Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search

hue

(4,949 posts)
Sat Nov 10, 2012, 07:13 AM Nov 2012

Drew Linzer: The stats man who predicted Obama's win

http://www.bbc.co.uk/news/magazine-20246741

Nate Silver of the New York Times explains the science of presidential predictions (see vid)


Pundits insisted the presidential race was a toss-up, but "polling aggregators" - who analyse polls to make predictions - were being criticised for favouring President Obama. Not any more.

In September we called Drew Linzer, an assistant professor of political science at Emory University, to ask for his predictions for the upcoming US presidential election.

Linzer runs the website Votamatic, which uses current election polls and past historical trends to predict the outcome of major elections. He gave the same prediction he had been posting on his site since 23 June.

Obama 332 votes, Romney 206.

Weeks later, the first presidential debate, when Obama's lacklustre performance kicked off a surge of momentum for the Republican challenger Mitt Romney, Obama's election odds had sunk like a stone in national polls, and states once considered toss-ups were being assigned as favourites for Romney.

Asked again for his updated prediction, Linzer gave the same answer.

No change, he said: Obama 332 votes, Romney 206.
5 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies
Drew Linzer: The stats man who predicted Obama's win (Original Post) hue Nov 2012 OP
Electoral college does make elections predictable. caseymoz Nov 2012 #1
He is the real quantitative scientist. Nate Silver is just a follower. Career will tell who is ... JackN415 Nov 2012 #2
Bwahahahha, from the article: Esse Quam Videri Nov 2012 #3
The thing is, that I strongly suspect much of the media cleduc Nov 2012 #5
This election the pollsters won. Baitball Blogger Nov 2012 #4

caseymoz

(5,763 posts)
1. Electoral college does make elections predictable.
Sat Nov 10, 2012, 08:32 AM
Nov 2012

I mean it doesn't matter if Oklahoma goes 70-30 percent red or 51-49. It's still worth only 7 electoral votes. And it's quite possible that the most extreme states are the ones where additional popular votes are won, and the more evenly divided states don't move very much. I mean, in the extreme states, the social pressure to vote with the crowd is stronger.

Really, what were the states that were really in any doubt this time? Not Ohio. In my opinion, Florida, North Carolina, and Virginia. That's it. If Obama had lost the two he won, that would have put him at 290. Still a clear victory.
 

JackN415

(924 posts)
2. He is the real quantitative scientist. Nate Silver is just a follower. Career will tell who is ...
Sat Nov 10, 2012, 09:41 AM
Nov 2012

the true statistical inference scientist. My money is on Linzer.

Esse Quam Videri

(685 posts)
3. Bwahahahha, from the article:
Sat Nov 10, 2012, 10:07 AM
Nov 2012

After the results were in, journalist Dan Lyons wrote: "Nate Silver and his computers may not put Scarborough and his ilk out of business - there's loads of airtime to fill, and windbags are still needed for that. But Silver has exposed those guys for what they are, which is propagandists and entertainers."

One can hope though, can't they?

Thanks so much for posting this great article!

 

cleduc

(653 posts)
5. The thing is, that I strongly suspect much of the media
Sat Nov 10, 2012, 12:14 PM
Nov 2012

already knew Silver and company were right. But

1) A tight race draws more ratings/subscribers resulting in higher ad revenues
2) The billionaires that contributed to Romney also control much of the media we consume

This time around a very special candidate and an exceptionally well run campaign, arguably the best in history, overcame that.

With the amount of lying and flip-flopping Romney was doing and the lack of substance to bolster his policies (ie a core tax plan and budget that wasn't close to adding up to support his claims), this election shouldn't have been close. But these rich old white guys came too close for comfort to buying the presidency of the United States.

The fact that it was as close as it was should be a warning heeded and no stone left unturned to see that it doesn't happen again.

For a democracy to be healthy, the media must serve as the arbiter for the truth - not a clandestine operation to exercise the will of the wealthy. I think we dodged a bullet.

Baitball Blogger

(46,745 posts)
4. This election the pollsters won.
Sat Nov 10, 2012, 12:03 PM
Nov 2012

Do you remember during the Bush era when he was losing the exit polls so they discontinued them?

We all need to prepare for 2016 because the Repubs have run out of tricks. They have tried:

1) Vote caging.
2) Sloppy Felon purgings that take down valid registered voters who have similar names.
3) Voter Suppression by overpolling Republicans to depress the Democratic vote.
4) False Voter Registrations sign-ups that toss out Democrats.
5) Disenfranchising students by convincing them to change their addresses, and then tossing out the registration forms.
6) Unreliable electronic voting machines.

How many millions of Dems did the Republicans disenfranchise and Obama still won.

We need to think of the next big monster that they're going to come up with. Thank God they didn't win, or they probably would have started Armageddon to keep their candidate in office for the total eight years. Yes, they're that crooked.

Latest Discussions»Issue Forums»Editorials & Other Articles»Drew Linzer: The stats ma...