538

[whoman69]

The latest 538 simulations have Obama winning 90.9% of the time with an average of 313.0 EC. The popular vote is seen as 50.8-48.3 or a 2.5 point lead for Obama.

The closest state contests are:
Florida 50.3% Obama
North Carolina 74.4% Romney
Virginia 79.4% Obama
Colorado 79.7% Obama
Iowa 84.3% Obama
New Hampshire 84.6% Obama

The following battleground states are now considered safe Obama meaning more than a 90% probability:
Michigan
Pennsylvania
Wisconsin
Nevada
Ohio

Obama has 303 EC at least 79%
Obama has 332 EC at least 50%

[FD]

Originally Posted by patteeu

Do you think Rasmussen and Gallup use math or is math just a 538 thing?

Rasmussen weights their results by an outcome variable, party ID, based on what they think it should be. This seems unnecessary but depending on how they get the party ID number isn't necessarily methodologically unsound. They've been pretty wrong in this election, however. There may be other things they do I'm unaware of that contributed to that.

Gallup seems to have done alright.

538 skeptics, not so much, thanks to poor understanding of statistics.

[dirk digler]

Oh and looks like hooker lover Dick Morris finally grows a brain. Honestly he should never be given any chance to spew his BS again.

Fox News contributor Dick Morris said on Wednesday that his prediction that GOP presidential nominee Mitt Romney would beat President Barack Obama was wrong because his election models were not reflective of “the new America.”

“I think that the reason the prediction I made was wrong is that I was criticizing the polling because I said it reflected the same turnout model as there was in 2008. And I said that I thought that was a one-off affair and that it would not continue and it would not be the permanent turnout model for the United States,” Morris said on Fox News.

He added: “What this is saying is this is the new America. This isn’t your father’s America.”

Morris, a former adviser to President Bill Clinton, had predicted a Romney landslide.

Morris said that unless the GOP-ers can appeal to some of the key Democratic constituencies, they won’t be able to win again.

“The percentage of single women, minorities and voters under 30 is so large at this point that unless the Republican Party fundamentally changes its appeal to those voters, it can never win an election,” Morris said.

He continued: “If this candidate in this economy against this opponent can’t win an election with this electorate — nobody ever can. And what the Republican Party needs to do is to stop running in the face of those demographics, and start appealing to them and start revising some of its priorities and its positions in order to reach that vote because that vote is here to stay.”

Read more: http://www.politico.com/news/stories...#ixzz2BYFCt0DG

[Pitt Gorilla]

Originally Posted by patteeu

Yeah, Nate Silver dominated. And those that had blind faith in him (even if they told themselves that their blind faith was an allegiance to math) picked the right horse.

what I don't understand is why someone like you was so sure silver was wrong. There was very little credible evidence to suggest otherwise.

[patteeu]

Originally Posted by dirk digler

He didn't have any relationship that I know of with the Obama campaign after 2008.

I and others like NS have been saying for a while that Ras has a noticeable party lean and are even biased. He even called them biased after the 2010 mid terms.

You can read that here. http://fivethirtyeight.blogs.nytimes...rmed-strongly/

He's calling Rasmussen cheap, not partisan.

[patteeu]

Originally Posted by Pitt Gorilla

what I don't understand is why someone like you was so sure silver was wrong. There was very little credible evidence to suggest otherwise.

My proprietary model is going to have to be adjusted. I guess I couldn't believe that Obama remained so popular after such a dismal four years. There were a lot of smart people who were skeptical of the state polls and they sounded more convincing to me than Nate Silver supporters did. Silver's track record was too short for me to look past his supporters and just trust his wisdom and modeling ability.

[KC native]

Originally Posted by patteeu

I've never doubted his math. I questioned whether he was making the right assumptions and using the right inputs.

People like Rasmussen and the guys at Gallup use a lot of math too. That's why the people cheering a victory for math here, like dirk for example, look so stupid.

