approx_aSPU: The function for adaptive sum of powered score (aSPU) test

In jasonzyx/approxaSPU: Adaptive Sum of Powered Test (aSPU) Based on Approximated Score Vector

Description

It gives the simulation-based p-values of the sum of powered score (SPU) with different power and aSPU test.

Usage

approx_aSPU(betas, vcov_mat, pow = c(1:8, Inf), B)

Arguments

betas	the vector (length = p) of maximum likelihood estimates; p is the number of paramters to be tested.
vcov_mat	the p by p variance-covariance matrix of MLE.
pow	the power vector for aSPU tests.
B	number of simulations

Details

the suggested power term is c(1:8, Inf)

Value

simulation-based p-values of the sum of powered score (SPU) with different power and aSPU test

Author(s)

Zhiyuan (Jason) Xu, Yiwei Zhang and Wei Pan

References

Wei Pan, Junghi Kim, Yiwei Zhang, Xiaotong Shen and Peng Wei (2014) A powerful and adaptive association test for rare variants, Genetics, 197(4), 1081-95

Yiwei Zhang, Zhiyuan Xu, Xiaotong Shen, Wei Pan (2014) Testing for association with multiple traits in generalized estimation equations, with application to neuroimaging data. Neuroimage. 96:309-25

Examples

# install.packages(lme4)
library(lme4)
library(MASS)
data(exdat_GLMM)
fit1<-glmer(Y~.-ID + (1|ID), ,family="binomial",data=dat,control=glmerControl(optimizer="bobyqa"))
betas<-fixef(fit1)[-1]
vcov_mat<-vcov(fit1)[-1,-1]
approx_aSPU(betas=betas,vcov_mat = vcov_mat,pow=c(1:8,Inf),B=1000) 

jasonzyx/approxaSPU documentation built on May 18, 2019, 5:55 p.m.