Methods of \(L_ 1\) estimation of a covariance matrix (Q1091707)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Methods of \(L_ 1\) estimation of a covariance matrix |
scientific article; zbMATH DE number 4011673
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Methods of \(L_ 1\) estimation of a covariance matrix |
scientific article; zbMATH DE number 4011673 |
Statements
Methods of \(L_ 1\) estimation of a covariance matrix (English)
0 references
1987
0 references
The classical relationship between the spectral decomposition of a covariance matrix and the estimation of its principal components is utilized in obtaining robust covariance matrix estimates from robust estimates of the principal components, based on \(L_ 1\) formulations. The performance of these estimates is studied using some problematical data sets discussed in the literature.
0 references
principal component estimation
0 references
linear and quadratic programming
0 references
\(L_ 1\)-estimation
0 references
spectral decomposition of a covariance matrix
0 references
robust covariance matrix estimates
0 references
0 references
