Second-order accurate inference on eigenvalues of covariance and correlation matrices

被引:7
|
作者
Boik, RJ [1 ]
机构
[1] Montana State Univ, Dept Math Sci, Bozeman, MT 59717 USA
关键词
confidence interval; correlation matrix; covariance matrix; edgeworth expansion; eigenvalue; principal components analysis; saddlepoint approximation;
D O I
10.1016/j.jmva.2004.09.009
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Edgeworth expansions and saddlepoint approximations for the distributions of estimators of certain eigenfunctions of covariance and correlation matrices are developed. These expansions depend on second-, third-, and fourth-order moments of the sample covariance matrix. Expressions for and estimators of these moments are obtained. The expansions and moment expressions are used to construct second-order accurate confidence intervals for the eigenfunctions. The expansions are illustrated and the results of a small simulation study that evaluates the finite-sample performance of the confidence intervals are reported. (c) 2004 Elsevier Inc. All rights reserved.
引用
收藏
页码:136 / 171
页数:36
相关论文
共 50 条