Oct 26 2008

Bi-Poller Part II

Published by at 10:59 am under 2008 Elections,All General Discussions

Reader Frogg passed along this really interesting commentary from a professional pollster who is (a) a die hard Obama supporter and (b) laughing at the public polls:

I was having dinner a night ago with a friend of mine who is a statistician for a well-regarded private polling company. They do some work for Republicans in California, but most of the work they do is for Democrats or Democrat-leaning operations (Unions, etc.). Anyway, her shop was retained to do a few Presidential polls for targetted states on behalf of a union so the union could decide where to spend their ad dollars for the last week. They did Ohio, Florida, North Carolina, New Hampshire, Pennsylvania, Colorado, New Mexico, Nevada and Missouri. After mocking the hell out of the voter id spreads used by Rassmussen, Zogby, etc. (and this is coming from a committed Dem who will be voting for Barry O) she said the results of their polling lead her to believe that McCain will definitely win FL, OH, NC, MO and NV. She says Obama definitely wins New Mexico. She said that Colorado and New Hampshire were absolute dead heats. She said she thinks there is a 55% chance Obama holds on in Pennsylvania and a 75% chance McCain wins Virginia. She absolutely laughed at the public polls showing Obama leading Virginia–and pointed out that all of those polls rely on Dem turnout being +4 and as much as +7, when in 2006, Republicans actually had the advantage by +3. She also pointed out that the numbers for Obama in SWVA look absolutely awful and that McCain is running 10 points better then Allen did in NoVa.

Anyway, her companies conclusion is that the election will come down to Colorado, New Hampshire and the Republican leaning district in Maine, which in her opinion might very well decide the Presidency (apparently the district in Nebraska that Obama thought he might be able to get is now off the table). She said she has very little doubt that the public polling is part of a “concerted voter suppression effort” by the MSM. She said IBD/TIPP was the only outfit doing public polling that was “worth a bucket of warm piss”.

Emphasis mine.  The turnout model scam of 2008 will be the big story of this election. In my last post on polls I noted how many of the polls out there are starting to fall into two camps. The first camp is the traditional approach using historic turnout models where party affiliation is actually quite close as both sides turn out their base equally well. The second model is new and unverified, and assumes there will be a huge difference in party affiliation turnout this year.

The first class of polls show a very tight race, the second class are so heavily weighted towards the dems they assume all the anger with the direction of the country has no impact on Democrats and their media puppets. The DC/NY Political Industrial Complex is mostly liberal in its make up, and it has recently become more and more isolated in its echo chamber. Just look at how it reacted to Sarah Palin.  The end result is the polls of polls are showing a classic bimodal result with clusters of polls at one of these two modes: “traditional’ and “extended” – just like the two turnout models now being openly produced by Gallup.

I think this pollster has it about right.  LJStrata and DJStrata have been out doing the GOTV stuff this week and what they find here in our part of Northern Virginia is there are about equal numbers of Obama and McCain supporters, but the Obama supporters are more open, and the McCain supporters are a bit down because of the tilted polls. The GOP support is quiet, but just as massive as the Obama support.

Sadly, one of the better pollsters has gone to the dark side of the bimodal results.  Rasmussen has decided to increase his Democrat edge to new heights, under the naive assumption Dem and GOP supporters are equally engaged in answering pollsters:

Like all polling firms, Rasmussen Reports weights its data to reflect the population at large. Among other targets, Rasmussen Reports weights data by political party affiliation using a dynamic weighting process (see methodology).

The targets are not set arbitrarily. Rather, they are established based upon survey interviews with a separate sample of adults nationwide completed during the preceding six weeks. A total of 500 nightly interviews are conducted for a total of 21,000 interviews over the six week period.

While it sounds reasonable, the fact is willingness to participate in polls may not be uniform between the left and right. And pollsters are more and more considered part of the problem, part of the Political Industrial Complex which the public blames for the country being on the wrong track by 90+%. There is a ‘pox upon all your houses’ mentality in the country that is starting to lump the media, the pollsters, the consultants in with the politicians from both sides. Trust in the political class is gone.

Rassmussen now gives the dems a questionable 33-40 edge in turnout (Indies at 27).  Previously in September he had Rep-Dem-Indie (RDI) at 34-39-28. Each time he increased the dems edge McCain lost ground – duh!

Let’s look at the latest Newsweek Poll which has Obama up 12%. One look at the internals gives the answer to the large lead. Supposedly from 1204 interviews they distilled out 1092 Registered Voters, which were further distilled down to 882 Likely Voters. Of these they claim 299 Reps, 380 Dems and 381 Indies.

If we do the math the total sample size for party affiliates is 1060 – which cleverly doesn’t map to interviews, registered voters or likely voters. What is also interesting is they have error bars on their party ID?  They claim the Rep error bar is +/-7 (which comes out to 2%.) and the indie/dem error bar is +/- 6. Not sure why they are not sure what party people claimed they were associated with was in doubt, but there it is.

