This is a continuation of a long topic, addressed by post number rather than by page. Start at post 1.
When trials differ in population, duration and comparator, the pooled estimate answers a question no individual trial asked. That is worth saying before the number is quoted.
The part I am sure of is shorter than the part I have written.
Sensitivity analysis: the authors re-run the meta-analysis excluding studies one at a time, or by quality, to see whether the pooled estimate changes. Robust results stay similar even when individual studies are excluded.
I have kept the units in throughout, for the obvious reason.
Confirming post #92 from a second method, which matters more than confirming it from a second person.
The claim about Individual participant data versus aggregate upthread is stronger than its source supports. I have read the source. The source says "associated with" and the post says "causes".
I had written a reply contradicting post #90 and deleted it. Here is what survived.
My understanding of Individual participant data versus aggregate is a few years old and may have been superseded. If it has been, I would genuinely like to know rather than keep repeating it.
Double extraction with disagreement resolution is standard and is worth checking for, because single extraction errors are common and non-random.
Filing this under things that are true until someone shows me otherwise.
On post #94 — agreed on the reasoning, with one qualification.
Adding what did not work for me on Individual participant data versus aggregate, since the failures never get written up and they are half the useful information.
Post #96 is right about the mechanism and I think understates the practical bit.
Individual participant data versus aggregate has a well-known answer and a correct answer, and the interesting work is establishing that they are the same. Nobody has done that here yet.
This follows post #96 rather than contradicting it.
I have three months of notes on Individual participant data versus aggregate and the honest summary is that the trend is real and the week-to-week numbers are noise. I nearly drew the opposite conclusion from the first fortnight.
Worth separating two things that post #98 runs together.
Something worth flagging about Individual participant data versus aggregate: the strongest-sounding claims in this thread are the ones with no source attached, which is the usual pattern and not a coincidence.
Pooled estimates and heterogeneity: when trials differ in population, duration, or comparator, a pooled estimate answers a question that no individual trial asked. High heterogeneity means effects genuinely differ across studies. The pooled number is an average of things that should not have been averaged.
Correct me on the arithmetic if it is wrong; I would rather know.
Useful. I had the fact and not the reason, which turns out to be the important half.
Picking up post #101: that is the part I would want checked first.
An honest declaration on Individual participant data versus aggregate: I have a prior here and it is strong enough that you should weight what I say downward. Stating it rather than hiding it.
Study quality and weighting: some meta-analyses weight all studies equally; others weight by study size or study quality. The choice affects the result and should be stated and justified.
I would call that likely rather than established.
Coming back to post #104, because the follow-up matters more than the original answer.
Individual participant data versus aggregate would be much easier to settle if anyone reported the denominator. Almost nobody reports the denominator.
Double extraction with disagreement resolution is standard and is worth checking for, because single extraction errors are common and non-random.
The claim is narrower than it sounds, and deliberately so.
Distinguishing three things in the Individual participant data versus aggregate discussion that keep getting used interchangeably: the observation, the proposed mechanism, and the recommendation that gets attached to both.
Building on post #106 rather than restating it.
I think the Individual participant data versus aggregate question is answerable and has not been answered, which is a more optimistic position than most of this thread.
Post #108 put the caveat in the right place and I want to underline it.
Study quality and weighting: some meta-analyses weight all studies equally; others weight by study size or study quality. The choice affects the result and should be stated and justified.
Not a strong opinion, just a consistent one.
I read post #107 twice before replying, because I had assumed the opposite.
An observation about Individual participant data versus aggregate that I cannot explain and am posting anyway, on the principle that unexplained observations are more useful public than private.
Double extraction with disagreement resolution is standard and is worth checking for, because single extraction errors are common and non-random.
| Topic | Participants | Replies | Views | Activity |
|---|---|---|---|---|
|
What pooling buys you and what it destroys
The question in the title: What pooling buys you and what it destroys I will give what I have already checked below so nobody repeats it. The question about pooling buys that I actually want answered is the…
|
+74 | 83 | 6.6k | 8mo |
|
About the Meta-analyses category
Pooled estimates, heterogeneity, publication bias, and when pooling was a mistake. This post is a community wiki: any member at trust level 3 or above can edit it, and every edit is recorded with its author…
|
4 | 15k | 13mo | |
|
Second pass at: When a network meta-analysis is defensible and when it is not
Posting this under the heading it deserves: Second pass at: When a network meta-analysis is defensible and when it is not Everything below is what sits behind that. Posting a small dataset on network…
|
2 | 2.8k | 21mo | |
|
Reading a meta-analysis you disagree with, fairly
Posting this under the heading it deserves: Reading a meta-analysis you disagree with, fairly Everything below is what sits behind that. I would like to disagree carefully with the settled view on reading a…
|
+7 | 13 | 2.5k | 23mo |
|
Revisiting: What pooling buys you and what it destroys
On the subject in the title: Revisiting: What pooling buys you and what it destroys Working notes rather than a conclusion. Pooling buys — I have the observation and I do not trust my interpretation of it, so…
|
+97 | 107 | 4k | 19h |
| Topic | Participants | Replies | Views | Activity |
|---|---|---|---|---|
|
Second pass at: Triple agonism: additive, synergistic, or neither?
Second pass at: Triple agonism: additive, synergistic, or neither? — that is the question, and I have not found it answered plainly anywhere I have looked. Posting a small dataset on Triple agonism. It is…
|
+114 | 120 | 1.4k | 10mo |
|
SURMOUNT-4 and what withdrawal data does and does not tell an individual — one year on
Posting this under the heading it deserves: SURMOUNT-4 and what withdrawal data does and does not tell an individual — one year on Everything below is what sits behind that. I would like to disagree carefully…
|
+122 | 136 | 48k | 9mo |
|
[2026 update] Heterogeneity as information rather than as a nuisance
Heterogeneity as information rather than as a nuisance Writing it up because I had to work it out twice and would rather nobody else did. I have seen SURPASS-4 ( Lancet , 2021) cited in support of a claim I…
|
4 | 32k | 11mo | |
|
Second pass at: Journal club: STEP 4 and what a withdrawal design can prove
Second pass at: Journal club: STEP 4 and what a withdrawal design can prove Writing it up because I had to work it out twice and would rather nobody else did. The question about STEP 4 that I actually want…
|
+81 | 90 | 54k | 9mo |
|
Multiplicity when you track fifteen variables
Multiplicity when you track fifteen variables — setting out what I have, and where I think it stops being reliable. Asking about multiplicity directly, because I have read four threads on it and each answered…
|
2 | 60k | 11mo |