Nate Silver: Patron Saint of Confirmation Bias
This morning, because the sun rose in the East, Nate Silver again increased his odds of Obama winning reelection. Silver now estimates Obama's chances of reelection at a precise 83.7%.
Now, I realize Obama's improved chances don't actually have anything to do with the Earth's rotation, but rather the result of Silver's "The Model," his own weighted index of political polling. Silver's construction of "The Model", though, produces results showing Obama's chances increasing with such regularity it's almost as predictable as the sun. In fact, it's not so much a model but an electric kool-aid acid test of Silver's bias.
Silver first came to national attention in the 2008. A highly skilled statistician, he, like many people his age, threw himself into politics for the first time that year. Beginning as an anonymous blogger at Daily Kos, he gained notoriety with insightful analysis of the election polling. His star shone bright when he correctly predicted the outcome of the race in 49 of the 50 states (he missed Indiana). It was an impressive record he rode into a prominent spot at The New York Times.
Earlier this year, however, it was reported that Silver was working in close coordination with the Obama polling team throughout the '08 campaign. He was given access to thousands of internal Obama polls. It was unprecedented access to a wealth of information unavailable to other pundits or analysts. It makes his near-perfect call of the campaign somewhat less impressive. It's kind of like a financial analyst nailing a company's earning's report after given private access to that company's full revenue and expense reports.
In the run-up to this year's election, Silver has worked to develop "The Model," a weighted index of all presidential polling which tries to smooth out the variations among polls to develop an "objective" picture of where the race stands. While Silver talks about "The Model" with such talismanic reverence one would think he's a character in a Douglas Adams novel, there is some value in this.
But, setting aside for now how especially meaningful this is in analyzing American politics, there is a foundational problem in Silver's "The Model." Josh Jordan, @NumbersMuncher on Twitter, did a masterful job looking under the hood of Silver's creation a little over a week ago:
The most current Public Policy Polling survey, released Saturday, has Obama up only one point, 49–48. That poll is given a weighting under Silver’s model of .95201. The PPP poll taken last weekend had Obama up five, 51–46. This poll is a week older but has a weighting of 1.15569.
The NBC/Marist Ohio poll conducted twelve days ago has a higher weighting attached to it (1.31395) than eight of the nine polls taken since. The poll from twelve days ago also, coincidentally enough, is Obama’s best recent poll in Ohio, because of a Democratic party-identification advantage of eleven points. By contrast, the Rasmussen poll from eight days later, which has a larger sample size, more recent field dates, but has an even party-identification split between Democrats and Republicans, has a weighting of .88826, lower than any other poll taken in the last nine days.
In other words, the results of "The Model" are dependent on Silver's subjective decisions on how each poll should be "weighted," i.e. how "accurate" Silver believes the poll is. After two decades in politics, I'm shocked that someone would think an almost two-week old poll is a more accurate picture of the race than a current poll from the same pollster. This isn't a model; this is an elaborate mathematical equation designed to generate what Silver "thinks" the outcome ought to be.
This was evident in Silver's predictions for the 2010 elections. While he acknowledged that the GOP was favored to win control of the House, he pegged their chances of picking up more than 60 seats at only 25%. In other words, there was a 75% probability that they would pick up less than 60 seats. They picked up 64.
Another serious problem for "The Model" is that Silver operates from a premise that state polls are, prima facie, more accurate than national polls. It is only in the last decade or so that we've had robust polling at the state and national level, so I'm not really certain we have enough data-points to back up this assumption. Yes, the presidential election is fought state-by-state, but state and national polling tends, over time, tend to move in concert. The reason a state is considered a "swing" state is that it generally matches up with the country as a whole.
This year, however, there is significant divergence between national and state polling. Most state polls, commissioned by media outlets, have samples where the Democrats would match or exceed their turnout advantage in 2008. In many recent national polls, the sample give Democrats less of a turnout advantage. One's assessment of the race essentially comes down to whether you believe turnout will be like 2008 or revert back to the recent norm. Silver clearly believes turnout will be closer to 2008. While this goes against actual early voting data, the assumption still lingers in state polling. So, Silver's assumption that state polls are more accurate dovetails nicely with his preference for an Obama victory.
There is still a necessary discussion of how meaningful even an objective polling model would be in estimating American elections. But, that will have to be another day. It was a great disservice to our understanding of elections when someone decided that politics was a "science." There is a certain hubris inherent in leftists like Silver, believing with determinist fervor that if we simply can get the right mathematical equation and perhaps calculate out another few decimal points, we can predict with 100% accuracy the outcome of an election.
When the history of the 2012 election is written, Silver deserves prominent attention. In the aftermath of Obama's debate debacle, Silver has been the left's oracle, reassuring them that everything is fine. His influence has been such that the Obama campaign didn't make any real course corrections in response to Romney's momentum. When the left wakes up on Wednesday, surveying the electoral wreckage around them, they may regret allowing themselves to be lulled into such a false sense of security.
Silver cut his chops analyzing baseball stats. He has tried to apply that discipline to the messy world of American politics. But, as Dave Weigel with Slate noted to me in reference to Silver, "politics isn't baseball." No, it isn't, and we will be reminded of that on Tuesday.
Follow Mike Flynn on Twitter.
Headline image: Randy Stewart