sampling {globaltest}R Documentation

Sampling random 'pathways' for the Global Test


For every pathway in a result of globaltest, calculates how many randomly drawn groups of genes of the same size have a smaller or equal p-value.


sampling(gt, geneset, ndraws = 10^3)


gt The output of a call to globaltest.
geneset The name or number of the geneset(s) to be used (only necessary if multiple genesets were tested).
ndraws The number of random pathways to be used.


For every pathway in gt[geneset], a number ndraws random 'pathways' is selected by randomly sampling sets of genes of the same size as the tested pathway. A 'comparative p-value' is calculated by counting what proportion of the random pathways has a smaller or equal p-value than the tested pathway.


An object of class gt.result.


The function sampling cannot be applied to a gt.result object resulting from a call to permutations.


Jelle Goeman:; Jan Oosting


J. J. Goeman, S. A. van de Geer, F. de Kort and J. C. van Houwelingen, 2004, A global test for groups of genes: testing association with a clinical outcome, Bioinformatics 20 (1) 93–99. See also the How To Globaltest.pdf included with this package.

See Also

globaltest, permutations, sampleplot, geneplot.


    data(exampleX)      # Expression data (40 samples; 1000 genes)
    data(exampleY)      # Clinical outcome for the 40 samples
    pathway <- 1:25     # A pathway contains genes 1 to 25
    gt <- sampling(globaltest(exampleX, exampleY, test.genes = pathway))

[Package globaltest version 3.2.0 Index]