...but the outer O is a Gaussian blur ring.
-
-
Replying to @St_Rev @Meaningness
So X and Y are perfectly correlated in the center, and uncorrelated outside it.
3 replies 0 retweets 0 likes -
Replying to @St_Rev @Meaningness
is there a good example in nature where this effect occurs?
2 replies 0 retweets 0 likes -
which effect tail independence or tail dependence?
1 reply 0 retweets 0 likes -
either
1 reply 0 retweets 0 likes -
for independence, any joint gaussian is tail independent *even if the variables are correlated!*
2 replies 0 retweets 0 likes -
if I understand any of this,
@The_Lagrangian ‘s lesswrong piece explains this well2 replies 0 retweets 1 like -
Replying to @Meaningness @karlrohe and
The LW piece is about range restriction. I don't get how that's related to this idea.
2 replies 0 retweets 0 likes -
Replying to @St_Rev
Well, with the proviso that I learned everything I know about pt from the back of a cereal box,
1 reply 0 retweets 0 likes -
Replying to @Meaningness @St_Rev
if you restrict to the near-extreme values then you can see why they become anticorrelated.
2 replies 0 retweets 0 likes
(which was the opposite of my intuition, and probably most people’s)
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.