pheno.kernel: Phenotype Kernel

In xyz5074/DKAT: Dual Kernel-based Association Test

Description

Calculates the kernel matrix for multivariate (potentially high-dimensional and structured) phenotypes

Usage

pheno.kernel(Y, rho = 0.1)

Arguments

Y	Phenotype matrix, each row is a sample and each column is a phenotype
rho	Graphical lasso regularization parameter used in estimating the precision matrix of phenotypes

Details

Let Θ be the graphical lasso estimator of the precision matrix of phenotypes. Then the phenotype kernel matrix is calculated as K=Y Θ Y^T.

Value

A n by n kernel matrix, where n is the number of subjects.

References

Friedman, J. et al. (2008). Sparse inverse covariance estimation with the graphical lasso. Biostatistics, 9, 432–441.
Zhan, X. et al. (2017). Powerful genetic association analysis for common or rare varaints with high–dimensional structured tratis. Genetics, submitted.

xyz5074/DKAT documentation built on May 4, 2019, 2:28 p.m.