On variance of sample matrix eigenvalue

被引:0
作者
Wywial, Janusz L. [1 ]
Sitek, Grzegorz [1 ]
机构
[1] Katowice Univ Econ, Dept Stat Econometr & Math, 1 Maja 50, PL-40287 Katowice, Poland
关键词
Matrix eigenvalue; Variance-covariance matrix; Canonical correlation; Approximation of variance; DISTRIBUTIONS;
D O I
10.1080/03610918.2019.1588315
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
The variance of a matrix eigenvalue estimator is considered. This estimator is a function of simple random sample variances and covariances of a multidimensional random variable whose distribution is not necessarily normal. The variance of the eigenvalue estimator is approximated based on the Taylor expansion for a function of simple random sample moments. A method for approximating the variance of the canonical correlation estimator is also proposed. A simulation analysis of the accuracy of variance estimation is presented. The considered approximation of variance can be applied to assessing the variance of a statistic which is the solution of any implicit interdependence functions of sample moments.
引用
收藏
页码:1943 / 1954
页数:12
相关论文
共 20 条
[1]  
Anderson T. W., 1962, An Introduction to Multivariate Statistical Analysis
[2]  
Benton D., 2002, Advances and Applications in Statistics, V2, P269
[3]  
Berman R., 1985, ANN STAT, V13, P95, DOI [10.1214/aos/1176346579, DOI 10.1214/AOS/1176346579]
[4]  
Cherian K. C., 1941, The Journal of the Indian Mathematical Society, V5, P133
[5]  
Cramer H., 1962, Mathematical Methods of Statistics
[6]   ASYMPTOTIC DISTRIBUTIONS OF FUNCTIONS OF THE EIGENVALUES OF SOME RANDOM MATRICES FOR NON-NORMAL POPULATIONS [J].
FANG, C ;
KRISHNAIAH, PR .
JOURNAL OF MULTIVARIATE ANALYSIS, 1982, 12 (01) :39-63
[7]  
FUJIKOSHI Y, 1980, BIOMETRIKA, V67, P45
[8]  
Harville D. A., 1997, Matrix algebra from a statistician's perspective
[9]  
KOTZ S, 2000, CONTINOUS MULTIVARIA, V1
[10]   DISTRIBUTION OF THE CANONICAL CORRELATION MATRIX [J].
MATHAI, AM .
ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 1981, 33 (01) :35-43