Tornado Alley (PROG)

[sylvester80]

Triumph of the Nerds: Nate Silver Wins in 50 States
http://mashable.com/2012/11/07/nate-silver-wins/
November 7, 2012 by Chris Taylor
31


[url=http://mashable.com/follow/topics/barack-obama]Barack Obama[/url] may have comfortably won re-election in the electoral college, and squeaked a victory in the popular vote. But here is the absolute, undoubted winner of this election: [url=http://mashable.com/follow/topics/nate-silver]Nate Silver[/url] and big data.

The [url=http://fivethirtyeight.com/]Fivethirtyeight.com[/url] analyst, despite being [url=http://mashable.com/2012/11/02/nate-silver-twitter/]pilloried by the pundits[/url], outdid even his 2008 prediction. In that year, his mathematical model correctly called 49 out of 50 states, missing only Indiana (which went to Obama by 0.1%.)

This year, according to all projections, Silver’s model has correctly predicted 50 out of 50 states. A last-minute flip for Florida, which finally went blue in Silver’s prediction on Monday night, helped him to a perfect game.

A caveat: Florida has not yet been called officially, but Obama is in the lead with 98% of precincts reporting. If anything, Silver’s placing of Florida on a knife edge makes him look even more prescient. No wonder one of the night’s more popular tweets suggested that he was actually from the future, working from old newspapers.

What does this victory mean? That mathematical models can no longer be derided by “gut-feeling” pundits. That Silver’s contention — TV pundits are generally no more accurate than a coin toss — must now be given wider credence.

The great thing about a model like Silver’s (and that of similarly winning math nerds, such as Sam Wang of the[url=http://election.princeton.edu/]Princeton Election Consortium[/url]) is that it takes all that myopic human bias out of the equation. The ever-present temptation to cherry-pick polls is subverted.

You set your parameters at the start, deciding how much weight and accuracy you’re going to give to each poll based purely on their historical accuracy. You feed in whatever other conditions you think will matter to the result. Then, you sit back and let the algorithm do the work.

Silver may be a registered Democrat, but he learned back when he was doing baseball analysis that he’d never get anywhere if his models weren’t absolutely neutral, straight down the line between feuding teams.

By 2016, if the networks are paying attention, don’t be surprised to see that the talking heads are all Nate Silver clones. Every media organization will now want its own state poll-based algorithm, especially given [url=http://mashable.com/2012/11/06/nate-silver-new-york-times-traffic/]how much traffic Silver has driven to the New York Times‘ website[/url]. We’ll see more about that kind of model, and less stories about individual polls, which are almost always misleading unless you aggregate them.

Statistics, big data, neutral mathematical models — this, it turns out, is what people want. Who knew?

Well, we geeks knew, but we’re starting to get used to having the rest of the world follow our lead. We had the smartphones first, we read the fantasy books before they became blockbuster movies and TV shows, and now we can boast that we stood shoulder-to-shoulder with Nate Silver’s data before it was popular.

And if you want to see just how accurate Silver’s model was, check this tweet out:

[url=https://twitter.com/cosentino]Michael Cosentino@cosentino[/url]
For the Nate-haters, here’s the 538 prediction and actual results side by side [url=http://t.co/jbny4pRX]pic.twitter.com/jbny4pRX[/url]


[url=https://twitter.com/cosentino/statuses/266042007758200832][/url]
[url=https://twitter.com/cosentino/statuses/266042007758200832]6 Nov 12[/url][url=https://twitter.com/intent/tweet?in_reply_to=266042007758200832]Reply[/url][url=https://twitter.com/intent/retweet?tweet_id=266042007758200832]Retweet[/url][url=https://twitter.com/intent/favorite?tweet_id=266042007758200832]Favorite

[/url]