OMNI_individual: omni_individual.R

In GBJ: Generalized Berk-Jones Test for Set-Based Inference in Genetic Association Studies

Description

Computes the omnibus test statistic combining GBJ, GHC, minP, and SKAT. This version of the function assumes you have the individual factor data (i.e. genotypes) for each subject. If you only have summary statistics, use omni_ss(). You WILL NOT be able to use this function unless you have also loaded the SKAT package (install.packages("SKAT"); library(SKAT)).

Usage

OMNI_individual(null_model, factor_matrix, link_function, num_boots = 100)

Arguments

null_model	An R regression model fitted using glm(). Do not use lm(), even for linear regression!
factor_matrix	An n*d matrix with each factor (i.e. each SNP) as one column. There should be no missing data.
link_function	Either "linear" or "logit" or "log".
num_boots	Number of bootstrap repetitions to find correlation matrix of set-based statistics.

Value

A list with the elements:

OMNI	The observed omnibus test statistic.
OMNI_pvalue	The p-value of the OMNI test
err_code	Sometimes if your p-value is very small (< 1*10^(-10)), R may run into numerical issues. This message will alert you if such a situation occurs.

Examples

factor_matrix <- matrix(data=rbinom(n=1000, size=2, prob=0.3), ncol=5)
Y <- rnorm(n=200)
null_mod <- glm(Y ~ 1)
OMNI_individual(null_model=null_mod, factor_matrix=factor_matrix,
link_function='linear', num_boots=5)

GBJ documentation built on March 26, 2020, 6:05 p.m.