RNOmni (version 0.3.0)

IINT0: Indirect-INT, Without Secondary Adjustment

Description

Two-stage regression procedure. In the first stage, phenotype is regressed on covariates and structure adjustments to obtain residuals. In the second stage, INT-transformed residuals are regressed on genotype only.

Usage

IINT0(y, G, X, S, calcP = T, k = 3/8, parallel = F, check = T)

Arguments

y

Numeric phenotype vector.

G

Obs by snp genotype matrix.

X

Model matrix of covariates.

S

Model matrix of structure adjustments.

calcP

Logical indicating that p values should be calculated.

k

Offset applied during rank-normalization. See rankNormal.

parallel

Logical indicating whether to run in parallel. Must register parallel backend first.

check

Logical indicating whether to check the input.

Value

A numeric matrix of Wald statistics, one for each locus in G, assessing the null hypothesis that genotype is unrelated to the outcome. If calcP=T, a p-value is additionally calculated for each locus.

Details

Note that, in simulations, this approach did not consistently control the type I error. For a similar approach that did provide valid inference, see IINT.

Examples

# NOT RUN {
# IINT0 against normal phenotype 
p = RNOmni::IINT0(y=RNOmni::Y[,1],G=RNOmni::G[,1:10],X=RNOmni::X,S=RNOmni::S);
# }