ClassifyR (version 1.2.4)

likelihoodRatioSelection: Selection of Differential Distributions with Likelihood Ratio Statistic

Description

Ranks features by largest ratio and chooses the features which have the best resubstitution performance.

Usage

"likelihoodRatioSelection"(expression, classes, ...) "likelihoodRatioSelection"(expression, trainParams, predictParams, resubstituteParams, alternative = c(location = "different", scale = "different"), ..., verbose = 3)

Arguments

expression

Either a matrix or ExpressionSet containing the training data. For a matrix, the rows are features, and the columns are samples.

classes

A vector of class labels.

trainParams

A container of class TrainParams describing the classifier to use for training.

predictParams

A container of class PredictParams describing how prediction is to be done.

resubstituteParams

An object of class ResubstituteParams describing the performance measure to consider and the numbers of top features to try for resubstitution classification.

alternative

A vector of length 2. The first element specifies the location of the alternate hypothesis. The second element specifies the scale of the alternate hypothesis. Acceptable values are "same" or "different".

...

Variables passed to getLocationsAndScales.

verbose

A number between 0 and 3 for the amount of progress messages to give. This function only prints progress messages if the value is 3.

Value

A list of length 2. The first element has the features ranked from most important to least important. The second element has the features that were selected to be used for classification.

Details

Likelihood ratio test of null hypothesis that the location and scale are the same for both groups, and an alternate hypothesis that is specified by parameters. The location and scale of features is calucated by getLocationsAndScales.

Examples

  if(require(sparsediscrim))
  {
    # Samples in one class with differential variability to other class.
    genesMatrix <- sapply(1:25, function(geneColumn) c(rnorm(100, 9, 1)))
    genesMatrix <- cbind(genesMatrix, sapply(1:25, function(geneColumn) rnorm(100, 9, 4)))
    classes <- factor(rep(c("Poor", "Good"), each = 25))
    likelihoodRatioSelection(genesMatrix, classes,
                    trainParams = TrainParams(), predictParams = PredictParams(),
                    resubstituteParams = ResubstituteParams(nFeatures = seq(10, 100, 10),
                                         performanceType = "balanced", better = "lower"))
  }