Where the group cannot agree, record the disagreement rather than resolving it by seniority. The recorded disagreement is more honest and more useful later.
This has been discussed before and I could not find the thread, so, again.
13 likes 11d
Evidence · Journal club · continued
Journal club: what we got wrong in an earlier session posts 91–120
This is a continuation of a long topic, addressed by post number rather than by page. Start at post 1.
Confirming post #91 from a second method, which matters more than confirming it from a second person.
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.
It is worth checking rather than assuming, which costs nothing.
4 likes 11d
Post #91 describes the usual case. This is about the unusual one.
Worth starting from what the authors set out to estimate rather than what they reported. Half the disagreements in a session dissolve once that is stated explicitly.
0 likes 11d
peak_purity, post #68: On post #67 — agreed on the reasoning, with one qualification. Suggest the next paper at the end of the session rather than by message afterwards. The room has just worked out what it wants to know next. Written in the hope of being told what I have missed. Go to post
Session format: read the paper before posting. The discussion is much better when everyone has. Start with the estimand and population, then methods, then results, then limitations. That order makes critique coherent.
On post #96 — agreed on the reasoning, with one qualification.
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.
This is the sort of thing that ought to be settled and apparently is not.
0 likes 9d
l.solberg, post #61: Reading a preprint in a session is fine provided the status is stated in the first minute and stays in the summary. Go to post
Picking up post #96: that is the part I would want checked first.
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.
f.chowdhury, post #70: I read post #67 twice before replying, because I had assumed the opposite. Where the group cannot agree, record the disagreement rather than resolving it by seniority. The recorded disagreement is more honest and more useful later. Noting that I have skin in this question and have tried to discount for it. Go to post
Post #96 put the caveat in the right place and I want to underline it.
Sessions on negative or null results are consistently the most instructive and the hardest to get anyone to attend.
a.delgado, post #10: Post #8 describes the usual case. This is about the unusual one. Where the group cannot agree, record the disagreement rather than resolving it by seniority. The recorded disagreement is more honest and more useful later. Posting it because the silence on this was starting to look like agreement. Go to post
Worth separating two things that post #99 runs together.
Where the group cannot agree, record the disagreement rather than resolving it by seniority. The recorded disagreement is more honest and more useful later.
If the premise is wrong, everything after it is decoration.
That is the distinction I keep failing to hold on to. Written down now.
15 likes 8d
Bringing the previous paper on the same question makes the session much better and doubles the preparation. Worth doing every third session rather than every one.
3 likes 8d
ma.nascimento, post #21: Useful. I had the fact and not the reason, which turns out to be the important half. Go to post
Post #103 and I disagree about the size of the effect, not about the direction.
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.
Adding it in case it saves somebody the afternoon it cost me.
Taking post #103 at face value and following it one step further.
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.
For what it is worth, the same held on the two occasions I checked.
10 likes 7d
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.
Not a conclusion. A place to stand while looking for one.
1 like 7d
bench_peak, post #45: Post #42 is the version of this I will quote in future. One addition. A session that ends with a list of what remains unresolved is more useful than one that ends with a verdict. The unresolved list is what feeds the next reading. Go to post
Where the group cannot agree, record the disagreement rather than resolving it by seniority. The recorded disagreement is more honest and more useful later.
n.serrano, post #96: 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 would hold that lightly until someone with a larger sample weighs in. Go to post
I came in to disagree and I am leaving without a disagreement.
ai.vukovic, post #72: Post #69 answers the question as asked. The question underneath it is different. A session that ends with a list of what remains unresolved is more useful than one that ends with a verdict. The unresolved list is what feeds the next reading. Go to post
Adding the measurement that post #107 says would settle it.
Suggest the next paper at the end of the session rather than by message afterwards. The room has just worked out what it wants to know next.
I have changed my mind on this once already, so take it as current rather than settled.
Collapsed as off-topic by two members at trust level 3 or above
The figures usually contain the finding and the text usually contains the interpretation. Separating them for the first twenty minutes is a discipline worth keeping.
It is worth stating the boring hypothesis before the interesting one.
a.vestergaard, post #14: 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. Old habit: I write down the expected answer before I calculate it. Go to post
Post #110 is the version of this I will quote in future. One addition.
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.
It is a small point and it changes the answer, which is an awkward combination.
The arithmetic in post #114 is right; the assumption feeding it is the part to check.
Reading a preprint in a session is fine provided the status is stated in the first minute and stays in the summary.
This is the sort of thing the wiki should carry and currently does not.
0 likes 4d
Answering the question post #112 raises rather than the one it answers.
Nothing discussed in a session is advice to anybody, and clinician participants here say so themselves as a matter of course rather than because a rule requires it.
Reading it back, the second half matters more than the first.
3 likes 4d
aliquot_line, post #3: Building on post #2 rather than restating it. 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. Not disagreeing with anyone above, just adding the bit I keep having to look up. Go to post
The figures usually contain the finding and the text usually contains the interpretation. Separating them for the first twenty minutes is a discipline worth keeping.
Noted, and thank you for writing it out rather than summarising it.
24 likes 3d