cwot {cwot}R Documentation

Cauchy weighted joint test for main effect and genotype-by-treatment interaction effect for binary endpoints.

Description

Cauchy weighted joint test for main effect and genotype-by-treatment interaction effect for binary endpoints.

Usage

cwot(nullmod, g, weights = seq(-1, 1, 0.1))

Arguments

nullmod

- The null model object from the output of cwot_null.

g

- The variable of interest, e.g., the genotype.

weights

- The pre-specified weights. The default choice is a vector of -1, -0.9,..., 0.9, 1.

Value

The p-values of CWOT, CWOT_Score, CWOT_LRT and the individual p-values of the composite genotypes.

References

Hong Zhang, Qing Li, Devan Mehrotra and Judong Shen. "CauchyCP: a powerful test under non-proportional hazards using Cauchy combination of change-point Cox regressions", arXiv:2101.00059.

Examples

n = 100
y = rbinom(n, 1, 0.3)
x = data.frame(x1=rnorm(n))
tr = rbinom(n, 1, 0.5)
g = rbinom(n, 2, 0.1)
nullmod = cwot_null(y, tr, x)
cwot(nullmod, g, weights=seq(-1,1,0.1))

[Package cwot version 0.1.0 Index]