Anyway, if we do the math the Newsweek RDI turnout model is 28-36-36. Recall Rasmussen’s model was 33-40-27. I mean they are not even close! 

One of the problems is a lot of people are still on the fence to some degree and pollsters are trying to push them into a lean for one candidate, but this is very shaky ground to be on. Look at this Minnesota poll which is making people sit up and take notice:

A St. Cloud State University poll shows that Democratic presidential candidate Barack Obama leads Republican opponent John McCain 42 percent to 37 percent in Minnesota.

After earlier surveys showed DFL challenger Al Franken with an edge, the SCSU poll shows Republican U.S. Sen. Norm Coleman leading with 36 percent, compared with 27 percent for Franken. Independence Party candidate Dean Barkley trails with 16 percent.

Not only is McCain down only 5%, there are an enormous number of undecideds given the low numbers for both candidates. I included the surprise Senate seat race for comparison because it shows similar numbers for Coleman and Franken (with the Rep out fron), but there is a substantial number voting for a 3rd party candidate in that race. There is no major 3rd party candidate on the national level.  In MN and with this poll, the race is wide open because of the enormous number of uncommitted voters. Obama could easily lose this state if this poll is to be believed.

So what do we have? We have polls using dynamic turnout models which link willingness to take a poll to willingness to get out and vote (a very suspect assumption IMHO). Especially since different pollsters are deriving vastly different turnout models as a result of this approach. All these polls share one thing, they tend to show massive Obama leads, while the traditional turnout models show a tight or tightening race.

So let’s take a random snapshot of the RCP national polls and take a look at the bimodal (what I like to call Bi-Poller) nature of the polls out there.  I will be placing Rassmussen in the non-traditional pool of course. So let’s start there, with the ‘extended’ or highly doubtful polls.

Today we have in this group: Rasmussen Reports (Obama +8), Gallup (Expanded) (Obama +8), Newsweek (Obama +12), ABC News/Wash Post (Obama +9), CBS News/NY Times (Obama +13) and FOX News (Obama +9).

The average of these polls gives us an Obama lead of 8.4%. The interesting thing is I could look at the Obama lead in the poll and eyeball which polls were using turnout models which tilted to the dems. I of course checked the internals to make sure I was right and was surprised to only twice (Fox and Hotline, which I would have guessed would be in opposite camps).

Anyway, let’s now look at the ‘traditional’ model polls: Reuters/C-SPAN/Zogby (Obama +5), Gallup (Traditional) (Obama +7), Hotline/FD (Obama +7), IBD/TIPP (Obama +4) and GWU/Battleground (Obama +3).

The average of these polls is an Obama lead of 5.2%, which is a much closer race than the other fuzzy math polls indicate.II also want to note that the Reuters/Zogby poll has shown Obama’s lead be cut in half, going from +12 to +5 in a very short span of time. The reason I call the other polls fuzzy math is because I noted a wildly fluctuating range of party ID models.  The Rep-Dem-Indie (RDI) breakdown for the first set of polls above was interesting to see side by side:

  1. Rassmussen RDI: 34-39-28 (Dems +5)
  2. Newsweek RDI: 28-36-36 (Dems +8)
  3. ABC/WaPo RDI: 29-37-30 (Dems +8)
  4. CBS/NYT RDI: 28-40-31 (Dems +12)
  5. Fox RDI: 37-43-16 (Dems +6)

Let me be clear, only one turnout model will be right. That means all of these will be wrong, and maybe one will be close to right.  But the rest will be badly wrong given how much they diverge. For historical perspective here are the national numbers for 2000, 2004 and 2006:

  1. 2000 RDI: 35-39-27 (Dems +4)
  2. 2004 RDI: 37-37-26 (Dems +0)
  3. 2006 RDI: 36-38-26 (Dems +2)

Is this year’s election more like 2000 or 2006? I would state it is both and neither. It is a rejection election like 2006. But with Obama’s ticket heavy with DC and Political Industrial Complex insiders one wonders where the ‘change’ is going to come from. And if Palin is drawing a huge, quiet protest vote of her own with the Maverick McCain the Dems will not be seeing a massive +8% wave at the polls. They would be lucky to get a +2 like they did when they swept Congress in 2006. It was not that there were fewer Reps and conservatives voting in 2006, the fact was the same numbers were out but experimenting with moderate dems (which won the races).

To assume the nation will now go full liberal is quite a leap of fantasy in my mind. We have now conclusive evidence that polls are falling into the more traditional model and those built on irrational exuberance. We don’t know which group will be proven right until the election is over, but those built on historical data have a much better chance than those based on wild and unproven assumptions.

In the end the answer is turnout. If the GOP can mobilize like I have seen them mobilizing in the last few weeks, there will be a very stunned and shocked Political Industrial Complex come the morning after the election. And a very loud signal will have been sent to DC and NY and all the other elites who have led this country into a massive rut.

