Estimation of covariance and precision matrices under scale-invariant quadratic loss in high dimension

DOI10.1214/14-EJS878zbMath1282.62140MaRDI QIDQ2441050

Akira Inoue, Tatsuya Kubokawa

Publication date: 21 March 2014

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/euclid.ejs/1392041253

zbMATH Keywords

covariance matrix; asymptotic expansions; Moore-Penrose inverse; Wishart distribution; point estimation; multivariate normal distributions; precision matrix; ridge estimator; Stein-Haff identity; risk comparison; scale-invariant quadratic loss

Mathematics Subject Classification ID

62H12: Estimation in multivariate analysis

62J07: Ridge regression; shrinkage estimators (Lasso)

Related Items

Estimation of the inverse scatter matrix of an elliptically symmetric distribution, Matrix means and a novel high-dimensional shrinkage phenomenon

Cites Work

• Unnamed Item
• A well-conditioned estimator for large-dimensional covariance matrices
• Limit of the smallest eigenvalue of a large dimensional sample covariance matrix
• Improved Stein-type shrinkage estimators for the high-dimensional multivariate normal covariance matrix
• Estimation of the precision matrix of a singular Wishart distribution and its application in high-dimensional data
• Shrinkage estimators for large covariance matrices in multivariate real and complex normal distributions under an invariant quadratic loss
• An identity for the Wishart distribution with applications
• Singular Wishart and multivariate beta distributions
• Asymptotic expansion and estimation of EPMC for linear classification rules in high dimension