contrastEstimationMatrix: Contrast estimation based on medians

In scmamp: Statistical Comparison of Multiple Algorithms in Multiple Problems

Description

This function performs estimates the contrast between algorithms through the medians

Usage

contrastEstimationMatrix(data)

Arguments

data	Matrix or data frame with the data to compare

Details

The test has been implemented according to Garcia et al. (2010), Section 3.3.

Value

A matrix where the estimation of all the pairs of differences are output. The differences correspond to row-column.

References

Kanji, G. K. (2006) 100 Statistical Tests. SAGE Publications Ltd, 3rd edition.

Examples

data(data_gh_2008)
contrastEstimationMatrix(data.gh.2008)

Example output

              C4.5 k-NN(k=1) NaiveBayes Kernel     CN2
C4.5        0.0000    0.0491     0.0059 0.1722  0.0348
k-NN(k=1)  -0.0491    0.0000    -0.0432 0.1231 -0.0143
NaiveBayes -0.0059    0.0432     0.0000 0.1663  0.0289
Kernel     -0.1722   -0.1231    -0.1663 0.0000 -0.1374
CN2        -0.0348    0.0143    -0.0289 0.1374  0.0000

scmamp documentation built on May 1, 2019, 10:10 p.m.