Primary endpoint hierarchies and why order matters — one year on

On the subject in the title: Primary endpoint hierarchies and why order matters — one year on Working notes rather than a conclusion.

Comparing SELECT (N Engl J Med, 2023) with SURPASS-2 (N Engl J Med, 2021) and finding the comparison harder than it looks.

Different populations, different durations, different endpoints defined slightly differently, and in one case a different estimand. People compare the headline percentages anyway, including me until recently.

Is there a defensible way to put these side by side, or is the honest answer that there is not and we should stop?

post #2 is right about the mechanism and I think understates the practical bit.

Confounding in observational data: a third variable can explain an apparent association. In a randomised trial, randomisation balances unknown confounders. In observational data, observed confounders can be adjusted for but unknown ones cannot.

Worth separating two things that post #2 runs together.

Having read the exchange above, I think I was wrong earlier in this topic and I want to say so plainly rather than quietly editing.

The correction was fair and I had been repeating something I had not checked carefully enough.

Picking up post #2: that is the part I would want checked first.

Open-label design: unblinded trials admit expectation effects. For weight-loss trials where one arm loses substantial weight and the other does not, complete blinding is impossible anyway. The unblinded nature is a limitation worth noting.

Dropout is information: high dropout rates can indicate tolerability problems or lower efficacy than the summary suggests. Where the analysis handled dropouts matters. An intention-to-treat analysis with many dropouts can give a smaller apparent effect than per-protocol analysis.

Thank you for the correction. I have edited my earlier post with a note rather than silently, so the thread still makes sense to read. The error was mine and it was the kind that comes from remembering a figure instead of looking it up.

On post #4 — agreed on the reasoning, with one qualification.

Generalisability: the enrolled population was selected in ways that matter. Entry criteria, run-in periods, and the simple fact that people who agree to a multi-year trial differ from people who do not, all narrow the population. That is how internal validity is bought, at the cost of external validity.

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.

I read post #8 twice before replying, because I had assumed the opposite.

Practical note that does not fit anywhere else. Whatever you conclude from this topic, write down what you did and when. The single most useful thing in your own records is not any individual result; it is that they are dated and consecutive.

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.

The estimand: what the trial set out to estimate. Two trials can be identical in structure but estimate different things by using different handling rules for people who stop taking the drug. Treatment-policy and hypothetical approaches are both legitimate but answer different questions.

Population narrowness: most trials in this class enrolled fairly specific groups. Baseline body mass index ranges, exclusion of renal disease, exclusion of certain comorbidities, all narrow the population. Applying point estimates to someone well outside the range is an extrapolation.

This follows post #11 rather than contradicting it.

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.