Skip to main content

Nobody who follows US politics is unaware of the accusations of bias in the pollster Rasmussen.  Neither can anyone be unaware of the logic behind such accusations.  Yet still, Scott Rasmussen’s apparently tireless work for the RNC continues to do its damage through the media who fail to understand how insidious manipulated polls can be.

Here’s a couple examples of Rasmussen polling’s evident blindness to reality.

●   In the final weeks of the 2010 governor’s race in California, Rasmussen’s results suggested, using more polling “data” than anyone else, that the race was a toss-up.  Right up to until Election Day, Rasmussen flooded the media with the view that Meg Whitman was going to pull off one of the greatest upsets in US voting history.  So what actually happened when voters went to the polls?  Whitman lost to Jerry Brown by 13 points.  This is despite the $140,000,000 of her own money she used to lather the airwaves with advertising.  This was not a “close race” or “tossup”—it was a slaughter.

●   Rasmussen also had an apparently out-of-thin-air rosy view of Sharron Angle’s Senate candidacy the same year in Nevada.  If he had set out to stir the chattering classes to accept the possibility of Harry Reid’s defeat, he sure got that to happen.  Press organs from coast to coast were all eager to participate in the “scoop” of Harry Reid, the Majority Leader of the US Senate, losing his seat.  Yet once again, Rasmussen’s polling proved to be entirely off the rails.  Reid beat Angle 51% to 44%.  Not even close.

So how is it that Rasmussen, with his dismal track record, continues to make such a stir in the media?  Well, the problem lies with scientific poll trackers such as Nate Silver at 538.com.  Silver will agonize in print over the possibility that Rasmussen is deliberately biased, yet Silver will continue to use all Rasmussen’s results in his aggregate polling figures, which throws everything out of balance.  Here’s how the dirty work gets done.

Rasmussen’s polls, being automated “robocalls”, constitute a huge fraction of the aggregate polling data for any period of time.  No outfit comes anywhere near producing the number of polls he does.  So anyone doing an aggregate of all polls over a, say, one week period will find much more data from Rasmussen than anyone else.

Let’s look at a scenario.  Let’s suppose there are four major pollsters producing data for an election cycle, Pollster A, B, C, and D.  Pollster A produces two polls within a two week period leading up to an election, Pollsters B and C each produce one poll, and Pollster D produces five polls.  Here’s a schematic of their results:

              Candidate #1          Candidate #2
Pollster A         50%                 47%
Pollster A         51%                 47%
Pollster B         49%                 48%
Pollster C         53%                 43%
Pollster D         42%                 49%
Pollster D         44%                 50%
Pollster D          43%                 50%
Pollster D         41%                 49%
Pollster D         42%                 48%       

So even though three pollsters show Candidate #1 with a substantial lead (50.75% to 46.25%), an aggregate of all polling done, including the 5 polls from the only pollster who shows Candidate #1 losing, is that Candidate #2 is ahead by roughly 48% to 46%.  Not only does this skew the actual support between the candidates, it causes Pollsters A, B, and C to wonder if their methodology is somehow wrong, and in many cases they adjust their future results to better conform to this aggregate figure.

The simple way to cure this “flood-polling bias” would be to take aggregate results from each pollster and only then aggregate the totals.  The numbers would then look like this:

              Candidate #1          Candidate #2
Pollster A         50.5%             47%
Pollster B         49%                 48%
Pollster C         53%                 43%
Pollster D         42%                 48%                               

Then the true aggregate would be: Candidate #1 49%, Candidate #2 46.5%.  The bias from Pollster D would still taint the overall result, but not so drastically as to forcefully misrepresent the actual relative strength of the two candidates.

EMAIL TO A FRIEND X
Your Email has been sent.
You must add at least one tag to this diary before publishing it.

Add keywords that describe this diary. Separate multiple keywords with commas.
Tagging tips - Search For Tags - Browse For Tags

?

More Tagging tips:

A tag is a way to search for this diary. If someone is searching for "Barack Obama," is this a diary they'd be trying to find?

Use a person's full name, without any title. Senator Obama may become President Obama, and Michelle Obama might run for office.

If your diary covers an election or elected official, use election tags, which are generally the state abbreviation followed by the office. CA-01 is the first district House seat. CA-Sen covers both senate races. NY-GOV covers the New York governor's race.

