localFDR {localFDR}R Documentation

local false discovery rate

Description

estimates the local false discovery rate corresponding to each null hypothesis. Unlike the p-value, the local false discovery rate approximates a posterior probability that the null hypothesis is true.

Usage

localFDR (p.values, threshold, prior.fdr, tolerance, ...)

Arguments

p.values a vector of p-values that have not been corrected for multiple comparisons. For example, p-values may be calculated from wilcox.test or cor.test for two groups, or from lm for multiple groups. Alternately, permutation-based p-values (achieved significance levels) may be calculated using sample.
threshold a numeric object, with each element between 0 and 1, that determines the space of possible estimates of the probability that a null hypothesis is true: more elements enable more precise estimates at the expense of computation speed.
prior.fdr an estimate of the proportion of null hypotheses that are true or a prior probability that any given null hypothesis is true. If this argument is missing, it takes the value returned by priorFDR.
tolerance the floating point tolerance to be used in the test of convergence used to compute the default value of prior.fdr.
... any other arguments for localFDR which are passed unchanged to find.alternative.prob.threshold, a low-level function not intended to be called by the typical user.

Details

Unlike the p-value, the local false discovery rate approximates a posterior probability that the null hypothesis is true. See the following references for additional details.

Value

Object of class numeric of the same length as the p.values argument. Each element represents an estimate of the local false discovery rate corresponding to a null hypothesis.

Author(s)

Zahra Montazeri (zahra@math.carleton.ca), David R. Bickel (DavidBickel.66846716@bloglines.com, http://www.davidbickel.com)

References

Bickel, David R. (2004) Error-Rate and Decision-Theoretic Methods of Multiple Testing: Which Genes Have High Objective Probabilities of Differential Expression?, Statistical Applications in Genetics and Molecular Biology 3: Iss. 1, Article 8 . Available on-line at http://www.bepress.com/sagmb/vol3/iss1/art8

Bickel, D. R. (2004) "HighProbability determines which alternative hypotheses are highly probable: Genomic applications include detection of differential gene expression," arXiv.org e-print ID q-bio.QM/0402049. Available on-line at http://arxiv.org/abs/q-bio.QM/0402049

See Also

priorFDR, find.alternative.prob.threshold, t.test, wilcox.test, cor.test, lm, sample

Examples

n.variables <- 10000

 # This could be the number of genes on a microarray.

n.individuals <- 5

 # This could be the number of microarrays per group.

n.effects <- 1000 

# This is the number of alternative hypotheses that are true, e.g., number of genes differentially expressed.

x1 <- matrix(c(rnorm(n.effects * n.individuals, mean = 2, sd = 1), rnorm((n.variables - n.effects) * n.individuals, mean = 0, sd = 1)), nrow = n.variables, byrow = TRUE) 

# Observed data, e.g., logarithms of gene expression ratios, for group 1.

x2 <- matrix(rnorm(n.variables * n.individuals, mean = 0, sd = 1), nrow = n.variables, byrow = TRUE) 

# The same for group 2.

p.values <- numeric(n.variables)

for(i in 1:n.variables) p.values[i] <- t.test(x1[i, ], x2[i, ])$p.value

local.false.discovery.rate <- localFDR(p.values)

plot(p.values,local.false.discovery.rate, main="localFDR",xlab="p-value", ylab="local false discovery rate estimate")

[Package localFDR version 2.1 Index]