Is SURMOUNT-1 a fair comparison of tirzepatide against its comparator arm?

The specifics, since they change the answer: SURMOUNT-1 · tirzepatide.

Somebody stated this to me confidently and I would like to check it before repeating it.

I would accept a well-reasoned negative answer over a poorly sourced positive one.

Is this actually true, and what is the evidence?

Fair depends on the comparator arm, and in SURMOUNT-1 that means asking whether the comparator was titrated to the same ambition as the experimental one. A head-to-head that runs its comparator to a dose below the one it is licensed at is not measuring the two agents, it is measuring one agent against a handicapped version of the other. Check three things: the maximum comparator dose reached, the proportion of the comparator arm that reached it, and whether the titration schedules had the same duration. If those match, the comparison is fair on dosing and the argument moves to the endpoint. If they do not, the effect size is partly an artefact of the protocol.

Answer first: read the primary endpoint, the comparator and the population before you read the effect size. Almost every argument on this site about a trial is really an argument about one of those three.

Intention-to-treat and per-protocol analyses answer different questions. ITT asks what happens if you offer the treatment; per-protocol asks what happens if it is taken as directed. The gap between the two is a measure of how tolerable the protocol was.

In practice, duration decides what can be seen. A 68-week trial can measure weight and glycaemia; it cannot measure anything whose event rate is one per cent per year without enrolling tens of thousands.

The caveat is that trial evidence is about licensed product administered under supervision. None of it transfers automatically to research-grade material of unverified content.

Read the protocol and the statistical analysis plan if the result matters to you. Both are usually published alongside.