TESTING THE APPROXIMATE AGREEMENT WITH A HYPOTHESIS

Abstract

When statistical tests are applied it is often known beforehand that the hypotheses would be rejected with sufficiently narge sample sizes. This happens whenever hypotheses is not exactly true but only approximately true. Some attempts of solution of this dilemma are discussed and exemplified with test of bioequivalence. One of these, powerfunction analysis, is applied on preparatory tests. In that case the approximate agreement with some condition (e.g. normal distribution) for the main analysis (e.g., t -test) is tested.