Hiding the Decline: What Polls Over-Sampling Democrats Mask

The over-sampling of Democrats in today’s polls most likely hides a sharp decline in support for President Obama among White voters. If President Obama’s support level among White voters dips a single percent or two below 40, his road to re-election would be in jeopardy. The national polling results today showing President Obama with support levels among Whites between 40-44% likely over-sample support for President Obama by 4% to 8% among this demographic. Poll re-weighting by race achieves an accurate demographic make-up for the United States in 2012 but almost certainly a wholly unrealistic split between self-identified Democrats and Republicans. Because the accurate re-weighting of polls by race often achieves political splits that are not credible, polling organizations give rise to accusations of bias when in reality better selected sample inputs would most likely achieve more credible end results but also meaningfully worse results for the President.

Problems with polls

The majority of polling critiques this election cycle focus almost exclusively on the amount of Democrats versus Republicans surveyed with the observation invariably there are far too many Democrats in the sample. There is much in dispute around this complaint because most polling organizations do not weight polls by the party identification of respondents. Polling organizations argue the disproportionately high amount of Democrats sampled draws a sharp inference there are more Democrats in the overall electorate, not just in the sample size. While it is possible and even probable there are a few more self-identified Democrats in the American electorate (the average in elections since 1984 is 3% more Democrats), the great dispute is the unusually large disparity of Democrats showing up in today’s polls, often as much as 7 to 12% higher than Republicans among the respondents. There are many reasons to challenge this conclusion which I will discuss later, but if we assume these polls have too many Democrats, an interesting phenomenon appears among which Democrats are oversampled.

Most polling methodologies, including how polls are weighted once responses are collected, mirror the Gallup Organization who has been the standard bearer in the US for over 75 years. According to the organization, “After Gallup collects and processes survey data, each respondent is assigned a weight so that the demographic characteristics of the total weighted sample of respondents match the latest estimates of the demographic characteristics of the adult population available from the U.S. Census Bureau. Gallup weights data to census estimates for gender, race, age, educational attainment, and region.” Based on explanations like this there is little reason to suspect intentional political bias in the disparate party weighting, especially when they do not re-weight polls by party identification. Importantly, though, they do re-weight polls by race. This gives rise to some curious issues regarding support levels for the President today.

Racial demographics and voting preference in the US

In the 2008 election, the racial breakdown of the national voting public was 74% White, 12% Black, 9% Hispanic, 2% Asian, 3% Other. When a survey is conducted polling organization re-weight the respondent answers to ensure the each of these groups has accurate representation in the final results. Most national polls reflect this reality usually within a 1% variation for any group.

If you look how each one of these groups vote, you find outsized rates of support for Obama among the non-White groups: Blacks ~95%, Hispanics ~70, Asians ~65%. These levels of support for Democrats are consistent with most modern elections although President Obama has been able to boost these levels slightly above historic averages. In aggregate, non-White support for Obama is roughly 80% in nearly every survey. At the same time Obama, like Democrat Presidential candidates before him, struggles with the White vote. In these same polls, Obama typically averages 40-44% support among White voters. His 2008 support level was 43% and it is widely believed by the Obama campaign among others that he needs support of at least 40% Whites to win the election.

Low potential for over-sampling non-White support for Obama

If we consider the idea that polling today has large over-samples of Democrats, the consistently high percentage of support for Obama among non-Whites makes it almost impossible to over-sample minority groups. First there is not a lot of room for support increases and second, data on the voting trends in non-White groups is often achieved through demographic specific polling of solely Blacks or Hispanics for example. Hence, any over-samples in the non-White demographic would meaningfully alter the already high levels of support for Obama and reveal itself as inconsistent with independent polling. Additionally, any over-samples in the non-White demographic would almost certainly change the racial make-up of the survey and set off red-flags to anyone scrutinizing polls. Therefore it is highly unlikely over-sampled Democrat polls contain an excess amount of non-White voters.

White Democrats

This leaves only White Democrats as the over-represented respondent in these polls that arguably over-sample Democrats. If the average in election turnout since 1984 is 3% more Democrats and these polls have 7 to 11% more Democrats, that means the polls specifically have 4 to 8% more White Democrats surveyed in their likely voter results. The problem for the Obama campaign is if his support level among White voters (74% of the voting public) is between 40%-44% and that support is based on a sampling that over-states his support 4 to 8%, his real level of support is probably closer to 36% or 37%. This is meaningfully below the campaign’s own magic level of 40% and is a huge danger zone for any Presidential candidate no matter how much anyone may spin the demographic changes in today’s America.

