• This is a political forum that is non-biased/non-partisan and treats every persons position on topics equally. This debate forum is not aligned to any political party. In today's politics, many ideas are split between and even within all the political parties. Often we find ourselves agreeing on one platform but some topics break our mold. We are here to discuss them in a civil political debate. If this is your first visit to our political forums, be sure to check out the RULES. Registering for debate politics is necessary before posting. Register today to participate - it's free!

Rasmussen Exposed

haymarket

DP Veteran
Joined
Sep 3, 2010
Messages
120,951
Reaction score
28,520
Gender
Undisclosed
Political Leaning
Undisclosed
this subject came up in another thread and I thought it deserved its own slot. This is an article that came out today on what was suspected for the last few months - the public opinion polls of Rasmussen are biased in favor of Repubican candidates. Here is the information


Rasmussen Being Rasmussen: The Evidence Is In
by Steve Singiser

Wed Nov 03, 2010 at 03:58:05 PM PDT

Now that the confetti has been swept up, and tears (of joy or anguish) have largely been dabbed dry, time for a little dispassionate analysis. As the resident poll guy here, I have been fairly steadfast in my criticism of Rasmussen Reports, as have several of my colleagues.

Given that Daily Kos partners with among the most accurate pollsters in the game (Public Policy Polling), it has always irked me to no end that the political media has always referenced any PPP poll as a "Democratic poll" (despite actually having a slight GOP house effect during this cycle). Meanwhile, Rasmussen (whose rooting interest, at this point, seems beyond discussion) is never categorized similarly. Indeed, one of the "serious journalists" actually described Rasmussen as "a pollster that liberals claim leans to the right."

Well, now we have results. And here is the evidence:

RASMUSSEN IS BIASED: Rasmussen polled over 75 races from the middle of October until Election Day. Let's narrow that down to their most recent polls in each race (since, after all, they polled some races multiple times). So, looking at unique races, we get down to 57 contests. The House of Ras overestimated the margins in the race to the advantage of the GOP in 46 out of those 57 contests (81%). In an ideal world, of course, a pollster would get their numbers wrong pretty evenly. For example, with our pollster (PPP), their numbers wound up overstating the Democratic performance 17 out of 32 times during the same time period, and the GOP 14 out of 32 times (they hit IL-Sen right down to the tenth of a point). It cannot be attributed to mere coincidence that Rasmussen's polling overstated Republican performance over three-fourths of the time.
RASMUSSEN IS NOT TERRIBLY ACCURATE: While PPP's polling had a few misses (as all pollsters will), they were largely confined to the impossible-to-predict Alaska Senate race and a couple of House races. In a tribute to their accuracy, 17 of the 32 polls PPP has conducted since mid-October led to them coming within 3% of the final margin (53%). How did Rasmussen do on that score? Twenty-one out of 57 polls (36.8%) met that same standard. They also get the reward for dropping the biggest bomb of a poll this cycle. On October 20th, they reported to a shocked America that the GOP wave had even reached the impenetrable longtime Hawaii Senator Daniel Inouye. The House of Ras had the Hawaii Senate race as a 13-point race, with the man that has represented Hawaii since statehood up only 53-40. On Election Day, of course, Inouye won by...53 points (75-22).
RASMUSSEN IS NOT TERRIBLY BOLD: Maybe the biggest curiosity for me in this election cycle is how timid they were at the close. Only three polls in the last day. Only 11 in the last three days. To place that number in context, place it in comparison to PPP. PPP hit fewer polls over the final three weeks (57 to 32), but hit twice as many polls as the House of Ras in the final two days. Unlike Rasmussen, who reserved the right to hide behind the "late breaking dynamics" excuse if they chose, PPP put its reputation on the line by calling their shot at the last possible second. Remember, of course, that Rasmussen did the same thing during the primaries. Most notably, they also did it during the Massachusetts Senate race, when they refused to poll the race in the last week, but inexplicably ran instead a national poll about who the country wanted to see win the race.
Nate Silver of 538/NYT fame crunched his own set of numbers on the House of Ras last night. He included the work that Ras subsidiary Pulse Opinion Research did for Fox News, and he found similar results:

Of the roughly 100 polls released by Rasmussen or its subsidiary Pulse Opinion Research in the final 21 days of the campaign, roughly 70 to 75 percent overestimated the performance of Republican candidates, and on average they were biased against Democrats by 3 to 4 points.

