« Kos: Krush Konservatives, Komrades | Main | Voodoo ACORNomics, Part Two »

One Obvious Reason the Polls Are Biased

I have said and will say again, that the opinion polls this year are simply wrong. They have fiddled with weighting and wording and various pieces of the demographics to create a false impression. You can either believe them or not, but as I have shown in the numbers for weeks now, believing the polls would be naïve at the very least.

But if the polls have been so biased, one may reasonably ask why that is so. I myself have commended groups like Gallup for a very professional job over many years, and even though I strongly disagree with the conclusions published by groups like CBS News, I applaud their open way of reporting at least some of the significant internal data. In fact, it is CBS News which reveals how this bias is operating, and how even well-intentioned pollsters can make major blunders in their assumptions.

I disagree with CBS News because of how it weights its respondent pool. And lately, what I have seen is a trend, verging on the ridiculous, of far too many Democrats in the pool to make any sense at all. This has been happening in both national polls and in state polls. For national polls, I mentioned some weeks back how Gallup managed to show Obama declining or staying steady in every political affiliation group over a week while McCain was steady or gained in every such group, yet Gallup's headline claimed Obama was gaining support overall, a mathematical impossibility without manipulating the proportionate weights.

For the states, Survey USA's polls also show a strong pro-Democrat bias, as shown in the following states (2004 and 2006 DRI splits come from actual elections, SUSA's 2008 split is arbitrary):

Ohio - 2004 DRI split was 35%/40%/25%, 2006 was 40%/37%/23%
SUSA in 2008 is using 46%/33%/20%

North Carolina - 2004 DRI split was 39%/40%/21%, 2006 was 39%/40%/21%
SUSA in 2008 is using 42%/37%/18%

Virginia - 2004 DRI split was 35%/39%/26%, 2006 was 36%/39%/26%
SUSA in 2008 is using 39%/30%/25%

Pennsylvania - 2004 DRI split was 41%/39%/20%, 2006 was 43%/38%/19%
SUSA in 2008 is using 54%/35%/10%

Florida - 2004 DRI split was 37%/41%/23%, 2006 was 36%/39%/25%
SUSA in 2008 is using 40%/42%/16%

Survey USA is using weights which have no historical validity whatsoever in their state polling. "Garbage" is not too strong a word to describe their published results.

So what's the deal? Something is happening to skew the polling groups' perception of how they think voters will turn out, and in publishing invalid conclusions as they have, they are - intentionally or not - misleading the public about the election conditions. Since the reputation of the polling group is essential in attracting future business clients, it hardly seems reasonable to consider these blunders to be deliberate. Although I have written that polls fall into the unethical habit of selling a roller coaster story which they know is not accurate, polls do try to stay close enough to be plausible. One must conclude that they have come to believe their own hype, forgetting Heisenberg's warning that observing a behavioral event not only influences the event, but also affects the observer as well.

So, in looking around for a cause, I found something all major polls have in common. Look at their headquarters locations:

Poll Headquarters
ABC News 77 W 66th St, #13, New York City, New York
CBS News 524 W 57th St, New York City, New York
FOX News 1211 Avenue of the Americas, New York City, New York
Gallup 901 F St NW, Washington DC
Hotline 88 Pine St, 32nd floor, New York City, New York
IBD 12655 Beatrice St. Los Angeles, California
LA Times 202 W 1st St, Los Angeles California
Marist 3399 North Rd, Poughkeepsie, New Jersey
Mason-Dixon 1250 Connnecticut Ave #200, Washington DC
Newsweek 251 W 57th St, New York City, New York
NY Times 1 City Hall, New York City, New York
Pew 1615 L St NW, #700, Washington DC
Quinnipiac 275 Mount Carmel Ave., Hamden Connecticut
Rasmussen 625 Cookman, #2, Asbury Park, New Jersey
Reuters 3 Times Square, New York City, New York
Survey USA 15 Bloomfield Ave., Verona New Jersey
TIPP 690 Kinderkamack Rd, Oradell, New Jersey
WaPo 1150 15th St NW, Washington DC
Zogby 901 Broad St, Utica, New York