Hiding the decline

The issue with the suspect polling internals and media embrace of the figures is the consistent lead for Obama would be immediately challenged if his support levels dropped dramatically among the outlined racial groups. Support levels of 60% among Hispanics (9% of the voting public) or 80% among Blacks (12% of the public) would jump off the page to poll watchers. The same holds true for support levels of 36/37% among Whites (74% of the voting public). It would be near impossible for Obama to win the Presidency with support levels like the ones I just outlined. Unfortunately support for President Obama among White voters has declined from 43% in 2008 to apparently as low as 36%-37% in today’s polls absent unrealistically high levels of self-identified Democrats. With White voters making up 73-74% of the electorate and support levels in the upper 30s, it is inconceivable President Obama has the advantage these polls lead readers to believe. But the results largely go unchallenged in the media despite the impractical internal party identification make-up.

Polling bias and Party identification

When we reflect on accusations of bias in polling based on party identification, it seems hard to justify when most organizations do not adjust their polls based on this metric. These organizations do, however, run the risk of confirmation bias where the media and polling firms have a predilection towards one candidate and upon achieving results they agree with fail to challenge outlier data like unrealistic Democrat turnout levels in 2012. Inconvenient poll compositions like the fantastical party identification of respondents shake the credibility of desired outcomes but no explanation is given for such oddities. This leaves more fair-minded poll watchers uneasy with the factual reporting on data with obvious internal issues while partisans react more strongly with bias accusations not substantiated based on the available data. The over-sampling of Democrats may not be showing the bias of polling organizations but it is likely hiding the decline of dwindling White support for Obama.

This only raises the question of where the polling firms are getting their samples from — possibly heavy Democrat districts — because the end results are party identification breakdowns unrealistic in today’s electorate. In 2008 seven percent more Democrats than Republicans identified themselves as such on election day, well above the historic average of 3%. This was a big change from 2004 when party identification was evenly split between the Democrats and Republicans. But there were many reasons for the strong Democrat turnout that do not exist today. The top of the ticket was a historic candidate (first Black President), America had war and Bush fatigue, the financial meltdown created an anti-Republican wave, and his opponent wasn’t the strongest (good biography, bad and underfunded candidate). These factors led to a strong Democrat self-identification advantage at the voting booth in 2008. But in the 2012 election, none of the advantages outlined above are there for Obama and many of those factors are now largely working against the President: 8%+ unemployment for three years, sub-2% GDP, 23 million unemployed, Arab Spring blowing up and casting the historic vote in 2008 is yesterday’s news. Additionally the Romney campaign ground game has exceeded the McCain campaign across many metrics as much as 10- to 15-fold.

Despite the stark changes in each of these factors, polling outfits thus far have consistently sampled an election turnout often greater than candidate Obama’s 2008 best-in-a-generation advantage.

That means something else is going on. But the polling organizations shrug their shoulders and have been found to say the losers in the results are just crying sour grapes. This is even though their sample outcomes have party identification splits unrealistic beyond any stretch of reason. Sadly no credible defense is given for the unusual party split in these results which gives rise to charges of bias whether intentional or accidental. If the polling firms believe today’s electorate will exceed the incredible 2008 advantage Obama achieved they should make the argument to justify results that contain suspect internal data. But they would also have to explain why the 2008 election gave Democrats massive majorities in the House of Representatives yet today’s electorate will likely return massive majorities in the House to Republicans. It defies all logic. But very likely due to “confirmation bias” the media and polling organizations report favorable results for President Obama without challenge.

There are many explanations for odd internal data in polls as well as the built in accuracy issues that come with the very nature of polling. As Michael Barone writes, “it’s getting much harder for pollsters to get people to respond to interviews. The Pew Research Center reports that it’s getting only 9 percent of the people it contacts to respond to its questions. That’s compared with 36 percent in 1997.” But consistently unrealistic sample outputs give rise to greater scrutiny from the polling outfits and media organizations who report the results uncritically for whatever their reasons may be.