Every pollster is entitled to a bad cycle now and again -- and Rasmussen has had some good cycles in the past. But their polling took a major downturn this year.

Clearly, one of the consequences of last night's midterms is that a number of changes are going to come to America. In the insular world of the political press, it is high time for one long overdue change: the ability to recognize Rasmussen for what it is. And this cycle proved is that Rasmussen is a partisan outfit that does not necessarily produce great results, and puts its thumb AND forefinger on the scale for its favored party.
 

OscarB63

Farts in Elevators
DP Veteran
Joined
Sep 7, 2010
Messages
26,526
Reaction score
9,462
Location
Alabama
Gender
Male
Political Leaning
Conservative
Every pollster is entitled to a bad cycle now and again -- and Rasmussen has had some good cycles in the past. But their polling took a major downturn this year.

this says all that needs saying. Rasmussen has been accurate in the past, but because he had a downturn this year...he is suddenly biased in favor of the GOP.


NEXT!!!!
 

haymarket

DP Veteran
Joined
Sep 3, 2010
Messages
120,951
Reaction score
28,520
Gender
Undisclosed
Political Leaning
Undisclosed
Whovian - so you do not even look at the factual information? You dismiss it out of hand because you do not like the source?

What is there about proven bias in a pollster than you consider funny? Or is bias in a pollster acceptable as long as it is bias in your direction?

Inquiring minds want to know.
 

Whovian

Banned
Joined
Oct 5, 2010
Messages
7,153
Reaction score
2,250
Location
dimensionally transcendental
Gender
Male
Political Leaning
Conservative
Whovian - so you do not even look at the factual information? You dismiss it out of hand because you do not like the source?

What is there about proven bias in a pollster than you consider funny? Or is bias in a pollster acceptable as long as it is bias in your direction?

Inquiring minds want to know.

Considering how far left the KOS is, certainly I look at anything sourced there as suspect. But, as you provided no link, nothing to show where the information came from, I have to conclude you're trying to hide something. Perhaps the liberal bent in the guys piece?

You also failed to include any mention of any other pollsters who were off. An unbiased piece would not focus only on Rass... they would have included ANY pollster that was off.

You, Singiser and Kos have an obvious agenda. Revel in your partisan hackery my friend.

Inquiring minds want to know.
 

roughdraft274

ThunderCougarFalconBird
DP Veteran
Joined
Feb 3, 2010
Messages
15,874
Reaction score
9,694
Location
Louisiana
Gender
Male
Political Leaning
Other
Considering how far left the KOS is, certainly I look at anything sourced there as suspect. But, as you provided no link, nothing to show where the information came from, I have to conclude you're trying to hide something. Perhaps the liberal bent in the guys piece?

You also failed to include any mention of any other pollsters who were off. An unbiased piece would not focus only on Rass... they would have included ANY pollster that was off.

You, Singiser and Kos have an obvious agenda. Revel in your partisan hackery my friend.

Inquiring minds want to know.

If gallup release a poll that's off by almost 50 points I promise you I'll post a link to it and you can call them liberals all you want, lol.
 

haymarket

DP Veteran
Joined
Sep 3, 2010
Messages
120,951
Reaction score
28,520
Gender
Undisclosed
Political Leaning
Undisclosed
from Whovian

I have to conclude you're trying to hide something.

Oh
my
gawd!

