Studies designed to examine the equivalence of treatments are increasingly common in social and biomedical research. Herein, we outline the rationale and some nuances underlying equivalence testing of the difference between two means. Specifically, we note the odd relation between tests of hypothesis and confidence intervals in the equivalence setting.
Blair, R. Clifford and Cole, Stephen R.
"Two-Sided Equivalence Testing Of The Difference Between Two Means,"
Journal of Modern Applied Statistical Methods:
1, Article 18.
Available at: http://digitalcommons.wayne.edu/jmasm/vol1/iss1/18