All of them deep in "blue" territory, many packed together up on the northeast corner of Obama territory. The only non-east-coast member of this group is the LA Times, located in the most liberal section of California, also solid blue in perspective. This is not a coincidence, all of the major polling organizations are based in locations where liberals are strongest and conservatives weakest, where 'democrat' and 'republican' take on meanings wildly different from the rest of the country. As a result, it is obvious that the prevailing culture in this limited part of the country has an undue influence on the focus applied by these polling groups. Democrats, especially liberal democrats, are over-represented in the poll reports because the culture of New York and Northeast America over-represents liberals. Republicans, especially conservative republicans, are suppressed in the poll reports because the culture at the polling groups' headquarters suppresses republican opinion.

I learned long ago, that when a manager displays certain personality traits, they are soon reflected by the employees at that company. A relaxed manager who is confident tends to improve the mood of his staff, while a tense micro-manager creates the same attitude in his employees. Knowing this, it's not at all hard to imagine the conversations between headquarters and the staff at these polling groups. They like Obama and expect him to win, so - what a surprise! - the polls they control reflect that same attitude.

Polls are useful for investigating trends and movement within a specific demographic, provided the polling group is ethical enough to publish its internals. But trusting them for an honest topline report amounts to trusting Obama's campaign to honestly report how the election is really going.


TrackBack

TrackBack URL for this entry:
/cgi-bin/mt-tb.cgi/32267.

Comments (42)

My greatest hope remains wi... (Below threshold)
Paul_In_Houston:

My greatest hope remains with the "Silent Majority".

It is very real, comprised of folks who abhor confrontation and arguing with loons, and are apt to respond to the left's "get into their faces" tactic by going into the voting booth with "Vengeance is mine!" in their thoughts.

They probably don't get polled all that much as they are busy with working and LIFE (and possibly skipped for fear they might give the wrong answers).

They aren't big on demonstrations or political stickers (I suspect the likelihood of people actually going to the polls and voting is inversely proportional to the number of stickers on their cars), but they DO go out and vote.

Obamaphiles: note how many cars are free of political stickers; and be afraid, be very afraid :-)

P.S. I totally believe what... (Below threshold)
Paul_In_Houston:

P.S. I totally believe what I said about the "Silent Majority".

I also suspect that the Bradley Effect will be in play here, because many people may have serious doubts about this guy's totally non-existent resume but choose to tell pollsters what they want to hear rather than argue about whether they are racist or not.

This could apply to exit polls as well, resulting in discouraging news when they are reported, followed by WTF? when the actual numbers come.

At least, that's my hope, and I don't think it an unreasonable one.

Don't lose heart. That's precisely what they want us to do; be so worn out and sick with despair, that we don't even go and vote election day.

I'm tempted to accommodate them this far; skip election day by early voting for McCain/Palin if I get the chance.

Think THAT will make 'em happy? :-)

Nah... Not even remotely possible. Ever notice how many of his supporters go around looking as if they just swallowed something particularly nasty?

If it wasn't for who they are, I'd probably feel sorry for them; it must really suck to BE them sometimes.

Perhaps they're going by re... (Below threshold)

Perhaps they're going by registration numbers. You know, the ones for which ACORN is being investigated...

DJ - please comment: To ec... (Below threshold)
Carol:

DJ - please comment: To echo BlueNight's point, are the pollsters using these Democrat heavy weightings because of the surge in Democrat registrations, a lot of which happened during the primary battle between Obama and Clinton? If so, it is possible they are right to assume a historically high turnout of Dems?

DJ, I have some university ... (Below threshold)

DJ, I have some university education in statistics use and agree with your analysis for the most part about problems in the use of samples by some polling organizations. That's why I tend to rely on both Rasmussen and Scott Elliot's ELECTION PROJECTION as the best sites for reputable analysis of the actual state of the race and more accurate sample analysis models.