Instead of attacking the messenger why don't you examine the article itself and tell us what is factually wrong with the information presented?

the article is filled with actual hard numbers from Rasmussen polls and others. It would be nice to deal with the actual numbers and what they mean rather than an ad hominem attack on the publisher or writer.
 

Deuce

Outer space potato man
DP Veteran
Joined
Feb 6, 2010
Messages
77,013
Reaction score
34,029
Gender
Male
Political Leaning
Undisclosed
from Whovian



Oh
my
gawd!

Instead of attacking the messenger why don't you examine the article itself and tell us what is factually wrong with the information presented?

the article is filled with actual hard numbers from Rasmussen polls and others. It would be nice to deal with the actual numbers and what they mean rather than an ad hominem attack on the publisher or writer.

I don't think you understand.

You didn't post an article. You posted words. To be "factual information," it needs a source.
 

Whovian

Banned
Joined
Oct 5, 2010
Messages
7,153
Reaction score
2,250
Location
dimensionally transcendental
Gender
Male
Political Leaning
Conservative
If gallup release a poll that's off by almost 50 points I promise you I'll post a link to it and you can call them liberals all you want, lol.

I take it you have a link to a Rassmusen poll that was 50 points off, in favor of the Republican candidate?

Link please?
 

haymarket

DP Veteran
Joined
Sep 3, 2010
Messages
120,951
Reaction score
28,520
Gender
Undisclosed
Political Leaning
Undisclosed
Whovian
thank you for making three posts to this thread. Your participation is welcome and appreciated. It would be even more welcome and appreciated if you decided to discuss the numbers in the original article that prompted the thread.

For example, does it bother you that

The House of Ras overestimated the margins in the race to the advantage of the GOP in 46 out of those 57 contests (81%).

Or is that acceptable to you since it agrees with your own bias?

Or how about this

On October 20th, they reported to a shocked America that the GOP wave had even reached the impenetrable longtime Hawaii Senator Daniel Inouye. The House of Ras had the Hawaii Senate race as a 13-point race, with the man that has represented Hawaii since statehood up only 53-40. On Election Day, of course, Inouye won by...53 points (75-22).

How does that sit with you knowing that the media presents Ras poll numbers as valid news and evidence of political trends?
 

Kandahar

Enemy Combatant
DP Veteran
Joined
Jul 20, 2005
Messages
20,688
Reaction score
7,320
Location
Washington, DC
Gender
Male
Political Leaning
Liberal
So, looking at unique races, we get down to 57 contests. The House of Ras overestimated the margins in the race to the advantage of the GOP in 46 out of those 57 contests (81%). In an ideal world, of course, a pollster would get their numbers wrong pretty evenly.

That doesn't make any sense. There may be perfectly legitimate reasons that a pollster would get their numbers wrong in favor of one party more often than the other. Maybe Rasmussen words its questions slightly differently than other pollsters, or it doesn't call cell phones, or it doesn't offer Spanish-language polls, or it used an estimation of likely voters that turned out to be incorrect.

Clearly, one of the consequences of last night's midterms is that a number of changes are going to come to America. In the insular world of the political press, it is high time for one long overdue change: the ability to recognize Rasmussen for what it is. And this cycle proved is that Rasmussen is a partisan outfit that does not necessarily produce great results, and puts its thumb AND forefinger on the scale for its favored party.

:roll:
Polls that favor one party doesn't mean there is some sinister conspiracy afoot, or that Rasmussen "puts its thumb and forefinger on the scale for its favored party." Rasmussen certainly had a bad election cycle and it's important to remember that in the future, but it doesn't mean that they're motivated by partisanship. It just means they had a bad election cycle.
 

cpwill

DP Veteran
Joined
Dec 20, 2009
Messages
65,620
Reaction score
33,492
Location
USofA
Gender
Male
Political Leaning
Conservative
DailyKos?

REALLY?

