“Liberty and Justice for ALL!”

Since: Jun 10

Bloomington, MN

#1 Nov 1, 2012
From http://electoral-vote.com/evp2012/Info/rasmus...

---------

Rasmussen and Bias

After the 2010 elections, the New York Times statistics wizard, Nate Silver, analyzed the polls produced by various polling organizations, including Rasmussen Reports, which is the house pollster for Fox News. Silver's analysis covered only polls taken during the final three weeks of the campaign and compared them to the actual election results. For polls taken much earlier, say in June, no one knows what the true sentiment of the electorate was, so there is no way to tell if the polls were accurate or not. Also, any pollster deliberately falsifying the results for partisan advantage would be advised to reduce the bias as the election neared. After all, no one can tell if a June poll is accurate but everyone can tell if a poll released the day before the election is accurate.

Silver analyzed 105 polls released by Rasmussen Reports and its subsidiary, Pulse Opinion Research, for Senate and gubernatorial races in numerous states across the country. The bottom line is that on average, Rasmussen's polls were off by 5.8% with a bias of 3.9% in favor of the Republican candidates.

There is much to criticize about Rasmussen's methods. All polls are conducted within a 4-hour window, the person who answers the phone (even a child) is sampled, phones that are not answered are not called back, and much more. All of Rasmussen's polls are done by computer; live interviewers are never used. However, other firms that do robopolling such as SurveyUSA and PPP get much more accurate results with no bias, so the problem is not the robopolling per se.

Just to look at one methodological issue, if no one answers the phone, Rasmussen picks a different random phone number instead of calling back two, three, four or more times as other pollsters do. Why does this matter? Because 20-somethings (who skew Democratic) are often out, whereas 60-somethings (who skew Republican) are often in. By not being persistent in finally getting through to a randomly chosen phone number, the sample is inherently biased towards Republicans because they are easier to reach. This may not have been intentional but it is understandable if you want to finish your survey in 4 hours. Nevertheless, cutting corners in the name of speed and cost don't improve accuracy.

Unlike companies like Strategic Vision, which most likely made up the data (but not very well) and also Research 2000, which probably did as well, no one is suggesting that Rasmussen is making up numbers without actually doing polling. There are many reports of people called by Rasmussen. The problem with Rasmussen is most likely its model of the electorate. Very briefly, if a pollster believes that in a certain state, say, 40% of the voters are Republicans and the actual survey just happens to turn up 35% Republicans, each Republican interviewed will be given a weight of 40/35 to correct for the undersampling of Republicans. All pollsters do this to correct for under- or oversampling by party, gender, age, race, income, and other factors. This is not only legitimate, but necessary with the small samples all the pollsters use. The issue here is whether Rasmussen's model of the electorate has more Republicans in it than in reality there are (not to mention whether this is accidental or deliberate).

You can read more about Silver's analysis here and here.

The conclusion is that some people do not believe in Rasmussen's polls any more. For these people, we have produced this page, which is generated exactly the same way as the main page and the Senate page, except that first all the Rasmussen polls are temporarily removed from the database. To see if this page is more accurate than the main page and Senate page, please check back on Nov. 7, 2012.
Toidi Slayer

Saint Paul, MN

#2 Nov 1, 2012
Le Jumbo wrote:
From http://electoral-vote.com/evp2012/Info/rasmus...
---------
Rasmussen and Bias
...
Yes, we all know that polls are meaningless unless they agree with the liberal left...
Fred

Saint Paul, MN

#4 Nov 1, 2012
More BS from the resident spamming commie.

"Poll Survey: Rasmussen, Pew Most Accurate in 2008

As the presidential election gets ever closer, new polls come out nearly every day, some suggesting that President Barack Obama is gaining an unassailable lead, others predicting challenger Mitt Romney is inching ahead.

Both sides like to put their spin on the results, however bad they look. Each wants to take comfort from a little piece of data hidden inside.

But how does the average voter find out which poll he or she should you believe and which polls are there merely as a distraction?

Costas Panagopoulos of Fordham University, surveying 23 polling organizations, prepared a list showing which organizations were most accurate in their final poll before the 2008 election.

