NONPARAMETRIC VALIDATION OF SIMILAR DISTRIBUTIONS AND ASSESSMENT OF GOODNESS-OF-FIT

In this paper the problem of assessing the similarity of two cumulativ e distribution functions F and G is considered. An asymptotic test bas ed on an alpha-trimmed version of Mallows distance Gamma(alpha)(F, G) between F and G is suggested, thus demonstrating the similarity of F a nd G within a preassigned Gamma(alpha)(F, G) neighbourhood at a contro lled type I error rate. The test proposed is applied to the validation of goodness of fit and for the nonparametric assessment of bioequival ence It is shown that Gamma(alpha)(F, G) can be interpreted as average and population equivalence. Our approach is illustrated by various ex amples.