A distribution-free procedure for the statistical analysis of bioequivalence studies.

摘要: In bioequivalence assessment, the consumer risk of erroneously accepting is primary concern. order to control risk, decision problem formulated with bioinequivalence as hypothesis and alternative. parametric approach, a split into two one-sided test problems application two-sample t-tests have been suggested. Rejection both hypotheses at nominal alpha-level equivalent inclusion classical (shortest) (1-2 alpha) 100%-confidence interval in range. This paper demonstrates that rejection by means nonparametric Mann-Whitney-Wilcoxon tests corresponding distribution-free (nonparametric) approach needs weaker model assumptions hence presents an alternative approach.