Saturday, November 3, 2012

It's Not Just Nate Silver Predicting Obama to Win Ohio and the Election

source: NYT 538 Blog

Nate Silver is getting pushback and lots of trash talk for sticking to his prediction that Obama will win the electoral college on Tuesday. Right now the prediction is that Obama has 85% chance of winning the electoral college if the election was held today. Actually, the election IS being held today, thanks to early voting, with thousands of new voters participating in every state. The vote may be slightly disrupted in the Northeast thanks to Hurricane Sandy, but plans are in place for mobile truck polling places in places like New Jersey and New York, which are blue states for Obama anyway. Ohio and Pennsylvania were not as affected by the storm, so any disruptions there are more likely to be overcrowded precincts and shenanigans from their Republican overlords in charge of the election.


And Obama is still set to win Ohio and Pennsylvania based on poll after poll. The only people who seem to doubt that are the pundits who are trying to make this into an "undecided" race when the numbers show something else entirely.

All the quotes from Nate, his detractors and other pundit hackery here:

Snark Amendment: Wagering War on Nate Silver
(Yes, the title is a pun not a misspelling)

There's a good reason for Silver's prediction. Look at the Polls:


All Obama needs is to win Ohio and then Romney can't possibly patch together enough votes to win. Yet media hacks like CNN's Wolf Blitzer, MSNBC's Chuck Todd, and several writers at Politico keep calling the race too close to call. They sound just like the wingnuts at Breitbart and Fox, so where is the journalistic integrity? If they won't report the facts then they are useless, and no better than Dick Morris or Karl Rove.

Particularly despicable is Chris Cillizza of Washington Post who moved Ohio to "Toss-Up" status the other day just because Mitt Romney needs the state to win. No real arithmatic involved, just pandering to the right, or perhaps nervousness about some Republican getting mad on the internet, LOL. Oooo, scary!

Washington Post
The Fix is moving Ohio from “lean Obama” to “tossup” in our presidential ratings amid a slew of polling that suggests that the race has tightened over the past month, even as the incumbent retains the slightest of edges.
. . . After reviewing all of the available public polling data as well as talking to operatives in both parties about the private polls they are privy to, we are convinced that Ohio is a 1-3 point race in President Obama’s favor at the moment.
That — coupled with the state’s electoral history and the absolute necessity for Romney to win the state if he wants to be president — leads us to move it back to the “tossup” category.

In response, numbers guy Sam Wang of Princeton wrote a piece called Perverse media incentive watch: Chris Cillizza
...Cillizza is hardly alone. A few days ago, Wolf Blitzer at CNN cited a single Ohio poll, done by his own organization, showing Obama up by 4%. He then proceeded to call this a "tie," revealing an amazing inability to interpret a simple number. Compounding this is the fact that dozens of polls have been conducted in Ohio. The odds of an Obama lead are extremely high. So why does he persist?
The news media have an incentive to fuzz up the picture: ratings and profit. A message that the cake is fully baked does not automatically bring back the viewers. Without the artificial suspense, Cillizza and Blitzer are put in a position of having to say something substantive or interesting that gets beyond a horserace number. Think how much work that would be.
The same problem extends to the aggregation of polling data, which many sites do (FiveThirtyEight, Oct. 31). But think of all the headlines you have seen about "Romney ahead nationally," "Obama pulls ahead in Wisconsin," "it's a dead heat," and other permutations. Each of these headlines was based on a single poll. But aggregation would lead to fewer news stories - and less of the breathless horserace coverage we are used to.

Today Wang stuck to his guns, writing:

President Obama is peeling away. As you can see from the electoral vote (EV) estimator, he is the candidate with the momentum, not Romney. In terms of EV or the Meta-margin, he's made up just about half the ground he ceded to Romney after Debate #1. And the indicators are still headed straight up.
A few days ago, the word was that Team Romney was buying ads in Minnesota and Pennsylvania. If he wins either of those states I will eat a bug. Ohio...a really big bug. And yes, I will post a photo.
Today I'll address a common concern among the commentariat: will President Obama lose the popular vote? Steve Lombardo is on the case with some Excel curve fitting of a quality that cannot even identify the Debate #1 bounce. Hmmm, someone take his keys away.
Anyway, the short answer: I estimate Romney's chance of winning the popular vote at 6%, odds of 16-1 against.

Here is the Princeton breakdown of states and electoral votes. Looks like Sam Wang won't have to eat a bug.


Another projection by the University of Illinois, Urbana, Election Analytics gives a similar result as Wang and Nate Silver:


Still not convinced? How about four different oddsmakers on


So there it is.

David Rothschild writes on Yahoo's The Signal: All eyes on—where else?—Ohio
Since the final presidential debate, 15 polls have surveyed voter opinion in Ohio, the state that is more likely than any other to determine the election. President Barack Obama leads former Gov. Mitt Romney in 13 of them. The candidates tied in one, and Romney leads in one. Those last two polls were both conducted by Rasmussen, one of the more right-leaning polling institutions, as FiveThirtyEight's Nate Silver has documented.

No one is saying Ohio is a walk for the president. The Huffington Post's Pollster and the RealClearPolitics average both have Obama leading with 51.2 percent among those who express a preference for either major candidate. There is still time for a shift toward Romney, and it's always possible that there is a systematic bias in the polls.

But I don't think it's likely. Historically, polls have been pretty accurate this close to the election. Based only on these surveys, the Signal gives Obama a 75 percent chance of victory in Ohio. When we factor in prediction markets, that figure ticks up a small amount, to 77 percent.

None of these analysts should be vilified for doing simple mathematical algorithms based on dating that other people provide to them. What is much more worrying is the press spinning numbers in a way they know to be DISHONEST just three days before a major election.

No comments:

Post a Comment