bdgraph.npn: Nonparametric transfer

Description

Transfers non-Gaussian data to Gaussian.

Usage

bdgraph.npn( data, npn = "shrinkage", npn.thresh = NULL )

Arguments

data

An (\(n \times p\)) matrix or a data.frame corresponding to the data (\(n\) is the sample size and \(p\) is the number of variables).

npn

A character with three options "shrinkage" (default), "truncation", and "skeptic". Option "shrinkage" is for the shrunken transformation, option "truncation" is for the truncated transformation and option "skeptic" is for the non-paranormal skeptic transformation. For more details see references.

npn.thresh

The truncation threshold; it is only for the truncated transformation (npn= "truncation"). The default value is \(1/(4n^{1/4} \sqrt{\pi \log(n)})\).

Value

data

An (\(n \times p\)) matrix of transferred data, if npn = "shrinkage" or "truncation", and a non-paranormal correlation (\(p \times p\)) matrix, if npn = "skeptic".

References

Liu, H., F. Han, M. Yuan, J. Lafferty, and L. Wasserman (2012). High Dimensional Semiparametric Gaussian Copula Graphical Models, Annals of Statistics 40(4):2293-2326 Zhao, T. and H. Liu (2012). The huge Package for High-dimensional Undirected Graph Estimation in R, Journal of Machine Learning Research, 13:1059-1062

Examples

Run this code

## Not run: ------------------------------------
# # Generating multivariate normal data from a 'random' graph
# data.sim <- bdgraph.sim( n = 6, p = 4, size = 4 )
# data     <- ( data.sim $ data - 3 ) ^ 4
# data
#    
# # Transfer the data by truncation 
# bdgraph.npn( data, npn = "truncation" )
#   
# # Transfer the data by shrunken 
# bdgraph.npn( data, npn = "shrunken" )
#   
# # Transfer the data by skeptic 
# bdgraph.npn( data, npn = "skeptic" )
## ---------------------------------------------