25 Comments

  1. No Tribe
    Posted October 1, 2012 at 1:27 pm | Permalink | Reply

    Romney leads by 4 among Independents in the Battleground poll today. Has there ever been a President elected whose not won the Independent vote?

  2. John Smith
    Posted October 1, 2012 at 1:48 pm | Permalink | Reply

    Pollsters deliberately oversample Democrats for years then act surprised when people stop answering

  3. No Tribe
    Posted October 1, 2012 at 2:04 pm | Permalink | Reply

    Oh my, here’s a beauty in Pennsylvania:

    “As written, the law says voters who do not bring proper photo ID on Election Day can cast a provisional ballot. They would then have six days to bring in the required photo ID for their votes to count.”

    I can imagine a close election, where a few votes separate, maybe a few thousand, and there are six days to get those votes counted.

    http://articles.philly.com/2012-09-29/news/34149464_1_voter-id-law-id-on-election-day-disenfranchise

  4. Posted October 1, 2012 at 2:04 pm | Permalink | Reply

    no president has won with a gallup approval rating under 50%. No presdient has won with a Mid September Gallup approval rating under 50%. No president has won without carrying the independents by at least 50.1%
    No president since FDR has won with unemployment rate above 8%.

    If Obama wins re-election, this election will be, in many eyes, far more historic and game changing than four years ago. As it will signify that for the first time the American people will have doubled down on a president the majority does not believe is doing a good job.

    • Ranger375
      Posted October 1, 2012 at 2:47 pm | Permalink | Reply

      There is no doubt Obama has made history before – none of it to be proud of.

      I hope it doesn’t go against history with this election.

      We have enough of his history to live with now.

  5. Posted October 1, 2012 at 2:14 pm | Permalink | Reply

    Sorry about the switch in title. I looked at the title for countless hours and knew something was “off” but of course it wasn’t until I actually “published” it that I realized the word Reveal was the opposite of what I meant. My bad. Thanks for visiting.

  6. Tim
    Posted October 1, 2012 at 3:27 pm | Permalink | Reply

    I know you don’t blog PPP polls, but their latest North Carolina poll is laughable (and desperate). They oversample Democrats +5%, and undersample independents -6%, but they conclude that Romney is keeping it close because he’s winning independents by 54-38 (16 points!). LOL. Pathetic!

    • Posted October 1, 2012 at 3:48 pm | Permalink | Reply

      that’s funny. Typical advocacy polling from PPP.

      • Posted October 1, 2012 at 3:53 pm | Permalink

        Im waiting for the PPP poll that shows statewide Romney leads 52% – 48% among all voters but Obama is up a whopping eleventy billion.

      • Posted October 1, 2012 at 4:04 pm | Permalink

        PPP is out of Durham, North Carolina

  7. Posted October 1, 2012 at 3:41 pm | Permalink | Reply

    Call me mathmatically nuts but the only ways that Romney leads independents by 16 and doesn’t win the state are 1) you have a massive number of democrats over republicans and/or 2) Obama is pulling a good share of republican voters on top of his democrat voters but not pulling independents? That doesn’t seem to be logical.

    • Posted October 1, 2012 at 4:01 pm | Permalink | Reply

      All the polls show Romney’s GOP support is higher than 0bama’s Dem support.

      • Posted October 1, 2012 at 4:16 pm | Permalink

        PPP Poll for North Carolina has a D+14 (48% D, 34% R, 18% Ind) and they show it tied. Wow they will go to great lengths to make sure Obama is not down in any state he won last time. Surprised they have up Indiana without some skew showing him up 1 with a D+99 poll 🙂

  8. Pete
    Posted October 1, 2012 at 3:56 pm | Permalink | Reply

    1. RCP Job Approval On This Date:
    10.01.04: Bush 52.8% Appv, 45% Dissapv
    10.01.08: Obama 48.7% Appv, 47.8 Dissapv

    BTW, W got 51%. Just sayin.

  9. geoffrey faust
    Posted October 1, 2012 at 8:12 pm | Permalink | Reply

    Is this also how Gallup’s 2 tracking polls can show Obama with a higher percentage head-to-head over Romney among “registered voters” than Obama’s % job approval among “adults”? Which otherwise would seem counter-intuitive….

