Description Usage Arguments Value Author(s) References See Also Examples
This function inputs a list of non-overlapping sets (atoms) and a vector of estimated gene-level posterior probabilities of differential expression, and outputs a matrix with estimates of the following quantities: expected number of false discoveries (EFD), the expected number of missed discoveries (EFD), the expected fraction of false discoveries (EFDR), and the expected fraction of missed discoveries (EMDR) for the given atoms.
1 | errDisc(atoms, post.prob.genes)
|
atoms |
A list of non-overlapping sets (atoms). |
post.prob.genes |
Vector of the estimated gene-level probabilities of differential
expression (output from |
Matrix with the estimated EFD, EMD, EFDR, and EMDR for each atom in atoms
as columns.
Simina M. Boca
Boca S.M., H. Corrada Bravo, B. Caffo, J.T. Leek, and G. Parmigiani (2010): A decision-theory approach to interpretable set analysis for high-dimensional data, JHU Biostat Working Paper 211, http://www.bepress.com/jhubiostat/paper211/
postProb
1 2 3 4 5 6 7 8 9 10 11 12 | ##first obtain estimates of the gene-level posterior probabilities
data(GenderStats)
data(ChromSets)
gene.stat <- (gene.stat - mean(gene.stat))/sd(gene.stat)
set.seed(70790707)
post.prob.genes <- postProb(gene.stat, null = rnorm(20 * length(gene.stat),
+ 0, 1), K = length(gene.stat))
##now run errDisc function
EFD.EMD.res <- errDisc(sets, post.prob.genes)
head(EFD.EMD.res)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.