Partial Correlations with Partial Least Squares

Share:

Description

This function computes the matrix of partial correlations via an estimation of the corresponding regression models via Partial Least Squares.

Usage

1
pls.net(X, scale = TRUE, k = 10, ncomp = 15,verbose=FALSE)

Arguments

X

matrix of observations. The rows of X contain the samples, the columns of X contain the observed variables.

scale

Scale the columns of X? Default is scale=TRUE.

k

Number of splits in k-fold cross-validation. Default value is k=10.

ncomp

Maximal number of components. Default is 15.

verbose

Print information on conflicting signs etc. Default is verbose=FALSE

Details

For each of the columns of X, a regression model based on Partial Least Squares is computed. The optimal model is determined via cross-validation. The results of the regression models are transformed via the function Beta2parcor.

Value

pcor

estimated matrix of partial correlation coefficients.

m

optimal number of components for each of the ncol(X) regression models.

Author(s)

Nicole Kraemer

References

N. Kraemer, J. Schaefer, A.-L. Boulesteix (2009) "Regularized Estimation of Large-Scale Gene Regulatory Networks using Gaussian Graphical Models", BMC Bioinformatics, 10:384

http://www.biomedcentral.com/1471-2105/10/384/

Examples

1
2
3
4
n<-20
p<-40
X<-matrix(rnorm(n*p),ncol=p)
pc<-pls.net(X,ncomp=10,k=5)