TANOVA (version 1.0.0)

F.stat.null: Generation of null F-statistics by bootstrap method

Description

This is an internal function to be called by tanova to generate null distribution of F-statistics. Users should call tanova whenever is possible.

Usage

F.stat.null(data,f1,f2,type,trim=0,B=100,equal.size=FALSE,eb=FALSE) F.stat.null2(data,f1,f2,tp,type,B=100,trim=trim,eb=FALSE)

Arguments

data

a data matrix containing expression values. Row and column represent gene (probe set) and array respectively

f1

a vector containing the levels of a factor in each array

f2

a vector containing the levels of a factor in each array

tp

a vector with length equal to the number of arrays. Each entry indicates the time point for the corresponding array. tp takes values 1,2,3 .... For non-time course data, let tp=0.

type

type of test the null F-statistics is for, 1 for, 2 for, 3 for, 4 for

trim

the fraction (0 to 0.5) of observations to be trimmed from each end of x before the mean is computed. Values of trim outside that range are taken as the nearest endpoint.

B

number of bootstrap resampling

equal.size

a logical indicator of whether the number of replicates under each biological condition is equal. Default is FALSE.

eb

whether to use Bayesian prior

Value

F.null

null F-statistics, each column is a bootstrap sampling.

See Also

tanova

Examples

	##data=matrix(rnorm(10000,mean=6, sd=1),nrow=500, ncol=20)
	##f1=rep(c(1,2), each=10)
	##f2=rep(c(1,2), 10)
	##F.stat.null(data,f1,f2,type=1,trim=0,B=100,equal.size=FALSE,eb=FALSE)