False Discovery Testing of p-values from multiple testing

iThis is the main function designed for general usage for determining significance based on the FDR approach, following the Ventura et al. reference below.

fdr(
  pvals,
  qlevel = 0.05,
  method = "original",
  adjustment.method = NULL,
  adjustment.args = NULL,
  verbose = FALSE
)

Arguments

pvals

a vector of pvals on which to conduct the multiple testing

qlevel

the proportion of false positives desired

method

method for performing the testing. 'original' follows Benjamini & Hochberg (1995); 'general' is much more conservative, requiring no assumptions on the p-values (see Benjamini & Yekutieli (2001)). We recommend using 'original', and if desired, using 'adjustment.method="mean" ' to increase power

adjustment.method

method for increasing the power of the procedure by estimating the proportion of alternative p-values, one of "mean", the modified Storey estimator that we suggest in Ventura et al. (2004), "storey", the method of Storey (2002), or "two-stage", the iterative approach of Benjamini et al. (2001)

adjustment.args

arguments to adjustment.method; see propAlt() for description, but note that for "two-stage", qlevel and fdr.method are taken from the qlevel and method arguments to fdr()

verbose

Be verbose (TRUE or FALSE)

Value

NULL if no significant tests, or a vector of the indices of the significant tests

References

Ventura, V., C.J. Paciorek, and J.S. Risbey. 2004. Controlling the proportion of falsely-rejected hypotheses when conducting multiple tests with climatological data. Journal of Climate, in press. Also Carnegie Mellon University, Department of Statistics technical report 775 (www.stat.cmu.edu/tr/tr775/tr775.html).

Benjamini, Y, and Y. Hochberg. 1995. Controlling the false discovery rate: a practical and powerful approach to multiple testing. JRSSB 57:289-300.

Benjamini, Y. and D. Yekutieli. 2001. The control of the false discovery rate in multiple testing under dependency. Annals of Statistics 29:1165-1188.

Benjamini, Y., A. Krieger, and D. Yekutieli. 2001. Two staged linear step up FDR controlling procedure. Technical Report, Department of Statistics and Operations Research, Tel Aviv University. URL: http://www.math.tau.ac.il/~ybenja/Papers.html

Storey, J. 2002. A direct approach to false discovery rates. JRSSB 64: 479--498.

See also

Other FDR: fdr.master(), fdrBasic(), propAlt(), storey()

Author

Chris Paciorek

Examples

if (FALSE) {
signif <- fdr(pvals,method="original",adjustment.method="mean")
}