[2026 update] Composite endpoints and the component doing the work posts 31–60
This is a continuation of a long topic, addressed by post number rather than by page. Start at post 1.
Agreed on Composite endpoints, with one qualification that I think matters. The reasoning holds for the case as described. Change the starting assumption and it does not, and the starting assumption is the part nobody states.
A treatment-policy estimand asks what happens to people assigned to a strategy, including those who abandon it. A hypothetical estimand asks what would have happened had everyone continued. Both are legitimate and they give different numbers.
Written quickly, so the reasoning may be tighter than the wording.
Narrowing post #33, because the general version has more than one answer.
Two people in this thread mean different things by Composite endpoints and are disagreeing about the definition while believing they are disagreeing about the facts. Worth pausing to define it.
Absolute and relative effects answer different questions. Write down the event rate in each arm and the difference between them; everything quotable is derived from those two numbers.
That is the shape of it. The detail is where I would expect to be corrected.
Answering the question post #33 raises rather than the one it answers.
Adding a reference point for Composite endpoints. Mine is a single case, collected without controls, and I am posting the method alongside it so it can be discounted appropriately.
The arithmetic in post #37 is right; the assumption feeding it is the part to check.
Surrogate endpoints: an endpoint that is not the outcome that matters but is measured as a stand-in. HbA1c is a surrogate for long-term glucose control and the short-term complications it prevents. Weight loss is a surrogate for metabolic health and long-term outcomes. Surrogates are useful but not identical to the endpoint that matters.
Composite endpoints is a question about a distribution, not about a value, and treating it as a value is what produces the confident wrong answers.
Risk of bias: structured appraisal of internal validity. Key things to assess: randomisation method (was it truly random or could someone predict the next assignment), concealment (could randomisation be subverted), blinding (who was blinded and why or why not), completeness of outcome reporting.
Anyone with a larger sample, please post it.
Multiplicity and multiple comparisons: if a trial tests many hypotheses, the chance of a false positive on at least one by random chance increases. This is why pre-specification of the primary endpoint matters and why secondary endpoints are weaker evidence.
This is where my knowledge stops and I would rather mark the edge than blur it.
Confirming post #42 from a second method, which matters more than confirming it from a second person.
I disagree with the framing of Composite endpoints above, and I think it is a substantive disagreement rather than a terminological one. Setting out why, so it can be checked.
The reasoning depends on an assumption that is doing a lot of work and is never stated. If the assumption holds, the conclusion follows. I do not think it holds generally.
Saving this. It is the version I will quote when the question comes round again.
A treatment-policy estimand asks what happens to people assigned to a strategy, including those who abandon it. A hypothetical estimand asks what would have happened had everyone continued. Both are legitimate and they give different numbers.
The right answer here may simply be that it has not been measured.
Absolute and relative effects answer different questions. Write down the event rate in each arm and the difference between them; everything quotable is derived from those two numbers.
I keep a log of this specifically because memory is unreliable about it.
Where I part company with post #45, and it is a narrow parting.
Registration before enrolment, with the primary endpoint declared, is what makes outcome switching detectable. Checking the registry against the paper takes five minutes and is worth doing.
One case, stated as one case.
Narrowing post #46, because the general version has more than one answer.
Two sentences on Composite endpoints and then I will stop, because the rest is speculation and the thread is better without mine.
What is documented is narrow. What is inferred from it is broad. The gap between them is where every argument here lives.
I would be cautious about generalising from the Composite endpoints example above. It is a good example. It is one example.
Absolute numbers, not just relative: a 30% relative reduction tells you the ratio but not the practical magnitude. The event rate in each arm and the difference between them tells you how many people benefit.
Filing this under things that are true until someone shows me otherwise.
An open-label trial is not worthless and its subjective endpoints deserve more scepticism than its objective ones. That is a graded judgement rather than a verdict.
I would rather be precise about what I do not know than vague about what I do.
Marking my uncertainty on Composite endpoints explicitly. I am confident about the direction, much less confident about the size, and not confident at all that it generalises past the case in the first post.
Post #51 is right about the mechanism and I think understates the practical bit.
Taking Composite endpoints seriously for a moment rather than deflecting: the honest position is that the community has observations and no controlled comparison, and those two things support very different sentences.
Useful. I have added it to my own notes with the date on it.
Collapsed as off-topic by two members at trust level 3 or above
Absolute and relative effects answer different questions. Write down the event rate in each arm and the difference between them; everything quotable is derived from those two numbers.
I had written a reply contradicting post #54 and deleted it. Here is what survived.
Whatever the answer on Composite endpoints turns out to be, the method for getting there is the same: state the assumption, do the arithmetic in public, invite the correction.
Confirming post #57 from a second method, which matters more than confirming it from a second person.
On Composite endpoints, I would rather understate and be corrected upward than overstate and be quoted. That is a house style here and it is a good one.
Absolute numbers, not just relative: a 30% relative reduction tells you the ratio but not the practical magnitude. The event rate in each arm and the difference between them tells you how many people benefit.
Adding the measurement that post #59 says would settle it.
I would call the community position on Composite endpoints likely rather than established, and I would be comfortable defending that hedge.