Rassmussen vs Nate Silver

[Farang]

Originally Posted by jpeyton

We already knew Rasmussen had a Republican lean for years. Advanced models like 538's had that accounted for (as well as the Democratic lean of other pollsters).

The point being that Rasmussen can still provide useful data for a model, as long as they are consistent in their bias. And to that extent, I think they are. It's just unfortunate for some right-wingers that they took Rasmussen's data at face value instead of properly running it through a model.

No, I'm saying it looks deliberate because the inaccuracies are inconsistent but just happen to end up giving Romney a tie/+1 result. So it looks like he started with the correct number, and then adjusted to give a tie/+1.

That as opposed to seeing him wrong R+2 everywhere.

[dullard]

Originally Posted by buckshot24

I don't think I need to produce any evidence at this point. If you're interested you can search on google rasmussen party affiliation poll and it should bee first result. Rasmussen had it +5.8 Republican which couldn't have been more wrong.

Buckshot24, I'll give you an honest answer without name calling. Shame on the other posters for resorting to such low depths.

Rasmussen came to fame in 2000 by just blindly assuming that democrats and republicans are equally weighted in the US. Rasmussen got the numbers right that year but for the wrong reason. He completely blew his 2004 results with a similar assumption. There flat out are far more Democrats than Republicans in the US. Far more. But Democrats historically don't vote for various reasons. 2000 was close not because there were so many Republicans, but because there were so few voting Democrats.

Rasmussen got better. He now tracks party ID and uses it in his polls. But party ID isn't enough. You also need to know enthusiasm. Will the Democrats vote? Republican enhusiam is nearly meaningless-they vote regardless. It is Democrat enthusiasm that matters. In 2008 there were many first time Democrat voters. Obama won easily. In 2010 there was no democrat enthusiasm, the young the poor the minorities don't vote in midterms.

The big failure was in misinterpretting their lack of midterm votes as a swing to the right. Rasmussen assumes that not voting in the midterms means they won't vote in 2012. So he ignored them. That was his mistake. That is why his party ID was off by so much. He needs to incorporate the fickle Democrats into his system.

[AstroManLuca]

What I read was that Rasmussen adjusts for party identification in his poll results, but the problem is that in recent years there have been a lot of Republicans who self-identify as "independents" because they are Tea Partiers or something. So he sees that the number of Republicans is lower than he expects, adjusts their numbers upward, and voila! Republican bias.

[HomerJS]

Originally Posted by AstroManLuca

What I read was that Rasmussen adjusts for party identification in his poll results, but the problem is that in recent years there have been a lot of Republicans who self-identify as "independents" because they are Tea Partiers or something. So he sees that the number of Republicans is lower than he expects, adjusts their numbers upward, and voila! Republican bias.

In other words, Rassmussen got it wrong

[Atomic Playboy]

Originally Posted by buckshot24

If we want to be picky. If Silver "predicts" 50 out of 50 states this is actually a failure of his model, at least of his percentage calculations, since there should have been some misses.

His method is a failure because it was too accurate? That's the best one yet.

[dullard]

Originally Posted by AstroManLuca

What I read was that Rasmussen adjusts for party identification in his poll results, but the problem is that in recent years there have been a lot of Republicans who self-identify as "independents" because they are Tea Partiers or something. So he sees that the number of Republicans is lower than he expects, adjusts their numbers upward, and voila! Republican bias.

I don't think that is quite correct. Rasmussen assumed 27.5% independents and exit polls had 29% independents. He was quite close there. It was his 33.3% democrats that was off the mark. Exit polls had 38% democrats voting.

[Charles Kozierok]

Those of you willing to give Rasmussen benefit of the doubt for his behavior this cycle are bigger men/women than me. I think he knew very well that he was far too right-leaning. He knows which side of his bread is buttered.

[First]

Originally Posted by CharlesKozierok

You're rewriting history.

You took the only two polls that showed you what you wanted to be true and repeatedly defended them against arguments from others that showed them to be outliers.

And by the way, what Silver does is a lot more complex and intelligent than just averaging polls together.

Originally Posted by buckshot24

I never ever argued that they were right and the others were wrong all I ever did is ask why you and others thought the two party ID polls were so wrong (when they had been fairly accurate up until last night). Now we know that they were full of shit. There was conflicting data which has since been resolved.

Really?

Originally Posted by buckshot24 in another thread

Please find a post where I said all of the other polls were wrong, thanks.

Originally Posted by buckshot24 earlier in the week

To be frank I don't think any of the polls are correct.

Amazing. You are literally too dumb to function.

[Todd33]

"For all the ridicule directed towards pre-election polling, the final poll estimates were not far off from the actual nationwide vote shares for the two candidates," said Dr. Panagopoulos.
On average, pre-election polls from 28 public polling organizations projected a Democratic advantage of 1.07 percentage points on Election Day, which is only about 0.63 percentage points away from the current estimate of a 1.7-point Obama margin in the national popular vote. [...]

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

LOL, wow, the outliers everyone knew about didn't do so well.

[Schmide]

Even the Trendy Dressing Dean Chambers the poster boy for lying polls (unskewedpolls), admits he was wrong.

Nate Silver was right, and I was wrong

[Phokus]

Originally Posted by Schmide

Even the Trendy Dressing Dean Chambers the poster boy for lying polls (unskewedpolls), admits he was wrong.

LMAO

And now he's calling out Rassmussen, hahahaha, i'm enjoying this GOP circular firing squad

[Charles Kozierok]

Chambers only admitted he was wrong after changing his map at the last second to show a near-tie. Hardly a model of honesty.

[SP33Demon]

Originally Posted by buckshot24

First of all FUCK YOU.

Secondly, Silver is BRILLIANT. That doesn't make him a wizard at predictions. Furthermore his results were too good for the percentages he gave each race he's written about this in his blog and he'll more than likely bring it up in an upcoming post.

Thirdly, a model could have been constructed using just polling aggregates that made the same predictions. Case in point.

First off, cursing is the retort of a mental midget. Grats!

Second, all of his results were within the margin of error and had a very good chance to play out in simulations. Saying his results were "too good" is ridiculous, did you spout such drivel in the last election when he went 49/50? lmao

Third, RCP didn't predict FL corrrectly, nor as a toss up state, but nice try. Nate > *

[Farang]

kudos to Silver for not gloating today.. but he deserves to. I think next cycle his model will be the definitive source on the status of the race, replacing RCP