A claim built entirely on a subgroup analysis Writing it up because I had to work it out twice and would rather nobody else did.
I would like to disagree carefully with the settled view on claim built, and I would like to be argued out of it if the disagreement is bad.
The disagreement is about one step, not about the conclusion. If the step holds I withdraw it entirely.
This is the answer, and the reason it is the answer is the more useful part.
Taking post #8 at face value and following it one step further.
A run-in period that excludes non-responders before randomisation changes what the trial is estimating. It is legitimate design and it must be stated in any summary.
I would treat that as a working assumption and revisit it.
This follows post #25 rather than contradicting it.
Worth separating claim built as a question about the compound from claim built as a question about the documentation. They get answered by different people and only one of them is answerable here.
Hold a trial to the standard something could actually have met. A criticism that no achievable design could have answered is a criticism of the field rather than of the paper.
That is the version I would defend. It is not the version I started with.
Everything in post #52 holds. The case it does not cover is the one I have.
Where a critique rests on a subgroup, check whether the interaction was tested. A difference between subgroups that is not statistically supported is not a difference.
The disagreement above is smaller than it looks once the terms are fixed.
Reframing claim built slightly, because I think the disagreement is about the question rather than the answer. If the question is "does it happen", yes. If it is "how often", nobody here knows.
This follows post #76 rather than contradicting it.
Placebo-controlled versus active-controlled changes what a result means entirely, and comparing across the two is one of the most common errors in this subcategory.
On reflection I would soften that slightly.
Read the full topic (81 posts)
| Topic | Participants | Replies | Views | Activity |
|---|---|---|---|---|
|
About the Study critique category
Structured criticism of a specific published study. Criticise the method, not the author. This post is a community wiki: any member at trust level 3 or above can edit it, and every edit is recorded with its…
|
4 | 114 | 16mo | |
|
Measurement error in a self-reported exposure
Posting this under the heading it deserves: Measurement error in a self-reported exposure Everything below is what sits behind that. The question about measurement error that I actually want answered is the…
|
+117 | 129 | 45k | 5mo |
|
Selection into a registry and what it does to the estimate
Selection into a registry and what it does to the estimate — setting out what I have, and where I think it stops being reliable. Working notes on selection rather than a conclusion. I would rather post the…
|
2 | 55k | 7mo | |
|
Coming back to: A structured critique template this community uses
Posting this under the heading it deserves: A structured critique template this community uses Everything below is what sits behind that. Reading back through what has been written here about structured…
|
+63 | 69 | 17k | 18h |
|
A claim built entirely on a subgroup analysis — what changed since
On the subject in the title: A claim built entirely on a subgroup analysis — what changed since Working notes rather than a conclusion. What changes if the standard account of claim built is wrong? I ask…
|
2 | 2k | 18mo |
| Topic | Participants | Replies | Views | Activity |
|---|---|---|---|---|
|
Reading a rodent study on a secretagogue without over-extrapolating — the long version
Reading a rodent study on a secretagogue without over-extrapolating — the long version — setting out what I have, and where I think it stops being reliable. A narrow question about Reading a rodent study,…
|
+59 | 66 | 30k | 4h |
|
Criticising the method without criticising the authors
Criticising the method without criticising the authors Writing it up because I had to work it out twice and would rather nobody else did. I was wrong about criticising the method without criticising in a…
|
+55 | 61 | 60k | 15mo |
|
Pooling trials with different estimands
On the subject in the title: Pooling trials with different estimands Working notes rather than a conclusion. Asking about pooling trials with different estimands on behalf of the question I keep seeing asked…
|
+120 | 132 | 2.3k | 1d |
|
One lot is one lot: when a report becomes a pattern
Posting this under the heading it deserves: One lot is one lot: when a report becomes a pattern Everything below is what sits behind that. Structured report rather than an opinion, following the format the…
|
2 | 19k | 14mo | |
|
Tracking a preprint to publication: a worked example — the long version
Posting this under the heading it deserves: Tracking a preprint to publication: a worked example — the long version Everything below is what sits behind that. A preprint question rather than a question about…
|
+38 | 47 | 560 | 22mo |