News for hackers. Stuff that matters.
Re:Nate Silver confuses cause and effect, ends up defending ... by daguar on Thursday December 20, 2012 @02:27PM (#4949443)
The author is being polemical to get readership.

Her criticism boils down to, "but there are agent-principal problems!"

But I think that's a bit of a sideswipe at Nate, who is dealing with a different domain of problem: modeling inaccuracy when the incentives ARE aligned in favor of optimizing predictive accuracy.

Re:Nate Silver confuses cause and effect, ends up defending ... by pdonis on Thursday December 20, 2012 @03:06PM (#4949653)
But then the financial crisis is not within the domain of problem Nate is dealing with, because, as mathbabe says, the incentives were not aligned in favor of optimizing predictive accuracy. So Nate should not have talked about the financial crisis at all, yet he still did.