    • AussieMarcus
      Posted October 2, 2012 at 12:23 am | Permalink | Reply

      The head-to-head is a 7 day tracking while the Approval is only 3 days, I think.

      Last week Gallup went screwy, with Obama’s approval going from tied to +9 in a day, and the head-to-head going from a tie to O+6-7. Whether it was a screwy sample or some delayed reaction to the 47% quote, who knows? But 7 day the head-to-heads will still have these Obama-friendly days in there, whereas the 3 day approval will have seen those days wash out.

  10. M.Remmerde
    Posted October 1, 2012 at 10:33 pm | Permalink | Reply

    Anyone else noticing these likely voter percentages in these polls are wildly optimistic?

    Looking at 2008 overall turnout:
    (from http://uselectionatlas.org/RESULTS/data.php?year=2008&datatype=national&def=vto&f=1&off=0&elect=0)

    National turnout as a percentage of registered voters: 74.4%
    Just for comparison, the other recent presidential years (also from uselectionatlas.org):
    2004: 72.9%
    2000: 67.1%
    1996: 66.4%
    1992: 78.1%
    1988: 72.5%
    1984: 74.6%
    1980: 76.5%

    Looking at the latest polls that have the interview breakdown (omitting the ones that don’t publish LV & RV count, which unfortunately, is most of them):
    (from http://realclearpolitics.com/epolls/latest_polls/)

    CNN/ORC 10/1: (O 50/R 47) – 783 LV / 883 RV = 88.6%
    ABC WaPo 10/1: (O 49/R 47) – 813 LV / 929 RV = 87.5%
    Fox News 9/27: (O 48/R 43) – 1092 LV / 1208 RV = 90.4%
    NBC/WSJ 9/17: (O 50/R 45) – 736 LV / 900 RV = 81.8%

    Again, 2008 turnout/registered voters was 74.4%.

    Now these below only had Likely vs Voting Age (adults) breakdown. The comparable 2008 national turnout as a percentage of adults: 58.3%
    Bloomberg 9/25L (O 49/R 43) – 789 LV / 1007 Adults = 78.4%
    Reason-Rupe 9/21: (O 52/R 45) – 787 LV / 1006 Adults = 78.4%

    And again, the 2008 turnout/adults was 58.3%.

    So what few pollsters that are willing to show us the number are assuming 2012 is completely obliterate the high water turnout of recent history. Hmm. Good luck with that.

    And going a little further into how these pollsters are divining “likely”, you have to wonder if 2008 has polluted that “likely voter” model. There were a lot of first time (i.e. unreliable this time) voters who turned out in 2008. And in most pollsters “likely” filtering methodology, the answer to the question “Did you vote in 2008?” will carry a lot of weight. And that is going to put a lot of first time Obama (and I am speculating one-time Obama voters) into this likely model.

    On the other side of it, you may have a subset of reliable Republican voters who sat out 2008. Whether it was lack of enthusiasm for McCain, or Bush fatigue, or the simple fact that it appeared all but hopeless for McCain by the time election day arrived – I think there could be a fair number of very motivated Romney voters who are getting washed out of the “likely” filter simply because they would have to honestly answer no to the “Did you vote in 2008?” question.

    • Posted October 1, 2012 at 10:49 pm | Permalink | Reply

      I’m not sure those figures are correct. The generally accepted source for the data is the Current Population Survey (CPS) from the Census Bureau: http://elections.gmu.edu/CPS_2008.html

      In 2008 the percentage of voters versus eligible adults was 63.6%. The percentage of voters versus registered voters was 89.6%
      In 2004, the percentage of voters versus eligible adults was 63.8%. The percentage of voters versus registered voters was 88.5%

      It would appear the current polling is properly screening likely voters from their registered voter sample based on the CPS data.

      Good write-up, unfortunately I think you were given bad source data.

      • M.Remmerde
        Posted October 1, 2012 at 11:47 pm | Permalink

        Thanks Keith, but you’ve only polluted by brain further here… 🙂

        From http://elections.gmu.edu/Registration_2008G.html
        2008 Total Voter Registration = 186,983,927

        From http://elections.gmu.edu/Turnout_2008G.html
        *2008 Total Turnout = 132,653,958

        = 70.94% turnout as a percentage of registered voters.

