Simulate a random correlation matrix — rand_cor

Creates a symmetric n x n correlation matrix with user-defined minimum and maximum correlations based on a continuous uniform distribution.

Usage

rand_cor_mat(
  n = 5,
  min.cor = -1,
  max.cor = 1,
  pos.def = FALSE,
  small.positive = NULL
)

Arguments

n: A scalar defining the dimensions of the correlation matrix.
min.cor: A scalar defining the minimum correlation.
max.cor: A scalar defining the maximum correlation.
Note: -1 < min.cor < max.cor < 1.
pos.def: When TRUE (default is FALSE), the function bend of the R package `mbend` is used to bend a non-positive (semi)-definite matrix to be positive (semi)-definite.
small.positive: Argument passed to bend when pos.def = TRUE (default is 1e-8). Eigenvalues smaller than small.positive are replaced by this.
Note: 0 < small.positive < 0.1.

Value

A symmetric n x n correlation matrix. When pos.def = TRUE, the correlation matrix is guaranteed to be positive (semi)-definite.

Examples

# Simulate and visualise a random correlation matrix with 10 columns and rows.
cor_mat <- rand_cor_mat(
  n = 10,
  min.cor = -0.2,
  max.cor = 0.8,
  pos.def = TRUE
)
#> Unweighted bending
#> max.iter = 10000
#> small.positive = 1e-08
#> method = hj
#> Found a correlation matrix.
#> Convergence met after 17 iterations.

plot_matrix(
  mat = cor_mat,
  order = TRUE
)