:2funny::2funny::2funny::2funny:

because they're known for their close connection to accurate polling

Daily Kos Polling Fraud


Rasmussen polls likely voters. the Democrats surprised pretty much everyone this time around with the power of their ground game in critical races; especially in Nevada. the ground game specifically targetting not 'likely voters'. so it makes sense that his polls would skew towards likely voters, who themselves skewed republican.

the disparity in the results here aren't a hit on Rasmussen; they are to the credit of Democrats.
 

haymarket

DP Veteran
Joined
Sep 3, 2010
Messages
120,951
Reaction score
28,520
Gender
Undisclosed
Political Leaning
Undisclosed
I really have to learn how the game is played by some here . For some ideologically driven posters it seems to be a pissing contest with the attitude of some (not all) being "oh yeah!!!!! your guys are worse than mine". In this case it seems to also be a bit of "sure we ran you over with our SUV - but we didn't mean to do it - at least the first time".
 

Whovian

Banned
Joined
Oct 5, 2010
Messages
7,153
Reaction score
2,250
Location
dimensionally transcendental
Gender
Male
Political Leaning
Conservative
I really have to learn how the game is played by some here . For some ideologically driven posters it seems to be a pissing contest with the attitude of some (not all) being "oh yeah!!!!! your guys are worse than mine". In this case it seems to also be a bit of "sure we ran you over with our SUV - but we didn't mean to do it - at least the first time".
Yes, you do.

If you're going to post crap without lining to the source, expect to be called out on it... by both sides. To their credit, the vast majority of posters on the liberal side who post, LINK to the source material or material that supports their position in a particular thread. You would do well to learn by their example.

BTW, what, exactly, IS 'my bias' in this thread? Please elaborate. Oh, and we're all still waiting for that link to a Rassmussen poll that was off by 50% in favor of the right.
 

apdst

Banned
DP Veteran
Joined
Jun 23, 2009
Messages
133,631
Reaction score
30,927
Location
Bagdad, La.
Gender
Male
Political Leaning
Very Conservative
I was really hoping that Liberals wouldn't be cry babies about getting their asses handed to them.
 

Taylor

DP Veteran
Joined
Aug 31, 2009
Messages
16,142
Reaction score
6,311
Location
US
Political Leaning
Undisclosed
For someone who calls himself "the resident poll guy" he makes some really stupid comparisons. If you want to compare accuracy, you really need to compare polls for the same state that were taken on the same day. Polls are just snapshots.
 

Taylor

DP Veteran
Joined
Aug 31, 2009
Messages
16,142
Reaction score
6,311
Location
US
Political Leaning
Undisclosed
Or how about this
On October 20th, they reported to a shocked America that the GOP wave had even reached the impenetrable longtime Hawaii Senator Daniel Inouye. The House of Ras had the Hawaii Senate race as a 13-point race, with the man that has represented Hawaii since statehood up only 53-40. On Election Day, of course, Inouye won by...53 points (75-22).
How does that sit with you knowing that the media presents Ras poll numbers as valid news and evidence of political trends?
Quite amusing that this "Steve Singiser" highlights this as proof of inaccuracy. The poll was apparently taken over two weeks before the election. Do you know how popular the guy was in middle of March? Steve Singiser sure doesn't. Nobody else bothered to poll during that time or anytime thereafter.

His heralded PPP provided the only other data point. Their "NOT TERRIBLY BOLD" poll was even more "timidly" conducted on Oct 2. I guess he forgot to mention that PPP also underestimated "the man that has represented Hawaii since statehood" by double digits, and were almost 20 points off on the margin.

Needless to say, who knows what happened between middle of March and Election Day, or in the 4-5 hours Hawaii still had to vote after election results started pouring in.
 