Two — Rasmussen Reports and the Pew Research Center — got the result dead right, Panagopoulos says. Of the other 21, 17 over-estimated support for Barack Obama, while just four said John McCain would receive a larger percentage of the vote than he actually did.

The big media organizations almost universally failed to give readers a final accurate prediction, with Newsweek coming in dead last, just behind polls for CBS/New York Times; Reuters/C-Span/Zogby and Gallup.

Polls carried out for Fox, NBC, ABC, the Washington Post, and Wall Street Journal were also all in the bottom half of Panagopoulos’ study."
nuff said

Chicago, IL

#5 Nov 1, 2012
Interesting ... how about PPP, Politco, etc., etc.

I suppose no bias on others? I think that would be unlikely!
Numeros

Sacramento, CA

#7 Nov 1, 2012
Fred wrote:
More BS from the resident spamming commie.
"Poll Survey: Rasmussen, Pew Most Accurate in 2008
As the presidential election gets ever closer, new polls come out nearly every day, some suggesting that President Barack Obama is gaining an unassailable lead, others predicting challenger Mitt Romney is inching ahead.
Both sides like to put their spin on the results, however bad they look. Each wants to take comfort from a little piece of data hidden inside.
But how does the average voter find out which poll he or she should you believe and which polls are there merely as a distraction?
Costas Panagopoulos of Fordham University, surveying 23 polling organizations, prepared a list showing which organizations were most accurate in their final poll before the 2008 election.
Two — Rasmussen Reports and the Pew Research Center — got the result dead right, Panagopoulos says. Of the other 21, 17 over-estimated support for Barack Obama, while just four said John McCain would receive a larger percentage of the vote than he actually did.
The big media organizations almost universally failed to give readers a final accurate prediction, with Newsweek coming in dead last, just behind polls for CBS/New York Times; Reuters/C-Span/Zogby and Gallup.
Polls carried out for Fox, NBC, ABC, the Washington Post, and Wall Street Journal were also all in the bottom half of Panagopoulos’ study."
You're referring to the outdated, invalid Fordham "Initial Report." It was compiled in the hours following the 2008 election, long before all ballots had been counted. http://www.fordham.edu/images/academics/gradu...

Calculations in this Initial Report were done using an ESTIMATE of a 6.15 Obama winning margin. However, when all the votes were tallied, Obama ACTUALLY won by a 7.2 margin.

Fordham later released a complete analysis based on the official popular vote outcome. Rasmussen and Pew no longer topped the list; eight pollsters were more accurate.

The final Fordham report: http://www.fordham.edu/images/academics/gradu...
Fred

Saint Paul, MN

#8 Nov 1, 2012
Which Presidential Polls are the Most Accurate and What are they Saying? UPDATE 10-23-2012
September 18, 2012
By editor

On a day when the national media is touting a rise in the national polls by President Obama the City County Observer decided to take some initiative and examine the past results of the polls that are being cited by the media. The best website to go to for examining the widest range of polls is a site called www.realclearpolitics.com . This site publishes daily and average of the last months polls from nine different polls. Today’s average of the nine included polls has President Obama trailing Mitt Romney by 0.7% nationally down from leading by 4.5% when this article originated. The polls used and their current results are as follows:

CBS News: Obama +2
Rasmussen Tracking: Romney +4
Gallup Tracking: Romney +5
IBD: Obama +2
Monmouth: Romney +3
Politico: Politico +2
ABC: Obama +1
Washington Times Obama +3
NBC tie

It is obvious that these polls are all over the map with some polls citing registered voters and others citing likely voters. Each poll also has a formula that they use to sample a given population. Historically speaking two of these polls have a solid track record for predicting presidential races to within less than 1% of the vote. These two polls are Rasmussen Tracking and Gallup Tracking (when shifted to likely voters)both of which report results of the trailing week as opposed to the flavor of the day. Their algorithms for sampling are slightly different yet both converge well.

