FDRsampsize (version 1.0)

fdr.sampsize: Determine sample size required to achieve a desired average power while controlling the FDR at a specified level.

Description

Determines the sample size needed to achieve a desired average power while controlling the FDR at a specified level.

Usage

fdr.sampsize (fdr, ave.pow, pow.func, eff.size, null.effect, max.n = 500,  min.n = 5, tol = 1e-05, eps = 1e-05, lam = 0.95, ...) 
"print"(x,...)

Arguments

fdr

Desired FDR (scalar numeric)

ave.pow

Desired average power (scalar numeric)

pow.func

Character string name of function to compute power; must accept n, alpha, and eff.size as its first three arguments. Other optional arguments may also be provided.

eff.size

Numeric vector of effect sizes; interally, this will be provided as the third argument of pow.func

null.effect

Scalar value of the effect size under the null hypothesis. This may be 0 or 1 for tests that respectively use differences or ratios for comparisons.

max.n

Maximum n to consider

min.n

Minimum n to consider

tol

Tolerance for bisection calculations

eps

Epsilon for numerical differentiation

lam

Lambda for computing anticipated pi0 estimate, see Storey 2002.

x

result of the fdr.sampsize function

...

additional arguments for pow.func

Value

e returns an object of class 'FDRsampsize', which is a list with the following components:

OK

indicates if the requirement is met

n

the computed sample size

alpha

the p-value threshold that gives the desired FDR

fdr.hat

anticipated value of the FDR estimate given n and effect size

act.fdr

actual expected FDR given n and effect size

ave.pow

average power

act.pi

actual value of pi0, the proportion of tests with a true null hypothesis.

pi.hat

expected value of the pi0 estimate

eff.size

input effect size vector

Details

This function checks the technical conditions regarding whether the desired FDR can be achieved by min.n or max.n before calling n.fdr. Thus, for most applications, fdr.sampsize should be used instead of n.fdr.

References

A Onar-Thomas, S Pounds. "FDRsampsize: An R package to Perform Generalized Power and Sample Size Calculations for Planning Studies that use the False Discovery Rate to Measure Significance", Manuscript 2015. Pounds, Stan, and Cheng Cheng. "Sample size determination for the false discovery rate." Bioinformatics 21.23 (2005): 4263-4271. Jung, Sin-Ho. "Sample size for FDR-control in microarray data analysis." Bioinformatics 21.14 (2005): 3097-3104.

Examples

 power.twosampt             # show the power.cox function
 res=fdr.sampsize(fdr=0.1,
                  ave.pow=0.8,
                  pow.func=power.twosampt,
                  eff.size=rep(c(1,0),c(10,990)),
                  null.effect=0)
 res