Estimating the proportion of true null hypotheses for FDR
Description
This package implements method(s) to (approximately
unbiasedly) estimate the proportion of true null hypotheses,
i.e., the pi0, when a very large number of hypotheses are
simultaneously tested, especially for the purpose of (local)
false discovery rate control for microarray data. It also
contains functions to estimate the distribution of
noncentrality parameters from a large number of parametric
tests.