Tags do not compound: that is, "education reform" is a completely different tag from "education". A tag like "reform" alone is probably not meaningful.

Consider if one or more of these tags fits your diary: Civil Rights, Community, Congress, Culture, Economy, Education, Elections, Energy, Environment, Health Care, International, Labor, Law, Media, Meta, National Security, Science, Transportation, or White House. If your diary is specific to a state, consider adding the state (California, Texas, etc). Keep in mind, though, that there are many wonderful and important diaries that don't fit in any of these tags. Don't worry if yours doesn't.

You can add a private note to this diary when hotlisting it:
Are you sure you want to remove this diary from your hotlist?
Are you sure you want to remove your recommendation? You can only recommend a diary once, so you will not be able to re-recommend it afterwards.
Rescue this diary, and add a note:
Are you sure you want to remove this diary from Rescue?
Choose where to republish this diary. The diary will be added to the queue for that group. Publish it from the queue to make it appear.

You must be a member of a group to use this feature.

Add a quick update to your diary without changing the diary itself:
Are you sure you want to remove this diary?
(The diary will be removed from the site and returned to your drafts for further editing.)
(The diary will be removed.)
Are you sure you want to save these changes to the published diary?

Comment Preferences

  •  Tip Jar (8+ / 0-)

    "The best lack all conviction, while the worst
    Are full of passionate intensity." --W. B. Yeats

    by Pragmatus on Fri Mar 16, 2012 at 05:13:29 PM PDT

  •  Repubs cook the books (2+ / 0-)
    Recommended by:
    judyms9, Redfire

    it's their real religion.. all the Christianist hoke is just a front.

    This Rover crossed over.. Willie Nelson

    by Karl Rover on Fri Mar 16, 2012 at 05:22:11 PM PDT

  •  I still remember a 2009 question from a Rasmussen (1+ / 0-)
    Recommended by:
    True North

    pollster on the phone;  "If President Obama was hosting your 7 year old daughter's Brownie Troop behind closed doors in the Oval Office and she emerged 5 minutes later in tears, would you still support his Health Care Reform?"

    I mean, come on!

    "I'd like to thank spiritplumber and LieparDestin for fixing oopsaDaisy's computer who can tip, recc, and hotlist now. I tried but couldn't do it despite her constantly foulmouthing me, so thanks U two." -God

    by oopsaDaisy on Fri Mar 16, 2012 at 05:37:24 PM PDT

  •  Great overview & great suggestion at the end-- (1+ / 0-)
    Recommended by:
    Pragmatus

    would at least lessen the toxic disinformation sludge.  

    I don't know what's the matter with Nate, who can mount a totally lucid and devastating critique of Ras but then succumbs to the sludge anyway.  But then we're doing the same thing on this site.  It's like, everyone was finally able to decide that Fox was disinformational, and just approach them that way, but because Rasmussen involves numbers, we're afraid of being anti-science or something...?

  •  It's worse than that (1+ / 0-)
    Recommended by:
    Pragmatus

    Come election time, many of the major news outlets and some websites (my favorite being electoral-vote.com) all track the electoral college state polls.

    With trash like Rasmussen and Fox who are out to deliberately skew polling results, those polls game the system (except the most savvy) to prop up their guys at the expense of the Dems.

    So, you say, it's just a poll?

    Not so! Many fundraisers look at these polls to judge whether the worthiness of their potential investment. Show one guy as being way out ahead, and chances are, the other guy's fundraising will dry up making the polls a self-fulfilling prophecy.

    Everyone likes a winner, too, so that also skews the eventual results.

    Especially this cycle, with a baker's dozen polls out every day, the integrity of the pollsters is more important than ever. Thank goodness we have PPP, but we need more to counteract the forces of evil, or we need to minimize their validity.

    What separates us, divides us, and diminishes the human spirit.

    by equern on Fri Mar 16, 2012 at 08:01:32 PM PDT

    •  I agree with your central point (0+ / 0-)

      ...that it has become a cesspool.  Half the "pollsters" operating are pushing an agenda, leaving even savvy voters unsure what is really going on.

