This is a continuation of a long topic, addressed by post number rather than by page. Start at post 1 · go to the accepted answer.
Everything in post #27 holds. The case it does not cover is the one I have.
Aggregating first-hand accounts does not produce evidence of the kind a trial produces. It produces a description of who chose to post, which is a real thing and a different thing.
I would be glad to be shown a cleaner way of putting this.
Bookmarking this. I will come back when I have something worth adding.
Reporting rather than recommending, on community side-effect dataset. What happened is above. Whether it should have is a different question and not one I am qualified to answer.
Post #35 answers the question as asked. The question underneath it is different.
A codebook describing each field takes twenty minutes and is what makes the file usable by anyone but you. Most shared datasets here do not have one.
The mechanism is plausible, which is not the same as established.
Worth separating two things that post #35 runs together.
Sample size is not the only thing that determines what a dataset can support. Selection is usually the larger problem here and it does not improve with volume.
Worth reading the earlier posts in this thread before acting on mine.
Summarising the community side-effect dataset thread so far, since it is long and the answer is buried: the first reply has the method, the fourth has the correction to it, and the rest is people agreeing at length.
How to contribute: if you have longitudinal data you want to add, the format is simple: date, measurement, context. Contact the maintainer of the specific dataset.
The arithmetic on community side-effect dataset is the easy part and it is where the errors are, which is an uncomfortable combination. Show your working and someone will catch it.
Units in the column header, always, and the same units down the whole column. Mixed units in one field is the commonest defect in shared spreadsheets here.
A dataset is only useful if the collection method is described alongside it. Numbers without a protocol are a list rather than data.
I would put the burden of proof on the interesting explanation, not the dull one.
Where the community side-effect dataset reasoning breaks down for me is the step from the group result to the individual case. That step is almost never argued for.
Publishing the raw records alongside the summary is what makes a dataset checkable. A summary alone asks for trust that nobody has earned.
The answer changed when I changed how I was measuring, which was informative.
Adding the measurement that post #45 says would settle it.
Version the file rather than editing in place. A dataset that changes silently under an analysis makes the analysis unreproducible.
Where a dataset is used to support a claim in a maintained document, the version used should be cited. Otherwise the document and the data drift apart silently.
Sensible. I would want the same detail before I acted on it either.
Answering the question post #50 raises rather than the one it answers.
The honest answer on community side-effect dataset is that it depends, and the useful part is the list of what it depends on. Four items, in rough order of how much they matter.
Most people get the first two right and then argue about the fourth.
Checked the community side-effect dataset claim against the primary source this morning. It survives, with a narrower scope than the version quoted here. Posting the narrower scope.
Post #53 is the version of this I will quote in future. One addition.
Bias toward positive outcomes: datasets collected by members are biased toward people who found the compounds useful. People who did not respond do not return. People who had bad outcomes might have left the community.
Reading it back, the second half matters more than the first.
Post #53 describes the usual case. This is about the unusual one.
Where a value is derived rather than measured, mark it. Derived columns get treated as observations the moment the file leaves your hands.
This is the sort of thing the wiki should carry and currently does not.
Reading rather than contributing, but this is the most useful thread I have found on it.
Temporal bias: older data in a dataset might reflect conditions (supplier, formulation, context) that have changed. Newer data is more current.
Good question, well framed, and I would like to see it answered properly.
Picking up post #57: that is the part I would want checked first.
Where a dataset is used to support a claim in a maintained document, the version used should be cited. Otherwise the document and the data drift apart silently.