cond.cdf: conditional cdf of p-values given noncentrality parameters
In pi0: Estimating the Proportion of True Null Hypotheses for FDR

Description Usage Arguments Value Note Author(s) References

conditional cdf of p-values given noncentrality parameters (ncp)

1
2
3

cond.cdf(p.eval,ncp,test=c("t","z"),alternative=c("two.sided","less",
    "greater"), df=if(test=="z")Inf else df,keep.cdf=NULL,
    suppressWarnings=TRUE)

`p.eval`	numeric vector, at which the conditional CDF is evaluated.
`ncp`	Numeric vector of noncentrality parameters
`test`	Either `t`-test or `z`-test.
`alternative`	The same as in `t.test`.
`df`	The degree of freedom.
`keep.cdf`	Either `NULL` or an `environment`. If this is non-null, the computed CDF will also be stored in `keep.cdf` environment to allow later use. As of version `1.4-0`, `keep.cdf=TRUE`, is no longer supported to comply with new CRAN policies; `keep.cdf=FALSE` will be treated the same as `keep.cdf=NULL`.
`suppressWarnings`	Logical, indicating if warnings are suppressed

A numeric matrix, with each row corresponding to p.eval and each column corresponding to ncp.

Warnings might be produced when full precision is not achieved in pt, but this is rarely very problematic.

Long Qu

Ruppert, Nettleton, Hwang. 2007. Exploring the Information in $p$-values for the Analysis and Planning of Multiple-test Experiments. Biometrics. 63. 483-495.

pi0 documentation built on July 9, 2017, 9:01 a.m.