A Canonical Representation of Block Matrices with Applications to Covariance and Correlation Matrices

12/04/2020
by   Ilya Archakov, et al.
0

We obtain a canonical representation for block matrices. The representation facilitates simple computation of the determinant, the matrix inverse, and other powers of a block matrix, as well as the matrix logarithm and the matrix exponential. These results are particularly useful for block covariance and block correlation matrices, where evaluation of the Gaussian log-likelihood and estimation are greatly simplified. We illustrate this with an empirical application using a large panel of daily asset returns. Moreover, the representation paves new ways to regularizing large covariance/correlation matrices and to test block structures in matrices.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 20

page 21

12/07/2020

Likelihood Geometry of Correlation Models

Correlation matrices are standardized covariance matrices. They form an ...
12/04/2020

A New Parametrization of Correlation Matrices

We introduce a novel parametrization of the correlation matrix. The repa...
06/19/2017

Detection of Block-Exchangeable Structure in Large-Scale Correlation Matrices

Correlation matrices are omnipresent in multivariate data analysis. When...
02/07/2018

Group kernels for Gaussian process metamodels with categorical inputs

Gaussian processes (GP) are widely used as a metamodel for emulating tim...
06/26/2018

Estimation of large block covariance matrices: Application to the analysis of gene expression data

Motivated by an application in molecular biology, we propose a novel, ef...
03/12/2020

Existence and Uniqueness of the Kronecker Covariance MLE

In matrix-valued datasets the sampled matrices often exhibit correlation...
10/31/2017

Bayesian Learning of Random Graphs & Correlation Structure of Multivariate Data, with Distance between Graphs

We present a method for the simultaneous Bayesian learning of the correl...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.