        [* – I see three missing states in the McDonald 2008 turnout table – CT, MS, TX – but I don’t know if that means they aren’t in the 132 million number. But in any case, the 132m is in line with the census 131m self-reported.]

        So the total number of registered voters nationally (in 2008) is off somewhere.

        Is there some problem with the census numbers *on registration alone* because it is self-reported? Or what I am missing here?

      • Posted October 1, 2012 at 11:59 pm | Permalink

        I’m going to have to take a closer look at this. I relied on the Pew Research Study from April 2009 (who used the CPS data) when there have been multiple updates and corrections to those figures. I’ll have to look a little deeper but there is something curious about the 187 million voter registration # you quote. And the 146 million number Pew quotes. I can understand nominal tweaks to the #s but 41 million? I’m not sure we’re comparing apples to apples here.

      • Posted October 2, 2012 at 12:00 am | Permalink

        Either way, good digging by you. Thanks

  11. Posted October 2, 2012 at 11:16 am | Permalink | Reply

    Just read an article by the editor in chief of Gallup who basically, in a very polite, way says we are off base looking at the party ID. But does say that observers of polls should not look at them as sinister plots but instead look at the ballot. Such as Ohio. You know Obama won in 2008 by 5 points, Bush by 2 and 3 (04-00) when a polls shows Obama up by 10…should you consider that a logical outcome, no. So he is advocating for the fact Party ID is not a valid way to look at it, yes those numbers change over time but also use logic. If Obama is up 10 in a state he carried only by 5 during the height of his popularity then you as an oberver can say that poll is probably not accurate.

    Rasmussen told Byron York the other day that he is prediciting D+3 and that history says the final weeks almost always break against the incumbent (history can be broken) and it all depends on how far up the incumbent is and as to how much the challenger can travel. I think by tomorrow Ras will have us dead tied, Gallup will be at 2 points and this debate will set the tone. I think whomever the American people think won the debate you will see poll numbers start moving toward that person and not stop until election day.

  12. Spiked Gallup
    Posted October 3, 2012 at 10:59 pm | Permalink | Reply

    Check Gallup’s Tracking poll data on Sep 7, Sep 14 and Sep 25.

    By using some mathematical inferring, you will note how Gallup’s 3 point jump towards Obama in the tracking poll for Sep 7 requires an unbelievable Obama lead of roughly 21 points on Sep 7.

    Use that to see if the Sep 14 data is possible without a very unusual spike on Sep 14.

    Then look at Sep 25 and try and explain that without a spike.

    Has Gallup been pressured to periodically spike its polls for Obama?

  13. Posted October 18, 2012 at 3:36 pm | Permalink | Reply

    For a look at the re-weighted polls based on a variety of models including 2004, 2008 and 2010 elections, visit http://www.insidepolling.com. You can find re-weighted national and state level polls along with electoral vote projections.

  14. ken
    Posted October 31, 2012 at 12:44 pm | Permalink | Reply

    If you look at the Ras poll only, you will find that obama and romney are tied 261 to 261, and WI, IA are the states in play.

8 Trackbacks

  1. […] (Excerpt) Read more at battlegroundwatch.com […]

  2. […] Read More… Share This! Share This! […]

  3. […] tougher road ahead than the media and recent polling would lead readers to believe. Consistent with my essay from yesterday, earlier national polls were overstating Obama’s support among White voters.  Interestingly […]

  4. […] IPO sold before November 6 because underneath this absurd racial make-up is a dwindling support for Obama among White voters likely to doom his re-election chances.  And if Obama has any more debates like his last, […]

  5. […] polls in 2012 will be superior to their advantage in 2008. Here is what I wrote on October 1st when critiquing the  large disparities party identification: In 2008 seven percent more Democrats than Republicans identified themselves as such on election […]

  6. […] explain why their sampling is often equally erroneous.  I have explained the problem many times on this blog but in the linked interview I screwed up and made it seem like every polling firm weights by party […]

  7. […] composition is correct, the Democrat over-sampling in polls like today’s D +9 means they are over-sampling White Democrats which hides the decline in support for Obama among White voters.  Now the polling outfits are […]

  8. […] Romney lead with whites (55 percent to 38 percent)– Here we are below the magic 40% mark which is the danger zone for Obama.  But again, you already knew that […]

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: