However, in the second example, the analysis method matters: keeping the non-inferiority margin fixed leads to a borderline significant result, and using the post hoc modification of the non-inferiority margin method leads to the same conclusion, as the non-inferiority margin modification is minimal.
← all excerpts
The Smooth Away From Expected (SAFE) non-inferiority frontier: theory and implementation with an application to the D3 trial.
1
—
—