make_random_precision_mat {PCGII}

Generate unstructured/random network skeleton and simulates corresponding precision matrix

Description

A utility function generates unstructured/random network skeleton and simulates corresponding precision matrix. The non-zero elements of the precision matrix are generated randomly from a uniform distribution with parameters (-upper, -lower) UNION (lower, upper).

Usage

make_random_precision_mat(
  eta = 0.01,
  p = 20,
  lower = 0.2,
  upper = 0.5,
  diag = 0.1
)

Arguments

eta

A number between 0 and 1, the probability for drawing an edge between two arbitrary vertices, i.e. the sparsity of the network.

p

A positive integer, the number of vertices.

lower

A positive number, lower limits of the uniform distribution.

upper

A positive number, upper limits of the uniform distribution.

diag

A small positive number to be added to diagonal elements, which guarantees the precision matrix is positive definite.

Value

A precision matrix of size p by p.

Examples

Omega = make_random_precision_mat(eta=.2, p=10)