Posted on 10/10/2012 8:12:40 AM PDT by xzins
September 30, 2012
| Republican | Democrat | Other | R - D | Quarterly | |||||||||
| 2012 | |||||||||||||
| Sep | 36.8% | 34.2% | 29.0% | 2.6% | 2.6% | ||||||||
| Aug | 37.6% | 33.3% | 29.2% | 4.3% | |||||||||
| Jul | 34.9% | 34.0% | 31.1% | 0.9% | |||||||||
| Jun | 35.4% | 34.0% | 30.5% | 1.4% | 1.8% | ||||||||
| May | 35.7% | 33.8% | 30.5% | 1.9% | |||||||||
| Apr | 35.1% | 33.1% | 31.8% | 2.0% | |||||||||
| Mar | 36.4% | 33.4% | 30.2% | 3.0% | 3.3% | ||||||||
| Feb | 36.0% | 32.4% | 31.6% | 3.6% | |||||||||
| Jan | 35.9% | 32.5% | 31.6% | 3.4% | |||||||||
I’m late to the game, how do we know Ras is using a D+5 model?
I have yet to have anyone show me a Rasmussen poll where he uses other than his own party affiliation model.
My guess is that he uses his own model.
Several freepers have reverse engineered Rasmussen’s model based on access to detailed, daily numbers. They came up with D+5.
Ras has been slowly increasing the “D” over the past few weeks, which explains how his approval number has slowly moved closer to (and above on some days) 50%.
No one has shown an example of Ras using a D+5. My guess is he uses his own numbers until someone shows me otherwise.
He used his own numbers in 2008 and 2010. I don’t know why he’d do differently now. Especially, since his numbers were the most accurate.
He was also the most consistent in 2008. He had Obama up throughout by about 4-6 points. He turned out to be correct.
Let me work out some logic here.
Lets assume you’re correct and that “affiliation should be based on last general election” is the standard by which Rasmussen determines the sample of his polls. If that’s the case then:
2012 polling should be based on 2008 results -D+6 or D+7 (Obama won by about 53-46).
and
2008 polling should have been based on 2004 results - R+2 ( Bush won by 51-49)
So, that being said
Rasmussen was accurate in 2008 - his polling predicted a 52-46 turnout and that’s within tenths of a point to what it was.
According to that logic, he’s saying:
He polled in 2008 using an R+2 sample
He came up with Obama winning 53-47 (or 52-46)
I am not a Rasmussen subscriber so I cannot go back and check the 2008 internals but I find that outcome - using an R+2 sample returned Obama winning by 4-6 points - very difficult to believe.
There is chicanery going on here. He’s varying his methodology for some reason (unexplained, to my knowledge)
Freepers have reverse-engineered the numbers???
So this is not based on anything that Rasmussen has reported about his own numbers?
I’m much less inclined to trust results by those who don’t have the actual data set numbers and the formula used than I am to trust the guy who collected those numbers and ran them, AND who has a stellar reputation for consistent correctness.
Here you go:
Rasmussen is using a D+5 model, and here’s the math.
In a prior thread, I reverse engineered the Ras breakdown percentages to 34.4%R / 39.3%D / 26.6% I (D+5 gap).
Since there’s some controversy on whether Ras is using 3D or 5D model, I thought I’d show the math. Here’s profit_guy’s internals (thanks, BTW!) as of Sunday:
Confirming these calculations are easy enough by picking a few party breakdown crosstabs and seeing if they match the answer. I picked the following three:
Total Approve (50%) = 0.14R 0.87D 0.42I
Wrong Direction (57%) = 0.89R 0.25D 0.62I
Romney Leaners (49%) = 0.89R 0.10D 0.54I
Here’s the math:
Total Appove = 0.14*0.344 + 0.87*0.393 + 0.42*0.266 = 0.5018 (50%)
Wrong Direction = 0.89*0.344 + 0.25*0.393 + 0.62*0.266 = 0.5693 (57%)
Romney Leaners = 0.89*0.344 + 0.10*0.393 + 0.54*0.266 = 0.4891 (49%)
So, I think my original calculations of Rasmussen using D+5 gap are correct after all. Furthermore, note that Rasmussen is predicting a D turnout equal to or slightly greater than 2008, where exit polls showed that 39% of the voters self-identified as Ds. Take what you will.
73 posted on Tuesday, October 09, 2012 2:39:51 AM by Cruising For Freedom (Don’t be the proof that MSM PsyOps works.)
[ Post Reply | Private Reply | To 35 | View Replies | Report Abuse]
http://www.freerepublic.com/focus/news/2941780/posts?page=73#73
True, but the Obama administration has managed to get voter ID overturned in some states. I don’t know if they can actually cheat enough to win the election, but they can cheat enough to influence polls, that’s what I meant. The Obama administration is putting pressure on pollsters to keep the Democrat numbers inflated.
FYI
Go to Post 27. Also, go to the link at the bottom of that post as it contains a raw data table.
It's nice to know I'm not alone.
However, I would think someone close to the industry lurks here and will step forward to explain.
Perhaps my memory is finally failing me, but I thought I'd read a short interview about a week ago or so with Mr. Rasmussen that 1) he thought the electorate would be about D+2 - D+4 on election day and that 2) he was increasing his own D numbers in his polls because, well, he kept coming up with lots more Dems in his nightly interviews than his model was predicting.
I've googled for a few minutes and been unable to find a reference. When I have time, I'll look some more.
sitetest
Rasmussen does not use that standard. His basic standard is a running poll of 15,000 respondents.
Rasmussen Reports tracks this information based on telephone interviews with approximately 15,000 adults per month since November 2002. The margin of error for the full sample is less than one percentage point, with a 95% level of confidence.http://www.rasmussenreports.com/public_content/archive/mood_of_america_archive/partisan_trends/gop_edge_in_partisan_id_slips_to_2012_low
It’s ridiculous. There’s nothing to indicate that Democrats will turn out in larger numbers than Republicans.
see #32
Thanks. Been wondering when the new numbers would come out.
I am projecting at this point we will see a D+1 sample during the election (because despite this poll there still are technically more Dems than GOP who vote in prez races).....making me extremely confident that unless something big happens, Obama’s going down.
I believe even Ras’ D+3/5 model is wrong.
See #32.
We don’t have Rasmussen’s data set. Without the data set, one can’t say too much about how Rasmussen arrives at his results.
Rasmussen himself says he arrives at Party ID by a sample of 15,000 respondents. Why would we not believe him?
Ras’s old model was R +3.4
His new model is R +2.6
According to Ras, that is. I’ve seen nothing convincing that proves otherwise than what Ras says on his website. Nor can I come up with a good reason for him to publicize these numbers on his website and then do something entirely different.
In September Rasmussen himself said D+2 to D+4 and we know from Cruising For Freedom’s calculations that he IS now using D+5. There is nothing more to debate about this subject. The math and Rasmussen’s own words tell the entire story.
We can’t assume his party affiliation numbers are the numbers he uses to weight his sample by party.
He might, but I’ve heard ad nauseam here that he doesn’t.
Too many assumptions on all sides, I suspect.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.