Ummm, why is that Paul? Ra... (Below threshold)
DJ Drummond:

Ummm, why is that Paul? Rasmussen, for example, releases NONE of his internal demographics, basically denying anyone the chance to check his math. That's plain unethical, conflicting with NCPP guidelines for poll reporting.

Scott Elliot is a great guy, but he uses aggregates of polls for his projections, which as you know is statistically invalid. It creates collinearity, doing that.

DJ,I went through ... (Below threshold)
Jeff:

DJ,

I went through the latest CBS poll with the proper historic weighting (like you did the last time) and found an actual 50-42% Obama lead.

But it's ridiculous to believe that "independents" went from +3 McCain a week ago to +18 Obama this week.

Heh.Jeff, I will b... (Below threshold)
DJ Drummond:

Heh.

Jeff, I will be posting about 'independents' later this week.

DJ,Thank you for y... (Below threshold)
David Marcoe:

DJ,

Thank you for your articles. They are the one ray of sunshine I see among right-wing blogs.

First of all, it is Demo... (Below threshold)
SDW:

First of all, it is Democratic, not "Democrat." Stop using the RNC meme to wrongly name the oldest political party in the USA. Thomas Jefferson would slap all of you if he were alive today.

Second, just because Grampy McPlain is down in the polls, now the polls are biased?

Puhleez. You guys got nothin.

January 20, 2009 - the day that Barack Obama is sworn in as President of the USA and possibly the day Bush, Cheney, Rummy and Co. are arrested for crimes against humanity and crimes against the Constitution.

Thank you SDW, for showing ... (Below threshold)
DJ Drummond:

Thank you SDW, for showing us the attitude of the modern Democrats. This is what we can expect if Obama wins, and frankly I do not think most of America wants that.

And btw SDW, I have been sa... (Below threshold)
DJ Drummond:

And btw SDW, I have been saying this since 2004, so you are just a tick or two behind the times.

DJ, actually Rasmussen did ... (Below threshold)

DJ, actually Rasmussen did release some new demographics information just in the last week that now includes 39.3% Democrats, 33.0% Republicans and 27.7% unaffiliated voters. This was a modification from the previous week's formula from 39.3% Democratic, 33.3% Republican and 27.4% unaffiliated voters. Rasmussen makes weekly adjustments to the weighted voter sample polls based on registration trends which I consider to be one of the best statistical pool sample adjustment formulas. Rasmussen also employs a three day rolling average method as well unlike many other polling organizations who rely on the less accurate voter "snapshot" formula.

I certainly agree that Scott Elliot is a fine guy, He's a wonderful Christian as well. His methods seem to yield very accurate results by analysis of the average of the polls of others without the expense of having his own polling data organization. On a shoestring, he's gained a solid reputation as one of the best in election data analysis.

Rasmussen does not release ... (Below threshold)
DJ Drummond:

Rasmussen does not release internal demographics, Paul. Things like how many republicans voted which way, how many democrats, how many independents, how many men and women, how many in the various regions, how many of differing age groups and educations, etc. Without that information, his opinion is unsupported by any real data.

Whether you like what a poll says or not, the critical point is that you have to be able to work out the math for yourself. Otherwise, you are just taking someone's word for something, which is just absurd.

And no, Paul, Scott Elliott is popular, but that is not the same as being the best credentialed. His aggregates are interesting, but they are no more statistically valid than a bowl of pork rinds is healthy food.

You know jeff (comment 7), ... (Below threshold)
DJ Drummond:

You know jeff (comment 7), CBS is actually saying that independents went from McCain + 10 (49-39 M) to Obama + 18 (51-33 O) in just one week, on no specific cause whatsoever!

DJ, probably those Rasmusse... (Below threshold)

DJ, probably those Rasmussen internal demographics are like closely held "trade secrets" to the Rasmussen organization and their own "meal ticket" so they don't chose to disclose that portion of their internal data collection. Rasmussen probably considers the disclosure of this much information as serious of a financial threat to their organization as KFC offering their chicken recipe for free to anyone.