Kandahar

Enemy Combatant
DP Veteran
Joined
Jul 20, 2005
Messages
20,688
Reaction score
7,320
Location
Washington, DC
Gender
Male
Political Leaning
Liberal
FiveThirtyEight has a more grown-up critique of Rasmussen's performance:

Rasmussen Polls Were Biased and Inaccurate; Quinnipiac, SurveyUSA Performed Strongly - NYTimes.com

Rasmussen’s polls have come under heavy criticism throughout this election cycle, including from FiveThirtyEight. We have critiqued the firm for its cavalier attitude toward polling convention. Rasmussen, for instance, generally conducts all of its interviews during a single, 4-hour window; speaks with the first person it reaches on the phone rather than using a random selection process; does not call cellphones; does not call back respondents whom it misses initially; and uses a computer script rather than live interviewers to conduct its surveys. These are cost-saving measures which contribute to very low response rates and may lead to biased samples.

Rasmussen also weights their surveys based on preordained assumptions about the party identification of voters in each state, a relatively unusual practice that many polling firms consider dubious since party identification (unlike characteristics like age and gender) is often quite fluid.

There were some serious problems with Rasmussen's methodology that caused a Republican bias in its results. Sorry, no sinister partisan conspiracy. :roll:
 
Last edited:

haymarket

DP Veteran
Joined
Sep 3, 2010
Messages
120,951
Reaction score
28,520
Gender
Undisclosed
Political Leaning
Undisclosed
The article I copied here did include mentions of the 538/Silver findings also.

The suspicion that Rasmussen tilts his results in favor of Republican or conservative candidates is not something which was just invented for this article. It was present for this entire election cycle. The numbers given to the public by Rasmussen so often deviated from other polling companies that they were often described as outliers and not reliable. There was also lots of discussion that Rasmussen was attempting to drive a particular partisan narrative early on in the cycle but would then get his numbers in line as the election day closed in.

btw - I had my own personal experience with polling recently and I came away a believer. I managed a political campaign for the office of State Representative. It was an nine person field for the hotly contested primary and in the last week it had closed to a two or three person race. With just six days to go, we commissioned a poll to give us a better idea of where we stood. The poll that we could afford was the cheapest possible way to do it and still get results considered anywhere near reliable. Basically, they took the names of some 6,000 likely voters and made robocalls to them over two evenings. The people on the other end were given three choices and they had to hit a certain button for each. We were told that if we got 700 or more responses the results would be within an accuracy range of five points.

Keep in mind that there was no screening of the calls to make sure we were talking to the actual voter. There was no allowance made for anyone who wanted to vote for anyone outside the three choices. There was no way to take a truly representative sample based on both demographics and spread throughout the district. It sounded pretty hit and miss to me but it was cheap and the candidate wanted to do it so we went ahead.

They came back two days before the election and told us they only managed to get about 350 responses. But the good news was we were 2 points ahead. They also told us we were running strongest among female voters but were five points behind with senior citizens. On election day we finished first 1.5 points ahead. We lost the absentee vote by 3 points - which is mostly seniors.

The accuracy of this rather unscientific poll done as cheaply as possible was amazing. It made a believer out of me.

