RankingBaldiLong: Ranking based on the t-statistic of Baldi and Long
In GeneSelector: Stability and Aggregation of ranked gene lists

Description Usage Arguments Details Value Note Author(s) References See Also Examples

Performs bayesian t tests on a gene expression matrix.

1 2	RankingBaldiLong(x, y, type = c("unpaired", "paired", "onesample"), m = 100, conf = NULL, pvalues = TRUE, gene.names = NULL, ...)

`x`	A `matrix` of gene expression values with rows corresponding to genes and columns corresponding to observations or alternatively an object of class `ExpressionSet`. If `type = paired`, the first half of the columns corresponds to the first measurements and the second half to the second ones. For instance, if there are 10 observations, each measured twice, stored in an expression matrix `expr`, then `expr[,1]` is paired with `expr[,11]`, `expr[,2]` with `expr[,12]`, and so on.
`y`	If `x` is a matrix, then `y` may be a `numeric` vector or a factor with at most two levels. If `x` is an `ExpressionSet`, then `y` is a character specifying the phenotype variable in the output from `pData`. If `type = "paired"`, take care that the coding is analogously to the requirement concerning `x`.
`type`	"unpaired": two-sample test. "paired": paired test. Take care that the coding of `y` is correct (s. above). "onesample": `y` has only one level. Test whether the true mean is different from zero.
`m`	Size of the sliding window that is used obtain the background variance from pooled similarly expressed genes, s. details.
`conf`	The number of 'pseudocounts' giving weight to the prior variance, s. details.
`pvalues`	Should p-values be computed ? Default is `TRUE`.
`gene.names`	An optional vector of gene names.
`...`	Currently unused argument.

The argument m determines the width of the window used to obtain an estimate for the average variability of gene expression for those genes that show a similar expression level.
The argument conf is non-negative and denotes the weight given to the Bayesian prior estimate of within-treatment variance. Baldi and Long report reasonable performance with this parameter set equal to approximately 3 times the number of observations, when the number of experimental observations is small (approximately 4 or less). If the number of replicate experimental observations is large then the confidence value can be lowered to be equal to the number of observations (or even less).

An object of class GeneRanking.

Results can differ slightly from the Cyber-T-Software of Baldi and Long.

Martin Slawski
Anne-Laure Boulesteix

Baldi,P., Long, A.D. (2001).
A Bayesian framework for the analysis of microarray data. Bioinformatics, 17, 509-519

RepeatRanking, RankingTstat, RankingFC, RankingWelchT, RankingWilcoxon, RankingFoxDimmic, RankingLimma, RankingEbam, RankingWilcEbam, RankingSam, RankingShrinkageT, RankingSoftthresholdT, RankingPermutation

## Load toy gene expression data
data(toydata)
### class labels
yy <- toydata[1,]
### gene expression
xx <- toydata[-1,]
### run RankingBaldiLong
BaldiLong <- RankingBaldiLong(xx, yy, type="unpaired")