aSPC (version 0.1.2)

aSPC: An adaptive sum of powered correlation test (aSPC)

Description

An adaptive sum of powered correlation test (aSPC) for association between two random vectors

Usage

aSPC(df1, df2, pow = c(1:6, Inf), B = 100, Z.transform = TRUE,
  method = "pearson")

Arguments

df1,

first sample matrix

df2,

second sample matrix

pow,

power integer candidates, default c(1:8, Inf)

B,

number of permutations to calculate a P-value. Default is 100.

Z.transform,

whether to do Fisher's z-transformation on Pearson correlation, default is TRUE.

method,

one of "pearson", "spearman", or "dcor". Default is "pearson".

Value

the P-values of SPC and aSPC tests

References

Xu Z., Pan W. 2017. Adaptive testing for association between two random vectors in moderate to high dimensions. Submitted to Genetic Epidemiology Kim J., Zhang Y., Pan W. Powerful and Adaptive Testing for Multi-trait and Multi-SNP Associa-tions with GWAS and Sequencing Data. Genetics, 2016, 203(2): 715-731.

Examples

library(mvtnorm)
sigma = diag(0.9, 10) + 0.1
n = 50 # sample size
Z = rmvnorm(n=n, mean=rep(0,10), sigma=sigma)
X = rmvnorm(n=n, mean=rep(0,15), sigma=diag(1, 15))
Y = rmvnorm(n=n, mean=rep(0,15), sigma=diag(1, 15))
X = as.data.frame(cbind(Z[,1:5], X))
Y = as.data.frame(cbind(Z[,6:10], Y))
set.seed(123) # to ensure we can replicate the permutation P-value
p = 2; q = 2; n=50
X = rmvnorm(n=n, mean=rep(0,p), sigma=diag(1, p))
Y = rmvnorm(n=n, mean=rep(0,q), sigma=diag(1, q))
a = proc.time()
aSPC(X, Y, pow = c(1:8, Inf), B = 1000, method = "pearson")
proc.time() - a

#' a = proc.time()
aSPC(X, Y, pow = c(1:8, Inf), B = 1000, method = "spearman")
proc.time() - a

a = proc.time()
aSPC(X, Y, pow = c(1:8, Inf), B = 500, method = "dcor")
proc.time() - a