[Retric]

“Where is the collection”

The samples that make such a calculation true. That’s what you’re missing an actual statistic X>Y is based on the underlying data.

Further someone can just as easily make up X = 27.24 +/- 0.01 with a 95% confidence interval as X > Y, it’s the actual data that makes something a fact rather than an option.

“None of the stuff you mention actually means anything when you try to apply it to policy if you don't know how the result was achieved, what it's actually measuring, and what the baseline is.” Again that applies equally to all statistics and you can provide them just as easily with either format.

[giantg2]

"The samples that make such a calculation true."

THAT'S WHAT I'M ASKING TO SEE! Which you didn't initial post!