Interesting paper that discusses breaks down a *cultural* distinction in stats: gambler vs scientist.
Most Bayesians are gamblers and Frequentists are scientists, but nothing fundamental to this. Just cultural. https://buff.ly/2Zx8CEU
ht @georgizgeorgiev
That "frequentist" is just wrong by any standard. It's not that "the probability of this result happening by chance is X", it's "if the result were chosen by pure chance, the probability of this result happening would be X".
-
-
Lots and lots of people get this wrong, of course, even among those who should know better. It's confusing P(A|B) with P(B|A), and Bayes' Theorem relates the two. But frequentists don't actually deny Bayes' Theorem; they just abstain from using it.
-
Not quite - frequentists say you can't use probability to represent opinions. The Bayesian probability is an opinion about the world. Bayes rule is changing your opinion when you see new data. Frequentist probability is about the long run occurrence of hypothetical events.
- 1 more reply
New conversation -
-
-
No he's right - the probability of getting "sun exploded" by chance if the sun didn't explode (i.e. H0) is 1/36. That is the objective error probability (the p-values) promised by frequentists. The power of the test p(report pos|true pos) is 100% according to the comic.
-
You're including the "if" clause, which makes it correct. He isn't.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.