Equivalence tests assess whether there is a practical difference in means. You must pick a threshold difference for which smaller differences are considered practically equivalent. The most straightforward test to construct uses two one-sided t-tests from both sides of the difference interval. If both tests reject (or conclude that the difference in the means differs significantly from the threshold), then the groups are practically equivalent. The Equivalence Test option uses the Two One-Sided Tests (TOST) approach. See Example of an Equivalence Test.

Help created on 7/12/2018