RankingEbam {GeneSelector} | R Documentation |
The approach of Efron et al. (2001) is based on a mixture model
for two subpopulations: genes that are differentially expressed and
those not. The posterior probability for differential
expression is used to obtain a ranking.
The function described below is merely a wrapper for the
function z.ebam
from the package siggenes
.
For S4
method information, see RankingEbam-methods.
RankingEbam(x, y, type = c("unpaired", "paired", "onesample"), gene.names = NULL, ...)
x |
A |
y |
If |
type |
|
gene.names |
An optional vector of gene names. |
... |
Further arguments passed to the function |
To find a better value for the fudge factor, the function
find.a0
(package siggenes
) can be used.
An object of class GeneRanking.
P-values are not computed - the statistic is a posterior probabiliy.
Martin Slawski
Anne-Laure Boulesteix
Efron, B., Tibshirani, R., Storey, J.D., Tusher, V. (2001).
Empirical Bayes Analysis of a Microarray Experiment.
Journal of the American Statistical Association, 96, 1151-1160.
Schwender, H., Krause, A. and Ickstadt, K. (2003).
Comparison of the Empirical Bayes and the Significance
Analysis of Microarrays.
Techical Report, University of Dortmund.
RepeatRanking, RankingTstat, RankingFC, RankingWelchT, RankingWilcoxon, RankingBaldiLong, RankingFoxDimmic, RankingLimma, RankingWilcEbam, RankingSam, RankingShrinkageT, RankingSoftthresholdT, RankingPermutation
### Load toy gene expression data data(toydata) ### class labels yy <- toydata[1,] ### gene expression xx <- toydata[-1,] ### run RankingEbam Ebam <- RankingEbam(xx, yy, type="unpaired")