Did Nate Silver nail it or what?

boooeee said:
I think Rachel would have had him on regardless, given that she's such an unabashed geek. Colbert too, probably (it would have played to his schtick). Probably not Maher, though.
Click to expand...

Why not? He had Frank Luntz and John Fund on in the last few weeks.
 
I think the bigger issue is the problem of large news outlets being willing to create a story ("dead heat" and so on) to increase their revenues rather than giving an accurate characterization of the polling. CNN, for example, had a story citing the national polling as evidence that the race was a dead heat on the eve of the election. Anyone who's had a civics class and understands how presidential elections work knew that the national polls were not evidence of a dead heat.

It really didn't even require boffo statistical models and super-accurate predictions to realize that the story was simply wrong.
 
What's really funny is that I'm seeing right-wingers complain that Silver's model was faulty because it was too accurate, claiming that if his percentages were actually correct he would have missed a few states instead of calling them all correctly.
 
ANTPogo said:
What's really funny is that I'm seeing right-wingers complain that Silver's model was faulty because it was too accurate, claiming that if his percentages were actually correct he would have missed a few states instead of calling them all correctly.
Click to expand...

Sort of the same logic that paranormal researchers used to offer to argue that when a subject was wrong more often than the expected by chance (i.e. the mean) in ESP tests that the subject must have some sort of negative ESP! :rolleyes:
 
ANTPogo said:
What's really funny is that I'm seeing right-wingers complain that Silver's model was faulty because it was too accurate, claiming that if his percentages were actually correct he would have missed a few states instead of calling them all correctly.
Click to expand...

...Whaaaaat? :newlol :newlol
 
Morrigan said:
...Whaaaaat? :newlol :newlol
Click to expand...

Here's a good example, though I've seen the same thing elsewhere too:

I never said Silver was wrong in his methodology. If his model was incorrect it would be because of the polling data not because of the model itself. I thought the polls were over estimating Democratic turnout which turned out to be 100% wrong.

If we want to be picky. If Silver "predicts" 50 out of 50 states this is actually a failure of his model, at least of his percentage calculations, since there should have been some misses.

Colorado and Virginia both with 80% chance for Obama, 84% chance for Iowa and 50.3% chance for Florida to go Obama. If these percentages actually mean anything the odds are that one of them would have missed. There should have been a 27% chance of getting all of those states right.

If you take all of his probabilities he should have been right 10% of the time on every one of his picks.
Click to expand...
 
It took me until today to realize that this Nate Silver is the Baseball Prospectus Nate Silver. (Okay, it was more of a "being told" than a "realizing.") That's why he's taking the anti-math attacks with such aplomb; he's heard the same thing for years from old-school baseball fans.
 
Last edited:
What's really surprising to me is how close the popular vote is turning out to his prediction. Many pundits were still touting the electoral college/popular vote split last night. Nate wasn't buying it.
 
ANTPogo said:
What's really funny is that I'm seeing right-wingers complain that Silver's model was faulty because it was too accurate, claiming that if his percentages were actually correct he would have missed a few states instead of calling them all correctly.
Click to expand...

Actually, he is also getting a little criticism like that from some statisticians, that his error limits were too conservative.

However, as I pointed out yesterday, based on his percentages, his probability of getting them all right (ignoring Florida) was about 25%. Therefore, the fact that he got them all right (ignoring Florida) is not inconsistent with the outcome.

Florida is an interesting wrinkle. Everyone admitted up front that Florida was basically a toss up, and could go either way. Silver went with the recent polls, which was a risk. It would not have been a mark on his model if he had gotten it wrong (just as it wasn't a big failure for Wang).
 
BenBurch said:
It looks to me like Silver and that fellow from Columbia college are the only ones who understand how to analyze American political polls.
Click to expand...

There's another guy from Irvine that does it, too (Drew something?). I saw his name mentioned at Wang's site.
 
You must log in or register to reply here.

Back
Top Bottom