testMultipleControl
Multiple Comparison Statistical Test (Friedman + Control Holm PostHoc)
Usage
testMultipleControl(e, output, rankOrder = "max", alpha = 0.05)
Arguments
 e
 Input experiment
 output
 The output for which the tet will be performed.
 rankOrder
 The optimization strategy, can be either maximizing "max" or minimizing "min" the target output variable.
 alpha
 The significance level used for the whole testing procedure.
Value

an testMultipleControl object
Description
This function perfoms a multiple comparison statistical test for the given experiment. First of all it performs a Friedman Test over all methods. In the case this test is rejected, meaning that significant differences are present among the methods a posthoc test is then executed. For that, a comparison using the best method as a control is performed for each other method, finally a Holm familywise error correction is applied to the resulting pvalues.
Examples
# First we create an experiment from the wekaExperiment problem and prepare # it to apply the test: experiment < expCreate(wekaExperiment, name="test", parameter="fold") experiment < expReduce(experiment, "fold", mean) experiment < expSubset(experiment, list(featureSelection = "yes")) experiment < expInstantiate(experiment, removeUnary=TRUE) # Then we perform a testMultiplePairwise test procedure test < testMultipleControl(experiment, "accuracy", "max") summary(test) Friedman test, objetive maximize output variable accuracy. Obtained pvalue: 3.3072e04 Chi squared with 3 degrees of freedom statistic: 18.6000 Test rejected: pvalue: 3.3072e04 < 0.0500  Control post hoc test for output accuracy Adjust method: Holm Control method: RandomForest pvalues: J48 0.2579 NaiveBayes 0.0324 OneR 0.0001 