find.ncp {SharedHT2}R Documentation

Find non-centrality parameter

Description

In order to provide a yardstick in designing simulation experiments this function calculates the non-centrality parameter for a simple F test of the null hypothesis of zero group means

Usage

find.ncp(e.I, e.II, nreps, d)

Arguments

e.I type I error i.e. level of significance
e.II type II error i.e. 1-power
nreps # replicates
d # groups

Value

An numeric vector of length 2 containing the calculated non-centrality parameter and the corresponding power of the standard F test of the null hypothesis that all group means are zero.

theta The non-centrality parameter
power Corresponding power

Note

Once you derive the non-centrality parameter then you can use it in specifying the population means for genes having differential expression. For example if investiagation using find.ncp turns up the value 7.5 then use $7.5/nreps^{0.5}$ to specify group means corresponding to experimental conditions under which the gene is differentially expressed.

Author(s)

Grant Izmirlian izmirlian@nih.gov

See Also

EBfit, SimAffyDat TopGenes, SimW.IW, Simnu.mix

Examples

  
  find.ncp(0.005, 0.0316, 3, 2)


[Package SharedHT2 version 1.3 Index]