dstar: Tools for Meta-analysis of gene expression data.

In Bioconductor/GeneMeta: MetaAnalysis for High Throughput Experiments

Tools for Meta-analysis of gene expression data.

Description

A small number of meta-analysis functions for comparing two gene expression experiments are provided.

Usage

dstar(d, n)
getdF(data, categ)
sigmad(d, ng1, ng2)

Arguments

d	A vector of t-statistics, i.e. the output of getdF.
n	The number of t-statistics.
data	The data used to compute t-statistics, either a matrix or an ExpressionSet.
categ	A vector of 0's and 1's indicating group membership.
ng1	The number of samples in group 1.
ng2	The number of samples in group 2.

Details

The functions getdF compute t-test statistics for the input data and group membership (note that group membership must be indicated by a vector of 0's and 1's).

The function dstar computes an unbiased estimate of the t-test. The function sigmad computes the variance estimate of dstar.

Value

The different functions have different return values, but generally they are vectors of the requested quantities.

Author(s)

L. Lusa, R. Gray and R. Gentleman

References

Choi et al, Combining multiple microarray studies and modeling interstudy variation. Bioinformatics, 2003, i84-i90.

Examples

  x = matrix(rnorm(1000), ncol=10)
  ds = getdF(x, rep(c(0,1), c(5,5)))
  dst = dstar(ds, ncol(x))
  sgd = sigmad(ds, 5, 5)

Bioconductor/GeneMeta documentation built on Oct. 29, 2023, 4:20 p.m.