In data science, when dealing with low probability events, the global distribution function is useless.
-
-
Replying to @EmilyGorcenski
To analyze events in the tail, you need to explore the tail distribution.
1 reply 1 retweet 13 likes -
Replying to @EmilyGorcenski
Put one way: 99.999% of aircraft servos work fine. But what happens when the 0.0001% don't? You can't use the population mean.
1 reply 1 retweet 9 likes -
Replying to @EmilyGorcenski
You have to look at the behavior locally in the tail.
2 replies 1 retweet 7 likes -
Replying to @EmilyGorcenski
Trans women of color are in the tail of the population distribution. There are so few that applying averages doesn't work.
1 reply 2 retweets 16 likes -
Replying to @EmilyGorcenski
We have to understand the dynamics of their lives in the tail. We don't need to wait for a right wing extremist to kill us to be afraid.
2 replies 1 retweet 17 likes -
Replying to @EmilyGorcenski
We can just be afraid. The statistics, broadly applied, don't apply locally.
1 reply 2 retweets 17 likes
If we wait for it to happen, we were afraid too late. That's our reality. Those are our local features here in the tail.
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.
