A minimal characterization of the covariance matrix
From MaRDI portal
(Redirected from Publication:1099540)
Let X be a k-dimensional random vector with mean vector \(\mu\) and non- singular covariance matrix \(\Sigma\). We show that among all pairs (a,\(\Delta)\), \(a\in {\mathbb{R}}^ k\), \(\Delta \in {\mathbb{R}}^{k\times k}\) positive definite and symmetric and \(E(X-a)'\Delta^{-1}(X-a)=k\), (\(\mu\),\(\Sigma)\) is the unique pair which minimizes det \(\Delta\). This motivates certain robust estimators of location and scale.
Recommendations
- Minimax estimators of a covariance matrix
- On estimation of matrix of normal mean
- Monotonic minimax estimators of a 2×2 covariance matrix
- Estimation of a covariance matrix with location: Asymptotic formulas and optimal B-robust estimators
- Improved Minimax Estimators of Normal Convariance and Precision Matrices
Cited in
(11)- Improved feasible solution algorithms for high breakdown estimation.
- Asymptotics of reweighted estimators of multivariate location and scatter
- Robust minimum information loss estimation
- Influence function and efficiency of the minimum covariance determinant scatter matrix estimator
- Outlier detection via a block diagonal product estimator
- The multivariate least-trimmed squares estimator
- A Surprising Covariance Involving the Minimum of Multivariate Normal Variables
- Fast and robust estimation of the multivariate errors in variables model
- The complexity of computing the MCD-estimator
- A Stability Framework for Parameter Selection in the Minimum Covariance Determinant Problem
- The minimum regularized covariance determinant estimator
This page was built for publication: A minimal characterization of the covariance matrix
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1099540)
