combineTestPvalsMeth: combineTestPvalsMeth

Description Usage Arguments Value Author(s) Examples

View source: R/differentialMethylation.R

Description

combine p-values of multiple tests using (a generalization of) Fisher's method. The parameter setting here is taylored to DNA methylation, but can be adapted. Reference: Makambi, K. (2003). Weighted inverse chi-square method for correlated significance tests. Journal of Applied Statistics, 30(2), 225-234.

Usage

1
2
3
4
5
6
combineTestPvalsMeth(
  pvalues,
  testWeights = NULL,
  correlated = FALSE,
  methExpectedTestCorrelation = 0.8
)

Arguments

pvalues

p-values to combine

testWeights

weights for the individual tests

correlated

are the individual tests correlated

methExpectedTestCorrelation

expected correlation. Empirically approximated to the default value of 0.8 for DNA-methylation

Value

the combined p-value

Author(s)

Fabian Mueller, Christoph Bock

Examples

1
2
p.vals <- 10^-c(0,1,5)
combineTestPvalsMeth(p.vals)

RnBeads documentation built on March 3, 2021, 2 a.m.