ranktruncated: Rank truncated p-Value procedure...

In mutoss: Unified Multiple Testing Procedures

Rank truncated p-Value procedure...

Description

Rank truncated p-Value procedure The program computes the exact distribution and with it the p-Value

Usage

ranktruncated(pValues, K, silent=FALSE)

Arguments

pValues	Vector of p-Values (not sorted)
K	the number of hypotheses / p-Values being in w
silent	If true any output on the console will be suppressed.

Details

This function computes the exact distribution of the product of at most K significant p-values of L>K observed p-values. Thus, one gets the pvalue from the exact distribution. This has certain advantages for genomewide association scans: K can be chosen on the basis of a hypothesised disease model, and is independent of sample size. Furthermore, the alternative hypothesis corresponds more closely to the experimental situation where all loci have fixed effects.

Please note that this method is implemented with factorials and binomial coefficients and the computation becomes numerical instable for large number of p-values.

Value

Used.pValue: List information about the used pValues; RTP: Test statistic and pValue

Author(s)

Frank Konietschke

References

Dubridge, F., Koeleman, B.P.C. (2003). Rank truncated product of P-values, with application to genomewide association scans. Genet Epidemiol. 2003 Dec;25(4):360-6

Examples

pvalues<-runif(10)
result <- ranktruncated(pvalues,K=2,silent=FALSE) # take the K=2 smallest pvalues
result <- ranktruncated(pvalues,K=2,silent=TRUE) # take the K=2 smallest pvalues
result <- ranktruncated(pvalues,K=5,silent=TRUE) # take the K=5 smallest pvalues

mutoss documentation built on March 31, 2023, 8:46 p.m.