For the 2008 election in which Barack Obama defeated John McCain by a 52.9% to 45.6% margin Rasmussen predicted an Obama victory by 52% to 46% while Gallup predicted an Obama victory of 53% to 42%. An average of those polls would have predicted a result of Obama 52.5%(0.75% error to the low side) to McCain 44%(7.8% error to the low side).
Numeros

Sacramento, CA

#10 Nov 1, 2012
Fred wrote:
Historically speaking two of these polls have a solid track record for predicting presidential races to within less than 1% of the vote. These two polls are Rasmussen Tracking and Gallup Tracking (when shifted to likely voters)both of which report results of the trailing week as opposed to the flavor of the day. Their algorithms for sampling are slightly different yet both converge well.
For the 2008 election in which Barack Obama defeated John McCain by a 52.9% to 45.6% margin Rasmussen predicted an Obama victory by 52% to 46% while Gallup predicted an Obama victory of 53% to 42%. An average of those polls would have predicted a result of Obama 52.5%(0.75% error to the low side) to McCain 44%(7.8% error to the low side).
OK, Obama won by 52.9% to 45.6%.

Now let me get this straight.
You take Rasmussen (who was off by by 1.3%)
You take Gallup (which was off by 3.7%)
You average them.(Gallup actually had Obama 55% to 44%, not 53% to 42%)
That gives you Obama 53.5% to 45%(which is still by 1.2%)

Now what was the point of all that?

CNN & Ipsos were still more accurate with Obama 53% to 46%. Even without playing an averaging game, they were only off by 0.3%

Since: Apr 12

Farmington, MN

#11 Nov 1, 2012
Numeros wrote:
<quoted text>
OK, Obama won by 52.9% to 45.6%.
Now let me get this straight.
You take Rasmussen (who was off by by 1.3%)
You take Gallup (which was off by 3.7%)
You average them.(Gallup actually had Obama 55% to 44%, not 53% to 42%)
That gives you Obama 53.5% to 45%(which is still by 1.2%)
Now what was the point of all that?
CNN & Ipsos were still more accurate with Obama 53% to 46%. Even without playing an averaging game, they were only off by 0.3%
http://www.politisite.com/2012/10/01/analysis...
Formulas
Every final poll showed Obama with a lead, so assessing their accuracy is just a matter of comparing their forecasted spread with the actual spread of the election which was Obama +6.5.

Final poll accuracy score = 100 –(|(POLL SPREAD – 6.5)|/ 6.5 )

All the pollsters graded had more than one poll during the month of October. If a poll reported a wide spread and then suddenly narrowed down right before the election, this formula produces a lower score. Likewise a pollster gets a lower score if they predicted a very tight race until the end and then widened up.
Amused Slew

Seattle, WA

#12 Nov 1, 2012
Poor trolls, buy Corvairs, YOU'LL never get to the polls....
Numeros

Sacramento, CA

#13 Nov 1, 2012
Trolls wrote:
<quoted text>
http://www.politisite.com/2012/10/01/analysis...
Formulas
Every final poll showed Obama with a lead, so assessing their accuracy is just a matter of comparing their forecasted spread with the actual spread of the election which was Obama +6.5.
Final poll accuracy score = 100 –(|(POLL SPREAD – 6.5)|/ 6.5 )
All the pollsters graded had more than one poll during the month of October. If a poll reported a wide spread and then suddenly narrowed down right before the election, this formula produces a lower score. Likewise a pollster gets a lower score if they predicted a very tight race until the end and then widened up.
First, see page 5 of the FEC report for the official 2008 popular vote oucome. http://www.fec.gov/pubrec/fe2008/federalelect...

Notice that this Report card was compiled in early November, 2008, before all ballots had been counted.

Notice that the Report Card's calculations are based on a spread of only 6.5. Obama's spread was actually 7.2.

Notice that it's based on Obama winning 52.6% to 46.1%. Obama actually won 52.9% to 45.7%.

Notice that it says Rasmussen was off by 0.5. He was actually off by a full 1.2.

Notice that it says CNN & Ipsos were off by 0.5. They were actually off by only 0.2.

CNN & Ipsos were more accurate than Rasmussen. This Report Card is outdated and invalid.
Unfit Mitt

Saint Paul, MN

#14 Nov 2, 2012
Fred wrote:
More BS from the resident spamming commie.
"Poll Survey: Rasmussen, Pew Most Accurate in 2008

meaningless garbage snipped
Your article refers to ONE SINGLE poll - the final presidential poll in 2008.

On the individual state polls in 2008 and 2010, Rasmussen was among the LEAST accurate pollsters, demostrating a 4 to 5 point average Republican bias.

