deds.genExtra: Generating Extra Parameters for Test Statistics Functions for Differential Expression

Description

deds.genExtra is used to pass in extra arguments for comp.stat and deds.stat.linkC, which computes various test statistics for differential expression in microarray data.

Usage

deds.genExtra(classlabel, tests)

Arguments

classlabel

A vector of integers corresponding to observation (column) class labels. For $k$ classes, the labels must be integers between 0 and $k-1$.

tests

A vector of character string specifying the statistics to be used to test differential expression. The character string could be any of the followings:

test="t":

one- or two-sample t-statistics;

test="f":

F-statistics;

test="fc":

fold changes among classes;

test="sam":

SAM-statistics;

test="modt":

moderated t-statistics;

test="modf":

moderated F-statistics;

Value

A numeric vector, the length of which is determined by the length of the names of the test statistics for the argument test.

Details

Given the names of the test statistics, deds.genExtra generates extra parameters needed to be passed in the functions comp.stat and deds.stat.linkC for the assessment of differential expression. Both functions are interfaces to C functions. deds.genExtra generates default parameters as follows: If test="t" or "f", "fc", "modt", "modf", the extra parameter needed is the number of classes; If test="sam", the extra parameter needed is the percentile of within-gene standard deviations that the fudge factor $s_0$ will be set at and the default is 0.5; If test="B", the extra parameter needed is the percentage of alternative hypotheses (differential expression) and the default is set at 0.01.

Examples

Run this code

## two sample test
L <- rep(0:1, c(5,5))
extras <- deds.genExtra(L, c("t","sam", "B"))
## extras will be c(2, 0.5, 0.01)