A condition for null robustness
canonical correlationscomplex normal distributionleft-spherical distributionsMANOVA problemsnull robustnesstests of independence
Random matrices (algebraic aspects) (15B52) Foundations and philosophical topics in statistics (62A01) Characterization and structure theory of statistical distributions (62E10) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Multivariate distribution of statistics (62H10)
Let X be an \(n\times p\) random matrix. If PX and X have the same distribution for each orthogonal matrix P of order n, we say that X is left-spherical [cf. \textit{A. P. Dawid}, J. R. Stat. Soc., Ser. B 39, 254- 261 (1977; Zbl 0371.62080)]. There are many statistics the distributions of which are invariant in the class of left-spherical distributions. Several authors studied this problem. In this paper sufficient conditions are given group theoretically that certain statistics have a common distribution under the class of left- spherical distributions or its subclasses. These results are applied to MANOVA problems, problems involving canonical correlations and certain statistics associated with the complex normal distribution. In fact, these invariant statistics can also be obtained by other sufficient conditions; see for example, the second author, Ann. Stat. 9, 1267-1275 (1981; Zbl 0474.62048) or the reviewer and \textit{Chen}, Tech. Rep. No.10, ARO Contract DAAG 29-82-K-0156, Dept. Stat. Stanford Univ. (1984).
- Nonnull and optimality robustness of some tests
- On Robustness for Hypotheses Testing
- Conditions for robust principal component analysis
- A note on robust hypothesis testing
- Robustness and the robust estimate
- Robust estimation without positive real condition
- scientific article; zbMATH DE number 1066958
- A problem of robustness theory
- Robustness of Zero Crossing Estimator
- A generalized multivariate analysis of variance model useful especially for growth curve problems
- A robustness property of Hotelling's T^ 2-test
- A Test for Reality of a Covariance Matrix in a Certain Complex Gaussian Distribution
- scientific article; zbMATH DE number 3136275 (Why is no real title available?)
- scientific article; zbMATH DE number 3942782 (Why is no real title available?)
- scientific article; zbMATH DE number 3671512 (Why is no real title available?)
- scientific article; zbMATH DE number 3738683 (Why is no real title available?)
- scientific article; zbMATH DE number 3755689 (Why is no real title available?)
- scientific article; zbMATH DE number 3578221 (Why is no real title available?)
- scientific article; zbMATH DE number 3206556 (Why is no real title available?)
- scientific article; zbMATH DE number 3344241 (Why is no real title available?)
- Representation of invariant measures
- Robust tests for spherical symmetry
- Robustness of multivariate tests
- Statistical Analysis Based on a Certain Multivariate Complex Gaussian Distribution (An Introduction)
- Student's t-Test Under Symmetry Conditions
- The general MANOVA problem
- The Relationship Between Sufficiency and Invariance with Applications in Sequential Analysis
- Two testing problems relating the real and complex multivariate normal distributions
- Relationships among classes of spherical matrix distributions
- Stein estimation under elliptical distributions
- The growth curve model: a review
- scientific article; zbMATH DE number 4074221 (Why is no real title available?)
- Sufficiency, ancillarity and independence in invariant models
- Locally minimax tests in symmetrical distributions
This page was built for publication: A condition for null robustness
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q790559)
