News for hackers. Stuff that matters.

A comment on New method identifies the root causes of statistical outliers. Parent comment

Re:New method identifies the root causes of statistical outl... by strangedejavu on Tuesday July 19, 2022 @07:43PM (#32159447)
This argument doesn't make much sense to me. You can definitely associate a probability based just on the measured data. What if you measured 5, 5, 5, 5, 5, 5,5 (1000 more 5s) , 5, 999999999? I think it's pretty intuitive to say that 999999999 is unexpected relative to the 5s. And you certainly can have expectations that are generated purely based off of the measured distribution and not off of some theoretical model.
[ Parent | on HN ]
Re:New method identifies the root causes of statistical outl... by whatshisface on Tuesday July 19, 2022 @07:52PM (#32159511)
It is unexpected relative to the 5s, but it is also rare in your sample, meaning that its occurrence in the sample is in exact proportion to how often you'd expect it to occur, given the distribution you inferred from your sample. That means you have no grounds for singling it out as "abnormal."
[ Parent | on HN ]
Re:New method identifies the root causes of statistical outl... by nl on Tuesday July 19, 2022 @08:15PM (#32159687)
And here we see the "Bayesian vs Frequentist" argument.

If this gets resolved in a HN thread you should publish it.

[ Parent | on HN ]