An orwellian discourse on the meaning and measurement of noninferiority.

The customary interpretation of active-controlled noninferiority trials is founded on a number of unverifiable assumptions. These assumptions can be circumvented, and the semantic and statistic interpretation of the trials placed on a more rational foundation, if treatment comparisons are analyzed from a Bayesian perspective. In conclusion, the resultant probabilistic measures thereby render the meaning of noninferiority more transparent and clinically relevant.