What I like the most about Rasmussen seems to be that they take into account more Republican leaning voters than many other polling organizations. And traditionally Republican turnout tends to be stronger than Democrats, so this polling method seems more accurate to me.

Many voters also are unwilling to vary very much in their usual voting patterns. In 1980 I lost a substantial portion of my income due to the Jimmy Carter recession which hit my business very hard and had to weight that against my foreign policy concerns about Ronald Reagan, so I was in the John Anderson camp until only days before the election.

These are really great post... (Below threshold)

These are really great posts. I have linked several of them to my site. I am really fascinated that all the major polling firms are located where they are. I think that there is a case that this is why there is so much stacking in the polling data. BTW, I refer those who want to keep peddling the "Bradley effect" to a post that I had that the George Deukmejian pollster saying that the election simply broke his way. Period. I also think that the polling is being done totally based on the issue of the day, not overall where people are in total thinking. I think that there are a lot of people like Paul Hooson who were in one camp and really thought about it and will switch before election day.

Again, no. Paul, many</... (Below threshold)
DJ Drummond:

Again, no. Paul, many major polls release internal data, including Gallup, Pew, FOX News and many of the universities. There is no proprietary aspect to internal demographics. There is no commercial reason whatsoever not to release that information, and such transparency is required by all adherents to the NCPP's Principles of Disclosure
(http://www.ncpp.org/?q=node/19), which Rasmussen has previously claimed he follows.

Hence, hiding such information is unethical at best.

A note on Rasmussen releasi... (Below threshold)
Bamaman:

A note on Rasmussen releasing his political affiliation assumptions: That only applies to the national polling numbers. More important to see from him would be his state by state assumptions.

A few aspects of these poll... (Below threshold)
Bamaman:

A few aspects of these polls that i would like an opinion on are the effect of those of us who no longer have home phones to call(a majority of the people in my office no longer have a home phone and rely totaly on cell phones) and also how the phone numbers are randomly selected. For my life in Lower Alabama, I have never once met someone who has ever been called and asked to participate in a national poll by any of the big organizations.

DJ, careful, I found that i... (Below threshold)
Ray H.:

DJ, careful, I found that if you disagree with either Paul or Lee, you get yourself banned.

Doesn't this all seem to wo... (Below threshold)
Baggi:

Doesn't this all seem to work together quite nicely?

Polls show Obama winning the election handily.

ACORN has registered 1.3 million new voters, a huge number by any historic means!

Obama has collected hundreds of millions of dollars more than any other candidate, all of it from .50 cent donations from all those who intend to vote for him during this next election.

Isn't it obvious that he should/will win this election? If he doesn't, the only answer is that Republicans cheated.

Either that or those donations Obama got were from overseas people without names, those 1.3 million voters ACORN registered were mostly fraudulent and the polls are all skewed to create the perception that both the fraudulent registrations combined with the fraudulent donations are meant to create.

It seems obvious that something is going on here but what i don't know. Vast conspiracies are difficult for me to believe.

Does it have to be a vast conspiracy in order for the above to be true?

Actually Ray, I do not thin... (Below threshold)
DJ Drummond:

Actually Ray, I do not think Paul bans people. Lee, of course, is a once-hopeful experiment gone bad, a disgruntled fiction-based lifeform with access to a terminal and DU. But he can't ban me from here, he can only ban me from WizBlue, where I am hardly likely to waste time or attention.

Keep KICKING ASS DJ !!!!!!!... (Below threshold)
PaRep:

Keep KICKING ASS DJ !!!!!!!!!!!!!

Regardless of my snide rema... (Below threshold)
Ray H.:

Regardless of my snide remark, this analysis continues to be very enlightening. thank you!

D.J. you said yesterday tha... (Below threshold)
Pam:

D.J. you said yesterday that you think McCain might flip Penn; do you have an stats we can look at or is it just a feeling based on where each man is campaigning?

You're doing the Lord's work. And I know some days you must hate doing blogs in order to keep the rest of us bucked up. But thank you for doing them. We need to hear it everyday. Turn out, Turn out, Turn out!

