A note on statistical inference for differences of covariances

다국어 초록 (Multilingual Abstract)

This article investigates statistical inferences about differences of covariances matrices when the response has more than two values. The subspace constructed by differences of covariance matrices is related to the sufficient dimension subspace and the central space.
The asymptotic distribution of test statistic for structural dimension is outlined.

참고문헌 (Reference)

1 Eaton, M. L., "The asymptotic distribution of singular values with applications to canonical correlations and correspondence analysis" 34 : 439-446, 1994

2 Li, K. C., "Sliced inverse regression for dimension reduction" 86 : 316-342, 1991

3 Cook, R. D., "Regression graphics" Wiley 1998

4 Cook, R. D., "On the interpretation of regression plots" 89 : 177-189, 1994

5 Li, K. C., "On principal Hessian directions for data visualization and dimension reduction : another application of Stein’s lemma" 87 : 1025-1039, 1992

6 Eaton, M. L., "On Wielandt’s inequality and its application to the asymptotic distribution of the eigenvalues of a random symmetric matrix" 19 : 260-271, 1991

7 Eaton, M. L., "Multivariate statistics: a vector space approach" Wiley 1983

8 Fabian, V., "Introduction to probability and mathematical statistics" Wiley 1985

9 Cook, R. D., "Discussion of sliced inverse regression for dimension reduction" 86 : 316-342, 1991

10 Cook, R. D., "Dimension reduction in binary response regression" 94 : 1187-1200, 1999