qvalue {WGCNA}

Estimate the q-values for a given set of p-values

Description

Estimate the q-values for a given set of p-values. The q-value of a test measures the proportion of false positives incurred (called the false discovery rate) when that particular test is called significant.

Usage

qvalue(p, lambda=seq(0,0.90,0.05), pi0.method="smoother", fdr.level=NULL, robust=FALSE,
  smooth.df=3, smooth.log.pi0=FALSE)

Arguments

p

A vector of p-values (only necessary input)

lambda

The value of the tuning parameter to estimate \pi_0. Must be in [0,1). Optional, see Storey (2002).

pi0.method

Either "smoother" or "bootstrap"; the method for automatically choosing tuning parameter in the estimation of \pi_0, the proportion of true null hypotheses

fdr.level

A level at which to control the FDR. Must be in (0,1]. Optional; if this is selected, a vector of TRUE and FALSE is returned that specifies whether each q-value is less than fdr.level or not.

robust

An indicator of whether it is desired to make the estimate more robust for small p-values and a direct finite sample estimate of pFDR. Optional.

smooth.df

Number of degrees-of-freedom to use when estimating \pi_0 with a smoother. Optional.

smooth.log.pi0

If TRUE and pi0.method = "smoother", \pi_0 will be estimated by applying a smoother to a scatterplot of log \pi_0 estimates against the tuning parameter \lambda. Optional.

Details

If no options are selected, then the method used to estimate \pi_0 is the smoother method described in Storey and Tibshirani (2003). The bootstrap method is described in Storey, Taylor & Siegmund (2004).

Value

A list containing:

call

function call

pi0

an estimate of the proportion of null p-values

qvalues

a vector of the estimated q-values (the main quantity of interest)

pvalues

a vector of the original p-values

significant

if fdr.level is specified, and indicator of whether the q-value fell below fdr.level (taking all such q-values to be significant controls FDR at level fdr.level)

Note

This function is adapted from package qvalue. The reason we provide our own copy is that package qvalue contains additional functionality that relies on Tcl/Tk which has led to multiple problems. Our copy does not require Tcl/Tk.

Author(s)

John D. Storey [e-mail], adapted for WGCNA by Peter Langfelder

References

Storey JD. (2002) A direct approach to false discovery rates. Journal of the Royal Statistical Society, Series B, 64: 479-498.

Storey JD and Tibshirani R. (2003) Statistical significance for genome-wide experiments. Proceedings of the National Academy of Sciences, 100: 9440-9445.

Storey JD. (2003) The positive false discovery rate: A Bayesian interpretation and the q-value. Annals of Statistics, 31: 2013-2035.

Storey JD, Taylor JE, and Siegmund D. (2004) Strong control, conservative point estimation, and simultaneous conservative consistency of false discovery rates: A unified approach. Journal of the Royal Statistical Society, Series B, 66: 187-205.