"The only non-east-coast me... (Below threshold)
Herman:

"The only non-east-coast member of this group is the LA Times, located in the most liberal section of California, also solid blue in perspective." -- DJ Drummond

Mr. Drummond, HOW DARE YOU INSULT THE GOOD CITIZENS OF THE PEOPLE'S REPUBLIC OF BERKELEY!!!

Try not to be so foolish next time, DJ.

Totally agree. No idea whi... (Below threshold)
Clint:

Totally agree. No idea which candidate is going to win the election, but all of the pollsters are going to end up with egg on their faces. (Unless they can succeed in convincing the public that the polls were accurate, but a vast undercurrent of secret racism foiled them. Shame on you, America!)

One note, re: Rasmussen -- he does release the internals, you just have to be a subscriber to get access. Unlike most of the other polls, his DRI split isn't so outrageous, but he's got Indpendents going for Obama by six to eight percent.

*shrug*

I still can't understand why all the polls are coming out about the same and moving up and down together. Their methodologies are so screwy and so different that there ought to be a much larger spread.

Leads me to believe that they are all watching all the other polls and if their poll gets too far from the pack, they assume something must be wrong and tweak their model a bit.

You know, just how proper scientists and statisticians do it. /snark

Here you go<a href... (Below threshold)
PaRep:
Regarding the polling data:... (Below threshold)
RPL:

Regarding the polling data:

Is there any way to account for the disaffected Hillary voters, and how many of them will cross party lines? I've heard estimates ranging from 10% to 40% of the 18 million. Alot of them are rather upset at the DNC, and the way Hillary was treated.

In 2006, republican voter turnout was low due to dissatisfaction with the way the party was being managed. Will that still be the case this year?

Given that Obama has told his supporters to "get in people's faces," how many people who support McCain or are leaning that way just stay quiet or give a wrong answer to avoid a fight?

In the samples, are they age weighted? Older people may vote more conservative, while younger people may vote a more liberal ticket.

There are other questions that would affect the data, and they have picked over before (cell phone/land line, Bradley effect). Jst other factors to consider in looking at the polls.

Well lookie lookie! The ga... (Below threshold)
Jeff:

Well lookie lookie! The gallup poll today is touting its registered vote results of 50-43 Obama. But if you look at its "traditional likely voter" model results it's 49-46% Obama.

Also, to add to 29:<p... (Below threshold)
LaMedusa:

Also, to add to 29:

Obama raised $1 million for foreign thug's election~Democrat joined Libya's Gadhafi among top contributors to Odinga

http://www.worldnetdaily.com/index.php?fa=PAGE.view&pageId=78035

HAHAHAHAHAHAHA John(Marines... (Below threshold)
PaRep:

HAHAHAHAHAHAHA John(Marines Murdered in Cold Blood)Murtha just called Western Pa. A racist Area

hahahahahahaha Thanks Jackoff John

If you think the exit polls... (Below threshold)
RSR:

If you think the exit polls were out of whack in 2004, wait until you see them this year. I believe there will be a Bradley effect because I suspect a fair number of McCain voters will tell exit pollsters that they voted for Obama simply so they won't have to deal with implied accusations of racism.

If the exit polls show Obama winning but McCain wins after the votes are all counted the left will go absolutely bonkers.

If the exit polls show O... (Below threshold)
Les Nessman:

If the exit polls show Obama winning but McCain wins after the votes are all counted the left will go absolutely bonkers.

Yep. And it shows how much of a disservice these skewed polls are doing to our country. They are directly contributing to civil unrest. If Brocko loses despite months of being 'ahead' in 'trustworthy, mainstream' polls, all hell is going to break loose.

uh,Paul Hooson,you better g... (Below threshold)
jhow66:

uh,Paul Hooson,you better get back over tp "Blue" as lee lee will have no one to comment on his posts.

