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.
The literature is thinner on this than the confidence in the thread implies.
0 likes 11mo
Data & Tools · Datasets · continued
Aggregated purity results across four services, with caveats — a second dataset posts 121–150
This is a continuation of a long topic, addressed by post number rather than by page. Start at post 1.
I would rather this thread reach "we do not know" about Aggregated purity results across four than reach a confident answer that nobody can support when asked.
1 like 11mo
t.dumitru, post #7: 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. Go to post
That is a cleaner way of putting what I was circling around.
On post #122 — agreed on the reasoning, with one qualification.
Where a value is derived rather than measured, mark it. Derived columns get treated as observations the moment the file leaves your hands.
It took me longer than it should have to see that.
15 likes 11mo
Post #124 answers the question as asked. The question underneath it is different.
I changed my mind about Aggregated purity results across four after someone here asked me for the source and I could not produce one. That is worth saying out loud because it is the ordinary way it happens.
0 likes 11mo
r.sobczak, post #78: Saving this. It is the version I will quote when the question comes round again. Go to post
What would change my mind on Aggregated purity results across four is a second dataset collected by someone with no stake in the first. Until then I hold it loosely and I would rather say so than pretend to more.
s.rasmussen, post #120: Two sentences on Aggregated purity results across four and then I will stop, because the rest is speculation and the thread is better without mine. What is documented is narrow. What is inferred from it is broad. The gap between them is where every argument here lives. Go to post
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.
Publishing the raw records alongside the summary is what makes a dataset checkable. A summary alone asks for trust that nobody has earned.
22 likes 11mo
ambient_review, post #67: Where a value is derived rather than measured, mark it. Derived columns get treated as observations the moment the file leaves your hands. If it helps: the failure mode here is usually boring rather than dramatic. Go to post
Where I part company with post #126, and it is a narrow parting.
The most useful dataset this community could hold is boring: lot, supplier, service, method, date, result. That is enough to answer most of the questions people ask badly.
Written quickly, so the reasoning may be tighter than the wording.
Temporal bias: older data in a dataset might reflect conditions (supplier, formulation, context) that have changed. Newer data is more current.
29 likes 11mo
Narrowing post #129, because the general version has more than one answer.
The number people quote for Aggregated purity results across four is a central estimate presented without its interval, and the interval is wide enough that the estimate is nearly uninformative on its own.
14 likes 11mo
a.adebayo, post #109: Aggregated purity results across four 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. Go to post
Post #129 put the caveat in the right place and I want to underline it.
Whatever the answer on Aggregated purity results across four turns out to be, the method for getting there is the same: state the assumption, do the arithmetic in public, invite the correction.
I read post #133 twice before replying, because I had assumed the opposite.
Independent test results are the most valuable data this community collects, and they are only comparable when the method is captured alongside the number.
Speaking for myself and not for anyone else who has posted here.
0 likes 11mo
two_year_line, post #126: What would change my mind on Aggregated purity results across four is a second dataset collected by someone with no stake in the first. Until then I hold it loosely and I would rather say so than pretend to more. Go to post
The version of Aggregated purity results across four that I was taught turned out to be a teaching simplification. Useful, and not true in the way I had assumed it was.
f.danquah, post #97: Appreciated. The plain phrasing does more work here than a longer post would. Go to post
One caution on Aggregated purity results across four: everything above assumes the underlying documentation is what it claims to be. That assumption is doing real work and is rarely stated.
A definition problem is doing most of the work in this Aggregated purity results across four discussion. Once the term is pinned down I suspect the disagreement mostly goes away and what is left is small.
0 likes 11mo
vial_desk, post #140: Combining results from different testing services into one column loses information that matters. Keep the service as a field. Go to post
Post #142 is the version of this I will quote in future. One addition.
A dataset is only useful if the collection method is described alongside it. Numbers without a protocol are a list rather than data.
That is the version I use. It may not be the version that is correct.
Publishing the raw records alongside the summary is what makes a dataset checkable. A summary alone asks for trust that nobody has earned.
I am not the right person to answer the follow-up to this.
19 likes 11mo
Post #144 describes the usual case. This is about the unusual one.
Independent test results are the most valuable data this community collects, and they are only comparable when the method is captured alongside the number.
I would be glad to be shown a cleaner way of putting this.
0 likes 11mo
r.szabo, post #14: 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. Happy to expand any of that if it is the useful part. Go to post
Helpful, and short, which on this subject is harder than long.
Post #146 answers the question as asked. The question underneath it is different.
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.
Marking that as an opinion rather than a finding.
0 likes 11mo
I read post #148 twice before replying, because I had assumed the opposite.
An honest declaration on Aggregated purity results across four: I have a prior here and it is strong enough that you should weight what I say downward. Stating it rather than hiding it.
4 likes 11mo