normalized_outcome: Implements the normalized modified outcome approach

In EpiSlim/epiGWAS: Robust Methods for Epistasis Detection

Description

Normalized modified outcome is an improvement to modified_outcome. Its large-sample variance is lower than the original modified outcome approach. The only difference between the two methods lies in the normalization of the propensity scores. The inverses of the propensity scores 1/P(A=1|X) and 1/P(A=0|X) are respectively normalized by their sum sum _i 1/P(A_i=1|X_i) and sum _i 1/P(A_i=0|X_i).

Usage

normalized_outcome(A, X, Y, propensity, parallel = FALSE, ...)

Arguments

A	target variant
X	rest of the genotype
Y	phenotype
propensity	propensity scores
parallel	whether to perform support estimation in a parallelized fashion
...	additional arguments to be passed to stabilityGLM or stabilityBIG

Value

a vector containing the area under the stability selection path for each variable in X

Examples

n <- 30
p <- 10
X <- matrix((runif(n * p) < 0.5) + (runif(n * p) < 0.5),
             ncol = p, nrow = n) # SNP matrix
A <- (runif(n) < 0.3)
propensity <- runif(n, min = 0.4, max = 0.8)
Y <- runif(n) < 0.4
normalized_scores <- normalized_outcome(A, X, Y, propensity,
                               lambda_min_ratio = 0.02 , n_subsample = 1)

EpiSlim/epiGWAS documentation built on Nov. 19, 2019, 7:15 p.m.