DJ: I agree with your anal... (Below threshold)
Jon S.:

DJ: I agree with your analysis all the way, but my fear is that the media-driven polls proclaiming Obambi to be well ahead will have the intended effect: suppression of Republican votes, driving up Indies who for some strange reason like to 'go with the winner.'

Are you concerned about these twin effects too?

If Brocko loses de... (Below threshold)
RFA:
If Brocko loses despite months of being 'ahead' in 'trustworthy, mainstream' polls, all hell is going to break loose.

That's cool by me. I have my Glock .40 loaded and by my side. If they come messing with me they'll get what they deserve.

These idiots will burn down their own neighborhood to protest this "Stolen Election"! Really bright like a 15 watt bulb.

Despite their transparency,... (Below threshold)
Louis:

Despite their transparency, the CBS Poll has been way off (on almost any subject, including elections) for as long as I can remember. You would think that they would tweak their methodology to align their results with reality. They would have more credibility if they did.

I started to ask D.J. why CBS persists in using this flawed model.

However, I think I may know his answer. I may be wrong, but my guess is that CBS has a certain customer base, and those customers want to see a liberal result. So the CBS polling unit keeps them happy for the simple reason that they don't want to lose those customers--especially in this era of newspaper/television-audience decline.

This rule also applies to any media poll, regardless of the supposedly non-biased polling unit they have paired with to help them gain respectability/believability. It's so transparent that you really wonder why media outlets even bother.

We make assumptions ... (Below threshold)
Ronsonic:


We make assumptions about where the financial interests of the polling companies lie, but those are only assumptions and I am guessing they are wrong. Us nutbag political junkies are not the ones actually writing the checks to Gallup. This is the angle that needs some exploration. As far as I can tell the guys sending the cash are major networks and newspapers who see politics mostly as a horserace and are mostly in the bag for Obama.

Thank you for some excellent analysis and please, look into the money angle. If all financial interests were as obvious as we assume Hollywood would stop making bad movies about American actions in the Middle East.

DJ & other folk read this d... (Below threshold)
PaRep:

DJ & other folk read this diary from Redstate

http://tinyurl.com/3p4hx4

"D.J. you said yesterday th... (Below threshold)

"D.J. you said yesterday that you think McCain might flip Penn"

The McCain campaign said on a conference call that their internal polls showed a close race in Pennsylvania. Obama is campaigning hard here, which is not what he would be doing if he were as ahead as we are led to believe. Also, during the evening, McCain ads outnumber Obama ads here by about 3:1. And McCain and Palin are doing rally after rally after rally here. I went to my third a week ago Saturday. If McCain were far behind, he'd pull out and spend his money elsewhere.




Advertisements









rightads.gif

beltwaybloggers.gif

insiderslogo.jpg

mba_blue.gif

Follow Wizbang

Follow Wizbang on FacebookFollow Wizbang on TwitterSubscribe to Wizbang feedWizbang Mobile

Contact

Send e-mail tips to us:

[email protected]

Fresh Links

Credits

Section Editor: Maggie Whitton

Editors: Jay Tea, Lorie Byrd, Kim Priestap, DJ Drummond, Michael Laprarie, Baron Von Ottomatic, Shawn Mallow, Rick, Dan Karipides, Michael Avitablile, Charlie Quidnunc, Steve Schippert

Emeritus: Paul, Mary Katherine Ham, Jim Addison, Alexander K. McClure, Cassy Fiano, Bill Jempty, John Stansbury, Rob Port

In Memorium: HughS

All original content copyright © 2003-2010 by Wizbang®, LLC. All rights reserved. Wizbang® is a registered service mark.

Powered by Movable Type Pro 4.361

Hosting by ServInt

Ratings on this site are powered by the Ajax Ratings Pro plugin for Movable Type.

Search on this site is powered by the FastSearch plugin for Movable Type.

Blogrolls on this site are powered by the MT-Blogroll.

Temporary site design is based on Cutline and Cutline for MT. Graphics by Apothegm Designs.

Author Login



Terms Of Service

DCMA Compliance Notice

Privacy Policy