During commute I spontaneously generated a model for selection bias in law enforcement and now I need to actually write the damn thing.
remembering that lovely graph of how LEOs' belief in their Detect Lies skill goes up over time while their actual Detect Lies goes down
-
-
I haven't seen that. I was thinking more of a mis-directed K-Means clustering algorithm based on a shitty but consistent evaluation.
-
Specifically to not measure the entire region but take a biased sample, and then re-inforce the bias in subsequent iterations.
End of conversation
New conversation -
-
-
who needs being right when you have the power to make people behave as if you had been right?
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.