estVarComp: Estimate variance components

In tamartsi/MetaCor: Performs Stratified SNP-trait analysis and combines the results using the MetaCor method

Description

Estimate the variance components in a mixed model, via the AI-REML procedure.

Usage

estVarComp(Y, W, covMatList, IDs = NULL, start = NULL, group.var = NULL, AIREML.tol = 1e-06, maxIter = 100, dropZeros = TRUE, verbose = TRUE)

Arguments

Y	An n vector of quantitative outcomes.
W	An n by k matrix of k covariates for each of n participants.
covMatList	A list of covariance matrices modeling the correlations between study participants (e.g. kinship/GRM matrix, household matrix)/
IDs	A vectpr of IDs that should be in the model. Should be a subset of the rownames of W. Will be taken to be W if not provided.
start	A potential vector of starting values for the variance components.
AIREML.tol	Tolerance for convergence of the AI-REML procedure.
maxIter	Maximum number of iterations of the AI-REML procedure.
dropZeros	If TRUE covariance matrices with respective variance components being equal to zero will be dropped and variance components will be re-computed to the other covariance matrices.
verbose	If TRUE progress will be reported.

Details

More soon...

Value

A list with estimated variance componets, and the cholesky decomposition of the inverse covariance matrix, and more.

Note

More details soon!

Author(s)

Matt Conomos

tamartsi/MetaCor documentation built on May 31, 2019, 2:56 a.m.