This is from the Wikipedia entry on Rasmusen polls

Criticism

TIME has described Rasmussen Reports as a "conservative-leaning polling group".[16] The Center For Public Integrity has pointed out that Scott Rasmussen was a paid consultant for the 2004 George W. Bush campaign.[17] According to Nate Silver's FiveThirtyEight.com, while there are no apparent records of Scott Rasmussen or Rasmussen Reports making contributions to political candidates in recent years and its public election polls are generally regarded as reliable, "some observers have questioned its issue-based polling, which frequently tends to elicit responses that are more conservative than those found on other national surveys."[18]
Josh Marshall of Talking Points Memo commented on their reliability in a February 2009 article:[19][20]
The toplines tend to be a bit toward the Republican side of the spectrum, compared to the average of other polls. But if you factor that in they're pretty reliable. And the frequency that Rasmussen is able to turn them around – because they're based on robocalls – gives them added value in terms of teasing out trends. But the qualitative questions, in terms of their phrasing and so forth, are frequently skewed to give answers friendly toward GOP or conservative viewpoints. All of which is to say that his numbers are valuable. But they need to be read with that bias in mind.
Nate Silver of fivethirtyeight.com observed that at the end of the 2010 general election cycle, Rasmussen Polls consistently were biased against Democrats by 3 to 4 points. [21]
I did a quick check on the accuracy of polls from the firm Rasmussen Reports, which came under heavy criticism this year — including from FiveThirtyEight — because its polls showed a strong lean toward Republican candidates. Indeed, Rasmussen polls quite consistently turned out to overstate the standing of Republicans tonight. Of the roughly 100 polls released by Rasmussen or its subsidiary Pulse Opinion Research in the final 21 days of the campaign, roughly 70 to 75 percent overestimated the performance of Republican candidates, and on average they were biased against Democrats by 3 to 4 points. ....it appears as though the worst poll of the political cycle will be the Rasmussen Reports survey of Hawaii, which had the incumbent Daniel Inoyue defeating Cam Cavasso by just 13 points. Mr. Inouye is ahead by 55 points right now. If Mr. Inouye’s margin holds, the 42-point error would be by far the worst general election poll in FiveThirtyEight’s database, which includes all polls since 1998; the previous record was 29 points.
Rasmussen has received criticism over the wording in its polls.[22][unreliable source?] Examples of Rasmussen's questions with wording issues include:
Agree or Disagree: "Rush Limbaugh is the leader of the Republican Party. He says jump, and they say how high."[23]
Do you favor or oppose the economic recovery package proposed by Barack Obama and the Congressional Democrats?[24]
Suppose that Democrats agreed on a health care reform bill that is opposed by all Republicans in Congress. Should the Democrats pass that bill or should they change the bill to win support from a reasonable number of Republicans?[25]
Do you agree or disagree with the following statement... it’s always better to cut taxes than to increase government spending because taxpayers, not bureaucrats, are the best judges of how to spend their money?[25][unreliable source?]
Some of Rasmussen polls have contained two different weights for questions, depending on the party of the statesman in the question.[26][unreliable source?] In one example, the first question asks for a job rating for Tim Pawlenty, a Republican governor, using an approve/disapprove scale. The next question asks for the way that Al Franken, a Democratic senator, is performing his role, but uses a Excellent/Good/Fair/Poor scale. Nick Panagakis of Pollster.com has pointed out that, when using the latter scale, "approval is often reported by combining the top two and bottom two scores", including the "fair" score as a "disapproval" vote.[27]
According to Charles Franklin, a University of Wisconsin political scientist who co-developed Pollster.com,[28] “He [Rasmussen] polls less favorably for Democrats, and that’s why he’s become a lightning rod." Franklin also said: "It’s clear that his results are typically more Republican than the other person’s results.”[29]
 
Last edited:

OscarB63

Farts in Elevators
DP Veteran
Joined
Sep 7, 2010
Messages
26,526
Reaction score
9,462
Location
Alabama
Gender
Male
Political Leaning
Conservative
I was really hoping that Liberals wouldn't be cry babies about getting their asses handed to them.

like my daddy always said..."you can hope in one hand and **** in the other and see which one fills up first" :lamo It's politics, I knew whichever side that lost would be crybabies about it.
 

haymarket

DP Veteran
Joined
Sep 3, 2010
Messages
120,951
Reaction score
28,520
Gender
Undisclosed
Political Leaning
Undisclosed
apdst

How is pointing out the weaknesses and inaccuracies of Rasmussen polls crying about the election results? You are confusing two different things.
 

OscarB63

Farts in Elevators
DP Veteran
Joined
Sep 7, 2010
Messages
26,526
Reaction score
9,462
Location
Alabama
Gender
Male
Political Leaning
Conservative
apdst

How is pointing out the weaknesses and inaccuracies of Rasmussen polls crying about the election results? You are confusing two different things.

ah..but you were not pointing out weaknesses and inaccuracies. you were accusing Rasmussen of deliberate bias in favor of the GOP. there is a difference. It would appear you are the one who is confused (or, more likely, simply being dishonest)
 

haymarket

DP Veteran
Joined
Sep 3, 2010
Messages
120,951
Reaction score
28,520
Gender
Undisclosed
Political Leaning
Undisclosed
did you not read this???

