Two-Sample Nonparametric Test for Testing Equality of Locations Based on Data Depth

In the recent years, the notion of data depth has been widely used in multivariate data analysis since it measures the centrality or outlyingness of the multivariate data points with respect to the given data cloud and it orders the data from center to outward in any direction called ‘center-outward ordering’. In the present work, we propose a nonparametric test for testing equality of location parameter of two multivariate distributions using notion of data depth. The proposed test is motivated from the concept of correlation. We compare powers of the proposed test with existing tests for multivariate symmetric and skewed distributions through simulation. The proposed test gives an attractive powers against various alternatives. Application to a real life data is also provided.