Since: Apr 12

Farmington, MN

#15 Nov 2, 2012
Numeros wrote:
<quoted text>
First, see page 5 of the FEC report for the official 2008 popular vote oucome. http://www.fec.gov/pubrec/fe2008/federalelect...
Notice that this Report card was compiled in early November, 2008, before all ballots had been counted.
Notice that the Report Card's calculations are based on a spread of only 6.5. Obama's spread was actually 7.2.
Notice that it's based on Obama winning 52.6% to 46.1%. Obama actually won 52.9% to 45.7%.
Notice that it says Rasmussen was off by 0.5. He was actually off by a full 1.2.
Notice that it says CNN & Ipsos were off by 0.5. They were actually off by only 0.2.
CNN & Ipsos were more accurate than Rasmussen. This Report Card is outdated and invalid.
Your "math" doesn't account for pollsters "cooking the books", or having big spreads leading up to the election, then, in their final poll, they show the "real" spread. You are not accounting for consistency.
Fred

Saint Paul, MN

#16 Nov 2, 2012
Numeros wrote:
<quoted text>
OK, Obama won by 52.9% to 45.6%.
Now let me get this straight.
You take Rasmussen (who was off by by 1.3%)
You take Gallup (which was off by 3.7%)
You average them.(Gallup actually had Obama 55% to 44%, not 53% to 42%)
That gives you Obama 53.5% to 45%(which is still by 1.2%)
Now what was the point of all that?
CNN & Ipsos were still more accurate with Obama 53% to 46%. Even without playing an averaging game, they were only off by 0.3%
"Now what was the point of all that?"

As 'Trolls' points out, consistency is a rating factor. Polls that try to influence voter interest with inaccurate polls, only to present their final poll as their most accurate one, rate poorly here.

Poll Score Grade Accuracy Consistency
Rasmussen Reports 91% A- 92% 86%
Ipsos/McClatchy 89% B+ 92% 79%
CNN/Opinion Research 88% B+ 92% 77%
Fox News 84% B 92% 61%
Pew 83% B- 92% 56%
GWU/Battleground 79% C+ 92% 41%
Diageo/Hotline 77% C+ 77% 79%
NBCNews/Wall St.Journal 76% C 77% 75%
Gallup Traditional 73% C- 77% 63%
Marist 67% D+ 62% 82%
ABC News / Wash Post 67% D+ 62% 82%
IBD/TIPP 66% D 77% 34%
Gallup Expanded 66% D 62% 78%
CBS News / NYT 60% D- 62% 56%
Reuters/C-SPAN/Zogby 35% F 31% 48%
Numeros

Sacramento, CA

#17 Nov 2, 2012
Fred wrote:
<quoted text>"Now what was the point of all that?"
As 'Trolls' points out, consistency is a rating factor. Polls that try to influence voter interest with inaccurate polls, only to present their final poll as their most accurate one, rate poorly here.
Poll Score Grade Accuracy Consistency
Rasmussen Reports 91% A- 92% 86%
Ipsos/McClatchy 89% B+ 92% 79%
CNN/Opinion Research 88% B+ 92% 77%
Fox News 84% B 92% 61%
Pew 83% B- 92% 56%
GWU/Battleground 79% C+ 92% 41%
Diageo/Hotline 77% C+ 77% 79%
NBCNews/Wall St.Journal 76% C 77% 75%
Gallup Traditional 73% C- 77% 63%
Marist 67% D+ 62% 82%
ABC News / Wash Post 67% D+ 62% 82%
IBD/TIPP 66% D 77% 34%
Gallup Expanded 66% D 62% 78%
CBS News / NYT 60% D- 62% 56%
Reuters/C-SPAN/Zogby 35% F 31% 48%
That "Report Card" weights consistency 25%, accuracy is 75%. Rasmussen blew it on the main factor...accuracy.
Unfit Mitt

