Scientific publications

In this paper a multivariate homogeneity test (of whether two sets of observations arise from the same distribution) is proposed. The test is based on the concepts of multidimentional quantile function, minimum volume sets, and one-class support vector machines. The test statistic is as a matter of fact, the test statistic for binomial proportions. We conducted experimental comparison of our test with some statistical tests such as Hotelling test, multivariate rank test, and kernel Cramer test. For the experiments we used package R – open source environment for statistical computing and graphics which is freely available for most computing platforms.