A0228
Title: DTH: A nonparametric test for homogeneity of multivariate dispersions
Authors: Asmita Roy - Johns Hopkins University (United States) [presenting]
Glen Satten - Emory University (United States)
Ni Zhao - Johns Hopkins University (United States)
Abstract: Testing homogeneity across groups in multivariate data is an important scientific question in its own right, as well as an auxiliary step in verifying the assumptions of ANOVA. Existing methods either construct test statistics based on the distance of each observation from the group center or on the mean of pairwise dissimilarities among observations in a group. Both approaches can fail when the mean within-group distance is similar across groups, but the distribution of the within-group distances is different. This is a pertinent question in high-dimensional microbiome data, where outliers and overdispersion can distort the performance of a mean-dissimilarity-based test. The non-parametric distance-based test for homogeneity(DTH) is introduced, which measures dissimilarity between groups by comparing the empirical distribution of within-group dissimilarities using a combination of the Kolmogorov-Smirnov and Wasserstein distances. For more than two groups, pairwise group tests are combined using a permutation-based p-value. Through simulations, it is shown that the method has higher power than existing tests for homogeneity in certain situations and comparable power in other situations. A simple framework is also provided for extending the test to a continuous covariate.