Minneapolis, MN

#18 Nov 2, 2012
Fred wrote:
<quoted text>"Now what was the point of all that?"
As 'Trolls' points out, consistency is a rating factor. Polls that try to influence voter interest with inaccurate polls, only to present their final poll as their most accurate one, rate poorly here.
Poll Score Grade Accuracy Consistency
Rasmussen Reports 91% A- 92% 86%
Ipsos/McClatchy 89% B+ 92% 79%
CNN/Opinion Research 88% B+ 92% 77%
Fox News 84% B 92% 61%
Pew 83% B- 92% 56%
GWU/Battleground 79% C+ 92% 41%
Diageo/Hotline 77% C+ 77% 79%
NBCNews/Wall St.Journal 76% C 77% 75%
Gallup Traditional 73% C- 77% 63%
Marist 67% D+ 62% 82%
ABC News / Wash Post 67% D+ 62% 82%
IBD/TIPP 66% D 77% 34%
Gallup Expanded 66% D 62% 78%
CBS News / NYT 60% D- 62% 56%
Reuters/C-SPAN/Zogby 35% F 31% 48%
I don't know what biased source you got this from, but in the 2008 and 2010 polls by state (NOT the final US presidential poll, but the hundreds of state polls, Rasmussen rated poorly and showed a 4 to 5 point average Republican bias.

I'll show you the same thing next week.
Unfit Mitt

Minneapolis, MN

#20 Nov 2, 2012
Even Rasmussen no longer has Romney in the lead!
Unfit Mitt

Minneapolis, MN

#21 Nov 3, 2012
Today's Rasmussen shows Obama and Romney tied - which is really a 4 point Obama lead!
Bob Schmahl

Saint Paul, MN

#22 Dec 3, 2012
Fred wrote:
More BS from the resident spamming commie.
"Poll Survey: Rasmussen, Pew Most Accurate in 2008
As the presidential election gets ever closer, new polls come out nearly every day, some suggesting that President Barack Obama is gaining an unassailable lead, others predicting challenger Mitt Romney is inching ahead.
Both sides like to put their spin on the results, however bad they look. Each wants to take comfort from a little piece of data hidden inside.
But how does the average voter find out which poll he or she should you believe and which polls are there merely as a distraction?
Costas Panagopoulos of Fordham University, surveying 23 polling organizations, prepared a list showing which organizations were most accurate in their final poll before the 2008 election.
Two — Rasmussen Reports and the Pew Research Center — got the result dead right, Panagopoulos says. Of the other 21, 17 over-estimated support for Barack Obama, while just four said John McCain would receive a larger percentage of the vote than he actually did.
The big media organizations almost universally failed to give readers a final accurate prediction, with Newsweek coming in dead last, just behind polls for CBS/New York Times; Reuters/C-Span/Zogby and Gallup.
Polls carried out for Fox, NBC, ABC, the Washington Post, and Wall Street Journal were also all in the bottom half of Panagopoulos’ study."
Hey, Fred, how did that Rasmussen poll thing work out for you?

Tell me when this thread is updated:

Subscribe Now Add to my Tracker

Add your comments below

Characters left: 4000

Please note by submitting this form you acknowledge that you have read the Terms of Service and the comment you are posting is in compliance with such terms. Be polite. Inappropriate posts may be removed by the moderator. Send us your feedback.

Minneapolis Discussions

Title Updated Last By Comments
Can't manage the gov & NOT honest or trustworthy (Nov '13) 2 hr LIbEralS 298
Global warming 'undeniable,' scientists say (Jul '10) 2 hr Mothra 33,750
Deflated Balls 20 hr Space ace 6
Obama state of the b#llsh!t 20 hr Space ace 30
Obama Threatens The Jews 20 hr Space ace 3
Obama's Muslim Friends Behead a Jap 21 hr Kuna kintay 1
Police: New Hope Liquor Store Employee Shot Dur... 22 hr Christsharia Law 2
Minneapolis Dating
Find my Match
More from around the web

Minneapolis People Search

Addresses and phone numbers for FREE

Personal Finance

Mortgages [ See current mortgage rates ]

NFL Latest News

Updated 1:22 pm PST

ESPN 1:22PM
Matthews fined $22K for block on QB Wilson
Yahoo! Sports 1:24 PM
What trick will Belichick pull from his hoodie sleeve next?
Bleacher Report 6:54 PM
Why Vikings Must Draft CB Quinten Rollins
Bleacher Report 5:47 AM
Dez Must Top Vikings' FA Wish List
NBC Sports 6:14 AM
Michael Bidwill on Larry Fitzgerald: We'll get this worked out