Color me not surprised you still don't understand Silver's model.

[patteeu]

Originally Posted by KC native

Color me not surprised you still don't understand Silver's model.

I'm not surprised you don't either. In fact, I'd be shocked if anyone does since it's not fully public. I'm sure that people like FD, cdcox and Pitt Gorilla have the ability to understand it. It would probably take a bit more effort for most of the rest of us.

[alnorth]

Originally Posted by patteeu

He's calling Rasmussen cheap, not partisan.

I agree with this. While Rasmussen has a partisan bias, I'm not cynical enough (yet) to think he intended it to sell his polling service to conservatives. I think he wants to be right, but he also wants to be cheap to earn a profit, and it burned him badly.

He's got enough of a track record to not just outright die, but he's got to do better in the next midterms, and to do that, he needs to call cell phones, and revisit his use of party weighting.

[Pitt Gorilla]

Originally Posted by patteeu

My proprietary model is going to have to be adjusted. I guess I couldn't believe that Obama remained so popular after such a dismal four years. There were a lot of smart people who were skeptical of the state polls and they sounded more convincing to me than Nate Silver supporters did. Silver's track record was too short for me to look past his supporters and just trust his wisdom and modeling ability.

That's what I find surprising. The state poll skeptics never made a convincing argument.

[alnorth]

Originally Posted by patteeu

I'm not surprised you don't either. In fact, I'd be shocked if anyone does since it's not fully public. I'm sure that people like FD, cdcox and Pitt Gorilla have the ability to understand it. It would probably take a bit more effort for most of the rest of us.

He doesn't need to release it into the public domain for us to understand, basically, what he's doing. He's explained why he weights some pollsters more than others without explaining why the weight for this poll is 1.2867 and not 1.3921. He's explained which economic factors go into the model early on and how its influence tapers off to zero by election day without giving us a formula.

We don't need the fine print. His approach is logical and he had a track record both in 2008 and 2010.

[patteeu]

Originally Posted by alnorth

He doesn't need to release it into the public domain for us to understand, basically, what he's doing. He's explained why he weights some pollsters more than others without explaining why the weight for this poll is 1.2867 and not 1.3921. He's explained which economic factors go into the model early on and how its influence tapers off to zero by election day without giving us a formula.

We don't need the fine print. His approach is logical and he had a track record both in 2008 and 2010.

Like I said, his track record was (impressive, but) short.

[KC native]

Originally Posted by patteeu

Like I said, his track record was (impressive, but) short.

Trollface.jpg

[dirk digler]

heh

Hearing from little bird that President’s pollsters final battleground polling was 1/10th of one percentage point off from the final aggregated battleground results.

So there’s a pollster in Obamaland with a Duracell battery on his shoulder, daring Nate Silver to knock it off …

[dirk digler]

PPP #1 again (I think Ringleader said they wouldn't be even close ). LOL at Rasmussen...loser

http://politicalwire.com/archives/20...ate_polls.html

November 07, 2012

The Most Accurate Polls

A Fordham University study ranked 28 polling firms on how their pre-election national surveys compared to the results on Election Day. The ranking:

1. PPP (D)
1. Daily Kos/SEIU/PPP
3. YouGov
4. Ipsos/Reuters
5. Purple Strategies
6. NBC/WSJ
6. CBS/NYT
6. YouGov/Economist
9. UPI/CVOTER
10. IBD/TIPP
11. Angus-Reid
12. ABC/WP
13. Pew Research
13. Hartford Courant/UConn
15. CNN/ORC
15. Monmouth/SurveyUSA
15. Politico/GWU/Battleground
15. FOX News
15. Washington Times/JZ Analytics
15. Newsmax/JZ Analytics
15. American Research Group
15. Gravis Marketing
23. Democracy Corps (D)
24. Rasmussen
24. Gallup
26. NPR
27. National Journal
28. AP/GfK

[KC native]

Oh yea I almost forgot about ringleader's bullshit simplistic model.