      "The best lack all conviction, while the worst
      Are full of passionate intensity." --W. B. Yeats

      by Pragmatus on Fri Mar 16, 2012 at 09:49:16 PM PDT

      [ Parent ]

  •  Could it be (0+ / 0-)

    that these biased polls sometimes have the opposite result from the one intended?  For instance, could it be that some Democrats in Nevada who weren't inclined to be bothered with voting saw the (false) poll numbers for Sharon Angle and decided they had better get out and vote?  Is it possible that these polls created some alarm among Democrats and encouraged more of them to vote?

  •  Just say no? (0+ / 0-)

    Clicking on your diary, I thought it was going to be a totally different suggestion.  A way we could all fight back!  I once took a Rasmussen poll, and was glad to do so, knowing how biased they are and feeling that at least they would get one very liberal respondent.  But perhaps this is the wrong attitude all together.  Pollsters who are not legitimate should not be responded to at all.  If we BOYCOTT such pollsters they couldn't continue to have any sort of legitimate results.  All their results would be skewed.  I would think that anyone who is interested in fair and objective polling would be supportive of this, not just liberals...and any liberal pollsters who play the same games should be blacklisted also.  

  •  There are some questionable assertions made (0+ / 0-)

    First, I should say that I agree, Ras' numbers are out of whack far too often and that they do carpet-bomb their data to try and develop a story. (Though converging to the mean as the race nears the end).
    I also agree that weighting the data more carefully would mute their impact on driving a story.

    That said, there are some fairly questionable assertions made in this dairy.

    Here is one on the upshot of too much Ras in your data stew:

    Not only does this skew the actual support between the candidates, it causes Pollsters A, B, and C to wonder if their methodology is somehow wrong, and in many cases they adjust their future results to better conform to this aggregate figure.
    Er, nowhere is there any evidence presented to support this conclusion. If it were true you would see instances of other regularly polling outfits (someone like say PPP) trending their data toward Ras as the mean. But that does not happen.

    There is another concerning Ras and Nevada Angle vs. Reid - several polls, not just Ras were, early in the contest positing a close race or a defeat for Reid. It was only later after Reid went totally nuclear in depicting accurately Angle's weirdness that the numbers turned around for him. Yes, Ras was off early on vs. the final result - but they were not alone in this. Yes, Ras was off in the final analysis - and in that they might have had less company.

    Lastly, I don't think it is fair to assign to 538.com full and total responsibility for the rest of the media lapping up Ras' data dumps. Perhaps he could do a second analysis as you suggest in which the quantity of data is re-weighted - but his current approach is at least self-consistent. Also, Silver has regularly taken a position that Ras is out of kilter, has a strong house effect, early in races. So it is not as if he isn't stating honestly his evaluation of Ras - perhaps he just is not using sufficiently virulent language to characterize them to your liking?

    •  I'll start with your last paragraph. (0+ / 0-)

      It is immaterial whether Nate Silver recognizes a pro-GOP bias in Rasmussen, and opines about it at length, if he then continues to derive his medians using all Rasmussen's data.  The "virulence" of Silver's remarks makes no difference, or whether he says anything at all, or even praises Rasmussen as the soul of impartiality.  What matters is that he willingly takes one poll from four different pollsters and five from Rasmussen and then averages them all together.  Old principle at work here--garbage in, garbage out.  

      Also, you need to read in depth about methodology.  Every pollster adjusts his/her numbers based on perceived unintended slants in the raw data.  Nate Silver has even described at length how some pollsters, seeing large effects in others' work their numbers don't capture, and fearful that their adjustments were wrong, recalibrate how they stew their raw data to come up with final figures more in line with everybody else (i.e. Rasmussen).  If you disagree with this your argument is with Nate Silver, not me.  Nobody who does polling simply totes up the columns of raw data then publishes the sums.  Every poll has been adjusted in one fashion or another--it's simply the way it is done.

      "The best lack all conviction, while the worst
      Are full of passionate intensity." --W. B. Yeats

      by Pragmatus on Sat Mar 17, 2012 at 11:35:26 PM PDT

      [ Parent ]

  •  Never trust a Republican poll cat (0+ / 0-)

    A more reliable poll is  a poll that only include minorities , they can add at least 5 to 10 percent to particular party or candidate ,  White  voters are usually   a statistical tie ,who polls well with minorities will usually win any close election , http://n.pr/...

  •  Polls that will doom Romney and other Republican (0+ / 0-)

Subscribe or Donate to support Daily Kos.

Click here for the mobile view of the site