Rave: 538

[Joe Shlabotnik]

Nate Silver freaking nailed it!

The guy is on the short list now. He could name his price for any politician that wanted to make use of his services.

[slide_into_first]

Rasmussen and Gallup were tainted, I wonder why.

[thrill]

Scroll over the darts to see where each pundit landed: http://www.slate.com/articles/news_and_ ... sults.html

[Joe Shlabotnik]

oops - I guess not...

Silver lovers aren't waiting for these comparisons. They're riding high on victory, and giving credit to the bearer of good news. In doing so, they’ve made the same mistake that Silver's critics made last week: They've confused his projected odds with hard-and-fast predictions, and underestimated the accuracy of polling. The fact that Obama won doesn't make Nate Silver right, any more than a Romney win would have made him wrong.

[AWvsCBsteeeerike3]

oops - I guess not...

Silver lovers aren't waiting for these comparisons. They're riding high on victory, and giving credit to the bearer of good news. In doing so, they’ve made the same mistake that Silver's critics made last week: They've confused his projected odds with hard-and-fast predictions, and underestimated the accuracy of polling. The fact that Obama won doesn't make Nate Silver right, any more than a Romney win would have made him wrong.

fixed this for you

[Arthur Dent]

Kind of dumb article there. Using intelligent poll aggregates (instead of cherry picking polls, talking from gut feelings, reporting on mood, etc.), as popularized by Silver, is a big improvement and the results reflect that. Yes, the success is based mostly in getting lots of good polling data not Nate's personal awesomeness, and some of the whirligigs in the methodology may not be that great, but the author claims that the only benefit is the confidence estimate, which he completely misunderstands:

"The fact that Obama won Virginia looks good for averaged polling—indeed, his margin appears to be a couple points, not far off from what was predicted—but we'll never know about that other part. Did Obama really have a 79 percent chance of winning? To get a sense of that, we'd need to run yesterday's election like a lab experiment, doing it 10,000 times to see how often Obama wins. Since that can't happen, we're left to scratch our heads."

As jim posted elsewhere, this isn't right. The probability is representative of incomplete knowledge of the electorate and not a claim that the election results will be random. It would be better to say that we'd need to re-run the polls 10,000 times than the election.