Of the roughly 100 polls released by Rasmussen or its subsidiary Pulse Opinion Research in the final 21 days of the campaign, roughly 70 to 75 percent overestimated the performance of Republican candidates, and on average they were biased against Democrats by 3 to 4 points. ....it appears as though the worst poll of the political cycle will be the Rasmussen Reports survey of Hawaii, which had the incumbent Daniel Inoyue defeating Cam Cavasso by just 13 points. Mr. Inouye is ahead by 55 points right now. If Mr. Inouye’s margin holds, the 42-point error would be by far the worst general election poll in FiveThirtyEight’s database, which includes all polls since 1998; the previous record was 29 points.

My opening post had lots of similar info including the Hawaii numbers.
 
Last edited:

OscarB63

Farts in Elevators
DP Veteran
Joined
Sep 7, 2010
Messages
26,526
Reaction score
9,462
Location
Alabama
Gender
Male
Political Leaning
Conservative
did you not read this???


did you not read this?????

Every pollster is entitled to a bad cycle now and again -- and Rasmussen has had some good cycles in the past. But their polling took a major downturn this year.

nothing in your sourceless posting indicates that Rasmussen was intentionally biased. he had a bad cycle.
 

haymarket

DP Veteran
Joined
Sep 3, 2010
Messages
120,951
Reaction score
28,520
Gender
Undisclosed
Political Leaning
Undisclosed
That is a rationalization - an excuse - an attempt to downplay the results. It changes nothing.

does this float your boat?

http://fivethirtyeight.blogs.nytime...rate-quinnipiac-surveyusa-performed-strongly/

a small part of the Nate Silver article

The 105 polls released in Senate and gubernatorial races by Rasmussen Reports and its subsidiary, Pulse Opinion Research, missed the final margin between the candidates by 5.8 points, a considerably higher figure than that achieved by most other pollsters. Some 13 of its polls missed by 10 or more points, including one in the Hawaii Senate race that missed the final margin between the candidates by 40 points, the largest error ever recorded in a general election in FiveThirtyEight’s database, which includes all polls conducted since 1998.

Moreover, Rasmussen’s polls were quite biased, overestimating the standing of the Republican candidate by almost 4 points on average. In just 12 cases, Rasmussen’s polls overestimated the margin for the Democrat by 3 or more points. But it did so for the Republican candidate in 55 cases — that is, in more than half of the polls that it issued.

If one focused solely on the final poll issued by Rasmussen Reports or Pulse Opinion Research in each state — rather than including all polls within the three-week interval — it would not have made much difference. Their average error would be 5.7 points rather than 5.8, and their average bias 3.8 points rather than 3.9.

and if that is not enough to show bias - it started before these midterm elections

The discrepancies between Rasmussen Reports polls and those issued by other companies were apparent from virtually the first day that Barack Obama took office. Rasmussen showed Barack Obama’s disapproval rating at 36 percent, for instance, just a week after his inauguration, at a point when no other pollster had that figure higher than 20 percent.

Rasmussen Reports has rarely provided substantive responses to criticisms about its methodology. At one point, Scott Rasmussen, president of the company, suggested that the differences it showed were due to its use of a likely voter model. A FiveThirtyEight analysis, however, revealed that its bias was at least as strong in polls conducted among all adults, before any model of voting likelihood had been applied.

Some of the criticisms have focused on the fact that Mr. Rasmussen is himself a conservative — the same direction in which his polls have generally leaned — although he identifies as an independent rather than Republican. In our view, that is somewhat beside the point. What matters, rather, is that the methodological shortcuts that the firm takes may now be causing it to pay a price in terms of the reliability of its polling.

This is not a guy merely having a bad season.
 
Last edited:
Top Bottom