Equal wealth distribution. (I'll see myself out now)
-
-
-
If you look through the thread, you'll find yourself in good company ;)
- 2 more replies
New conversation -
-
-
Gumbel. - Beautiful Cdf P(y| a, b) = exp(-exp(-(y-a)/b)); inverse transform rng =easy - Gives distribution of maximums from exponential distributions. - If x~ gumbel(a1, b), y~ gumbel(a2, b) then x-y ~ logistic(a1-a2, b) - if unobserved utility is gumbel, p(choice) is softmax
-
With a (screen) name like Savage Jim, I'm weighting this preference heavily.
End of conversation
New conversation -
-
-
Cauchy because it’s the nicest — it has no mean!
-
cc:
@kareem_carr because I think you'll enjoy
End of conversation
New conversation -
-
-
Manjaro! It has Arch's advantage of very current software available in the package manager, but it has (several) collections of reasonable default installs instead of making you configure and decide on every last wheedly detail
-
wait did I misunderstand the question? Poisson! I like the "it's mostly like this but you expect every so often to have a that"
- 1 more reply
New conversation -
-
-
The distribution of sample means, which because of the Central Limit Theorem can be described as normal even if the parent distribution from which the samples are drawn is not, which is, as I say to my students, a bit of fucking magic.
-
Ah, this is sorta what motivated my post! I've been trying to learn how to teach well, and I wanted to find ways to make normal distributions more intuitive and interesting.https://twitter.com/generativist/status/1137046146193301504 …
- 1 more reply
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.