News for hackers. Stuff that matters.

A comment on Berkson's Paradox. Parent comment

Re:Berkson's Paradox by rrmm on Wednesday March 24, 2021 @04:14PM (#26572319)
The series of tweets for me just wasn't illuminating and I didn't get what the actual 'paradox' was given the graphs. But my issue was more that the graphs weren't clear in pointing out what I should be looking at.

Wikipedia was much clearer for me, https://en.wikipedia.org/wiki/Berkson's_paradox , but ymmv of course.

Another good statistical foible to be aware of along with Simpson's.

[ Parent | on HN ]
Re:Berkson's Paradox by billynomates111 on Thursday March 25, 2021 @04:15AM (#26577575)
If anyone's impatient like me, this example from wikipedia helped me get it:

> For example, a person may observe from their experience that fast food restaurants in their area which serve good hamburgers tend to serve bad fries and vice versa; but because they would likely not eat anywhere where both were bad, they fail to allow for the large number of restaurants in this category which would weaken or even flip the correlation.

[ Parent | on HN ]
Re:Berkson's Paradox by klyrs on Wednesday March 24, 2021 @09:25PM (#26575488)
Having selected for interesting content: quality of presentation is inversely correlated to length of a tweet thread?
[ Parent | on HN ]