied Statistics, 1974