netgwas (version 0.0.1-1)

R.approx: The expectation of covariance using approximation method

Description

This function implements the approximation method within the Gaussian copula graphical model to estimate the conditional expectation for the data that not follow Gaussianity assumption (e.g. ordinal, discrete, continuous non-Gaussian, or mixed dataset).

Usage

R.approx(y, Z = NULL, Sigma=NULL, rho = NULL, ncores = NULL )

Arguments

y

An (\(n \times p\)) matrix or a data.frame corresponding to the data matrix (\(n\) is the sample size and \(p\) is the number of variables). It also could be an object of class "simgeno".

Z

A (\(n \times p\)) matrix which is a transformation of the data via the Gaussian copula. If Z = NULL internally calculates an initial value for \(Z\).

Sigma

The covariance matrix of the latent variable given the data. If Sigma = NULL the Sigma matrix is calculated internally with a desired penalty term, rho.

rho

A (non-negative) regularization parameter to calculate Sigma. rho=0 means no regularization.

ncores

If ncores = NULL, the algorithm internally detects number of available cores and run the calculations in parallel on (available cores - 1). Typical usage is to fix ncores = 1 when \(p\) is small \(( p < 500 )\), and ncores = NULL when \(p\) is large.

Value

ES

Expectation of covariance matrix( diagonal scaled to 1) of the Gaussian copula graphical model.

Z

New transformation of the data based on given or default Sigma.

References

1. Behrouzi, P., and Wit, E. C. (2017c). netgwas: An R Package for Network-Based Genome-Wide Association Studies. arXiv preprint, arXiv:1710.01236. 2. Behrouzi, P., and Wit, E. C. (2017a). Detecting Epistatic Selection with Partially Observed Genotype Data Using Copula Graphical Models. arXiv preprint, arXiv:1710.00894.

Examples

# NOT RUN {
D <- simgeno(p = 90, n = 50, k = 3)
R.approx(D$data)
# }