GenerateCliquesCovariance: Generate a block diagonal covariance matrix

In spcov: Sparse Estimation of a Covariance Matrix

Description

This function is included in the package so that it can be used in the example code provided in spcov.

Usage

GenerateCliquesCovariance(ncliques, cliquesize, theta)

Arguments

ncliques	number of blocks
cliquesize	size of each block
theta	magnitude of non-zeros

Details

This function generates a block diagonal positive definite matrix with randomly-signed, non-zero elements. A shift is added to the diagonal of the matrix so that its condition number equals p, the number of variables.

Value

Sigma	the covariance matrix
A	symmetric square root of Sigma
shift	how much the eigenvalues were shifted. See details.

Author(s)

Jacob Bien and Rob Tibshirani

References

Bien, J., and Tibshirani, R. (2011), "Sparse Estimation of a Covariance Matrix," accepted for publication in Biometrika.

spcov documentation built on May 30, 2017, 12:42 a.m.

spcov index

Solving penalized Frobenius problem.