Abstract
A general way of constructing classes of goodness-of-fit tests for multivariate samples is presented. These tests are based on a random signed measure that plays the same role as the empirical process in the construction of the classical Kolmogorov-Smirnov tests. The resulting tests are consistent against any fixed alternative, and, for each sequence of contiguous alternatives, a test in each class can be chosen so as to optimize the discrimination of those alternatives.
Citation
A. Cabaña. E. M. Cabaña. "Transformed empirical processes and modified Kolmogorov-Smirnov tests for multivariate distributions." Ann. Statist. 25 (6) 2388 - 2409, December 1997. https://doi.org/10.1214/aos/1030741078
Information