A multiple testing procedure based on pooled LIS statistics

Share:

Description

It controls the global FDR for the pooled hypotheses from different groups

Usage

1
plis(lis, fdr = 0.001, adjust = TRUE)

Arguments

lis

pooled LIS statistics estimated from different groups

fdr

nominal fdr level you want to control

adjust

logical. If TRUE (the default), will calculate and return "adjusted" LIS value– the corresponding global FDR if using the LIS statistic as the significance cutoff. It may take hours if you have hundreds of thousands LISs to adjust.

Value

States

state sequence indicating if the hypotheses should be rejected or not: 0 accepted , 1 rejected

aLIS

the corresponding global FDR if using the LIS statistic as the significance cutoff

Author(s)

Wei Z, Sun W, Wang K and Hakonarson H

References

Multiple Testing in Genome-Wide Association Studies via Hidden Markov Models, Bioinformatics, 2009

See Also

see em.hmm for examples