All of Nate Silver's State-Level Polling Predictions Proved True

kkleiner writes "For the last few months, the political pundit class has been at war with NYT/FiveThirtyEight blogger Nate Silver. Joe Scarborough of MSNBC called him a "joke," while an op-ed in the LA Times accused him of running a "numbers racket." But last night, Silver triumphed: every one of his state-level presidential predictions proved true. "

Comments

Math

[Anonymous Coward]

http://www.xkcd.org/1131/

Re:Math

[mcgrew]

This topic isn't nearly as wild as the election the year I was born. From USA Today's In '52, huge computer called Univac changed election night:

In a few hours on Nov. 4, 1952, Univac altered politics, changed the world's perception of computers and upended the tech industry's status quo. Along the way, it embarrassed CBS long before Dan Rather could do that all by himself.

Computers were the stuff of science fiction and wide-eyed articles about "electric brains." Few people had actually seen one. Only a handful had been built, among them the first computer, ENIAC, created by J. Presper Eckert and John Mauchly at the University of Pennsylvania in the 1940s.

In summer 1952, a Remington Rand executive approached CBS News chief Sig Mickelson and said the Univac might be able to plot early election-night returns against past voting patterns and spit out a predicted winner. Mickelson and anchor Walter Cronkite thought the claim was a load of baloney but figured it would at least be entertaining to try it on the air.

On election night, the 16,000-pound Univac remained at its home in Philadelphia. In the TV studio, CBS set up a fake computer -- a panel embedded with blinking Christmas lights and a teletype machine. Cronkite sat next to it. Correspondent Charles Collingwood and a camera crew set up in front of the real Univac.

By 8:30 p.m. ET -- long before news organizations of the era knew national election outcomes -- Univac spit out a startling prediction. It said Eisenhower would get 438 electoral votes to Stevenson's 93 -- a landslide victory. Because every poll had said the race would be tight, CBS didn't believe the computer and refused to air the prediction.

Under pressure, Woodbury rejigged the algorithms. Univac then gave Eisenhower 8-to-7 odds over Stevenson. At 9:15 p.m., Cronkite reported that on the air. But Woodbury kept working and found he'd made a mistake. He ran the numbers again and got the original results -- an Eisenhower landslide.

Late that night, as actual results came in, CBS realized Univac had been right. Embarrassed, Collingwood came back on the air and confessed to millions of viewers that Univac had predicted the results hours earlier.

In fact, the official count ended up being 442 electoral votes for Eisenhower and 89 for Stevenson. Univac had been off by less than 1%. It had missed the popular vote results by only 3%. Considering that the Univac had 5,000 vacuum tubes that did 1,000 calculations per second, that's pretty impressive. A musical Hallmark card has more computing power.

That doesn't take away from Silver's math, though, considering that the polls all had Obama and Romney neck and neck and Obama won by a huge margin. It seems Woodbury did a far better job with an incredibly primitive computer than the modern polsters' statisticians did with today's high tech machines.

Re:Math

[Anonymous Coward]

"That doesn't take away from Silver's math, though, considering that the polls all had Obama and Romney neck and neck and Obama won by a huge margin."

That's the thing though, Silver's math was extrapolated directly from the polls themselves. The polls weren't really close; that was just an illusion created by bad interpretation of the data. Media pundits cherry picked the closest polls, fudged margins of error, and made differences of 1% sound very small when in reality they represented hundreds of thousands of votes.

That's the whole point. The election wasn't ever really close at all. The evidence was there, most people just interpreted it badly (or outright dishonestly).

Re:Math

[Dahamma]

That doesn't take away from Silver's math, though, considering that the polls all had Obama and Romney neck and neck and Obama won by a huge margin.

Actually, there wasn't all *that* much math... and in fact (given most of his raw data was just the polls) - the polls that mattered did *not* have them neck and neck. His key insight was just to use polling information by state, find the bias in some polls (like Rasmussen, which had Romney by 2%, hah!) and then weigh and average those polls to get predicted electoral votes. I bet it's simple enough computations Univac could chug through it in a reasonable time :)

It's basically a given now that future presidential race predictions will be based on those same ideas... in fact, the Princeton predictions use a similar model and came up with pretty much the same results:

ELECTORAL PREDICTION (mode): Barack Obama 303 EV, Mitt Romney 235 EV. The mode is the single most frequent value on the EV histogram. It corresponds to the map below, and has a 22% chance of being exactly correct. The next-most-likely outcome is Obama 332, Romney 206 EV.

[and unlike Silver, their blog goes into all of the gory details of their model, which is pretty cool...]

Re:Good for him

[Anonymous Coward]

Another possibility is that the Founding Fathers understood just what kind of dumbshits most of "the people" are, and built in some safeguards to allow civilization to survive the inevitable popular vote to shut it down.

Why Nate?

[MyLongNickName]

Why does Nate get so much attention, when other sites like electionprojection.com and electoral-vote.com do a similar service, are open on their methods and have had almost perfect results for the past two elections. This past election, those two sites only missed on Florida and that one was truly too close to be 90% confident on one way or another.