High‐dimensional covariance estimation for Gaussian directed acyclic graph models with given order
Focus Article
Published Online: May 22 2019
DOI: 10.1002/wics.1468
Can't access this content? Tell your librarian.
Abstract The covariance matrix is a fundamental quantity that helps us understand the nature of relationships among variables in a multivariate data set. Estimating the covariance matrix can be challenging in modern applications where the number of variables is often larger than the number of samples. In this paper, we review methods which tackle this challenge by inducing sparsity in the Cholesky parameter of the inverse covariance matrix. This article is categorized under: Algorithms and Computational Methods > Numerical Methods Statistical and Graphical Methods of Data Analysis > Multivariate Analysis Statistical and Graphical Methods of Data Analysis > Analysis of High Dimensional Data
The placement of zeros in the Cholesky factor T: (a) Banding; (b) Lasso penalty of Huang et al.; (c) adaptive banding
[
Normal View
|
Magnified View
]