If 2008 was a win for social 2012 was a win for biggish data (and political numeracy)…

There’s probably more US stories out there than any of us can process, so I’m planning to ‘dump’ judicially. Wired on the big non political winner of this US election, Nate Silver’s rigorous modelling techniques (which perhaps resulted in a great deal less bellicosity in US news rooms):

Data was also the story of how this election was analyzed. Obama won the election. But Nate Silver ofThe New York Times completely reshaped its coverage. Silver steadied the nerves of liberals and rattled the teeth of conservatives, all through a proprietary model of poll aggregation and weighting.

Silver, who called the 2008 election with stunning accuracy, sought to do for politics what sabermetrics did for baseball: Factor out as many subjective judgments as possible, to determine who would win the race. Conservatives noted that Silver’s model consistently favored Obama and smelled a rat, giving rise to the alternative Unskewed Polls (and, inevitably, the sardonic hashtag #unskewedpolls).

Silver’s model is disruptive. It implicitly calls into question the utility of political pundits, and the pundits struck back. MSNBC’s Joe Scarborough and Politico’s Dylan Byers were among the mainstream journalists rolling their eyes at Silver, and others went way further, calling Silver effeminate, as if that refuted his model. (Naturally, the internet provided Is Nate Silver A Witch).

Whatever the outrage against Silver, political quantification is likely here to stay, because, as Zeynep Tufecki wrote for WIRED, it strips much of the superficiality away from political reporting (and helps confront innumeracy, too).

, ,

  • Nate Silver came home a big winner. But his methods and analyses are not, by any means, unique. The Iowa Electronic Markets, out of the Tippie College of Business, have been at it a while. The Pollyvote engine at UPenn follows similar methodologies. All have been ‘proved’ viable — at least for this cycle.

    The NYTimes needs all the credibility it can get — especially up against the Murdochian prejudices of the WSJ, who — lest we forget — imposed Ryan as the Romney pick.

    The historical perspective may be useful. How did the Republican Party of Lincoln, commanding the Union States, go so wrong? Anyone up for a debate on that one?

    As I see it, this time around, the wild card wasn’t the storm on the East Coast Coast — though that already seems to have entered the mythology. It was the women’s votes. As that early-hours comment had it: ‘If you’re a GOP politician with views on rape and abortion, better keep them to yourself, huh?’

    Claire McCaskill surfed tremendous support against Todd ‘Legitimate Rape” Akin. It was women what won it. Check.

    Linda McMahon’s wealth and crassness can’t buy a Senate seat. Check.

    Wisconsin is prepared to elect the first even openly-gay Senator, Tammy Baldwin. Check.

    Elizabeth Warren. Say no more. Check.

    Tammy Duckworth, ditto. Check.

    And Michele Bachmann, 600 votes up (she had an 8% lead and a plurality in 2006!) twisting in the wind and forever damaged goods. Spent $12 million to Jim Graves’s $2m. Ho, ho, ho!

  • Reader

    I was wondering what this was about…

  • Brian

    Thank god Obama has won.

    I waited 90 minutes to vote, the longest I have ever waited.

    Anyway, I was going to to be very angry with Nate Silver if he got our hopes up to see us crushed. But I did very much enjoy his posts and analysis, regardless.

  • Mick Fealty

    I can see this thread is not taking off. I wonder if the point is too obscure for us in a far away country, where we have to subsist between polls for a long time, and where the pollsters themselves are still learning how to adjust for changing circumstances…

    So two very different accounts of Nate Silver’s role in this election:

    First a grumpy one from Daniel Engber on Slate (http://goo.gl/peJZx):

    “…the polls are more important than the poll watcher—good polling yields good predictions. In the future, I’ll be curious to see how Silver’s model does in cases like Montana, where it picks the polling underdog. Does his secret sauce yield some unexpected scores—winners who surprise the pundits and the pollsters—or does it just distract us from the obvious?

    “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.”

    Then a more favourable account of the Silver phenomenon (http://goo.gl/L737w):

    “In the end, Silver gets the last laugh. He correctly picked the winner in all 50 states, many times hitting the exact percentage of votes for each candidate. After proving his predictive statistical model in baseball, he has now refined it for politics. And made a whole lot of people look like fools along the way.”

    Earlier, Dan Rowinski noted the key difference between Silver and his pundit critics:

    “There is no emotion in his model. It is the logical approach to predictive data analysis taken to the nth degree.”

    Nat Silver has cut the fun and future freelance wages of dozens of pundits. But it’s not just him. The Geeks on Fox News had to try and break it to Karl Rove gently last night that he’d let his own emotions cloud his own judgement:

  • Dewi

    Always been a great fan of 538 and to be very fair to Nate he often himself doubts the nuance of some of the methodology….and to be absolutely accurate Nate didn’t quite forecast a Dem win in FLA….he left that one as undecided.