pruneMatrix: Prune square matrix to those variables having nonzero entries

In CFWP/rags2ridges: Ridge Estimation of Precision Matrices from High-Dimensional Data

Prune square matrix to those variables having nonzero entries

Description

Convenience function that prunes a square matrix to those variables (features) having nonzero row (column) entries (i.e., to features implied in graphical connections).

Usage

pruneMatrix(M)

Arguments

M	(Possibly sparsified) square matrix.

Value

A pruned matrix.

Author(s)

Carel F.W. Peeters <[e-mail]>

Examples

## Obtain some (high-dimensional) data
p = 25
n = 10
set.seed(333)
X = matrix(rnorm(n*p), nrow = n, ncol = p)
colnames(X)[1:25] = letters[1:25]

## Obtain regularized precision under optimal penalty
OPT <- optPenalty.LOOCV(X, lambdaMin = .5, lambdaMax = 30, step = 100)

## Determine support regularized standardized precision under optimal penalty
PC0 <- sparsify(symm(OPT$optPrec), threshold = "localFDR")$sparseParCor

## Prune sparsified partial correlation matrix
PC0P <- pruneMatrix(PC0)

CFWP/rags2ridges documentation built on Oct. 21, 2023, 10:19 a.m.