Journal club: SURMOUNT-OSA and a hard endpoint in a soft field posts 31–52

Worth stating the null on SURMOUNT-OSA before we explain it: the observation may be nothing. That possibility deserves a sentence and usually does not get one.

This follows post #31 rather than contradicting it.

A note on how SURMOUNT-OSA gets discussed rather than on SURMOUNT-OSA itself: the confident posts get the replies and the careful ones get ignored, and the careful ones have been right more often.

Coming back to post #31, because the follow-up matters more than the original answer.

The baseline characteristics table is the single most useful page for the questions that get asked here, because it tells you who the result applies to.

That is all I can say without guessing.

I read the earlier replies on SURMOUNT-OSA twice before writing this, because I had assumed the opposite and wanted to be sure I was disagreeing with what was said rather than what I expected.

Post #31 and I disagree about the size of the effect, not about the direction.

If you are new and reading this thread for the answer to SURMOUNT-OSA: the answer is conditional, the conditions are in the third reply, and the rest of the thread is worth skipping.

Taking post #35 at face value and following it one step further.

Where the group cannot agree, record the disagreement rather than resolving it by seniority. The recorded disagreement is more honest and more useful later.

Nothing above should be read as advice about what anyone else should do.

The arithmetic on SURMOUNT-OSA is the easy part and it is where the errors are, which is an uncomfortable combination. Show your working and someone will catch it.

Appreciated. The plain phrasing does more work here than a longer post would.

The most common failure mode is spending fifty minutes on the effect size and ten on the population. Reversing that ratio would improve most sessions.

I am confident about the direction and much less about the magnitude.

Adding a reference point for SURMOUNT-OSA. Mine is a single case, collected without controls, and I am posting the method alongside it so it can be discounted appropriately.

The failure mode on SURMOUNT-OSA is boring rather than dramatic. It is almost always the step everyone assumes was done correctly because it is too simple to get wrong.

Taking post #40 at face value and following it one step further.

Reading order that works for these sessions: registry entry, methods, baseline table, primary result, then abstract last. Reading the abstract first anchors everything that follows.

If anyone has run this properly I would rather read that than my own guess.

This settles it for me, at least until somebody posts a reason it should not.