19 responses so far

19 Responses to “Bi-Poller Part II”

  1. Redteam says:

    I get most of my news coverage from the internet,which has to be filtered (by me), and Fox News which seems to be relatively neutral overall.
    Anyhow, I can hardly stand to watch or read much because of the obvious tilt in the polls(at least I hope it’s all tilt)
    So last night, I accidentally watch the weekend Geraldo show with him talking with Sean Hannity. Sean was making the point that character counted in a presidential candidate and that Obama’s relationship with Ayers, Wright, Rezko, etc was an indicator of a flaw in Obama’s character. Geraldo hoo hooed that, saying the only thing important, in this election, was the economy and that Obama was blowing McCain out on that subject alone.
    Well, if the economy were the only important subject, McCain should be ahead on that because he at least realizes that the new president can’t come in from day one and pile on new taxes and hi priced programs. Maybe it is becoming only a welfare state. But, to me, the character issue is very important and it’s not even close. Obama about zero and McCain toward the high end.
    How many times have I been polled? once.
    I don’t believe that just because a person is registered with a party makes it a certainty that person will vote that way. It may well be, but I question that. And it is not at all certain to me that all independents will vote in exactly the same proportion as those registered by party.
    If race were not a factor in this election and if the polls were neutral, I would predict McCain would be way ahead. We’ll see how it turns out.

  2. Terrye says:

    The polls are so strange this year. The latest Reuters/Zogby had Obama losing and McCain gaining 7 points in two days. That is just strange, people don’t change their minds that much that fast.

  3. Birdalone says:

    Terrye – polls can change this fast when there is so much soft support for Obama. Biden’s “international test”, Palin’s refound articulateness (and being a good sport for SNL), and even the MSM talking about super-majority P-O-R (two gas pedals, no brake) have all resonated this past week.

    Or maybe enough people have had enough exposure to Roland Martin on CNN and/or the terrible Obama attack ad on McCain’s “I am not Bush”. I am so sick of that one that I change the channel.

    and the realization that neither candidate can wave a magic wand and fix this economy.

  4. crosspatch says:

    There is no reason for anyone to be down about the polls. Look, in 2004 only about 53% of the population of voting age actually voted. If you can convince just one in ten Republicans to vote who were apathetic and were going to stay home, McCain wins.

    Voter participation can trump polls by TENS of points. The state doesn’t call you up on election day to collect your ballot, you must take time and go to the poll and stand in line, etc. If that 50% participation can be raised to 60% participation, Mac wins easily and all their “likely voter” demographics go out the window.

  5. […] Joe the plumber. Gallup is showing the same spread. For some very good optimistic poll analysis see AJ Strata. For pessimistic view points see Moderate […]

  6. Pondering polls…

    AJ Strata, continuing his musing over polls and whether they’re really accurate this year, passes on the following intriguing anecdote: I was having dinner a night ago with a friend of mine who is a statistician for a well-regarded private……

  7. djl130 says:

    Wow – thanks for reporting this! It is uplifting. After watching Stephanapolous today and Fox with Wallace – I was completely bummed. Really, all the news shows have Obama all tucked into his bed in the family quarters of the WH. Peggy Noonan made me want to barf. My husband and I just drove from NC to Wisc. We drove many back roads and really, there aren’t that many Obama signs. We have theory about the ‘undecideds’. They just do not want to say. I will bet the exot polls are very skewed. Also, look at the levels of early voters – very even, no blow out there for Obama. Keep up the good work!

  8. sjreidhead says:

    Thanks for the great post.

    A note from the wild west of New Mexico: Don’t count McCain out just yet. I’m seeing things here that are rather positive. I’ll be writing more about this on The Pink Flamingo sometime either today or tomorrow.

    The very real question is will the overwhelming support for John McCain in counties like Otero, Lincoln, and Chaves be enough to counter the Obama support in ABQ, Santa Fe, and up north.

    The media loves to talk about NM being a “swing state” because of 2000, but they never get the story right. McCain can count on maybe 45-50 support in the liberal areas of the state. BUT – in these 3 conservative counties his support is something perhaps 60%.

    Of course when dealing with New Mexico, none of this really matters. We’re always the last state to have the final results. There’s a very simple reason for this. It takes awhile to tinker in the cheating to get the results the Democrats want. It will take a good 2 weeks for a final NM count.

    The Pink Flamingo

  9. rayabacus says:

    Let’s even say that the “new” weighting model is correct for illustration purposes. What is not taken into consideration in any of this is the “PUMA” or disaffected Dem vote. Hillary commanded 18 million voters in the primary and if just one in four votes McCain/Palin they wipe out the edge in the uptick of party affiliations.

    I had hoped that Obama would win the Dem nomination because I believed that no one on the Rep side could defeat Hillary. I still believe that McCain is going to win 40 states and win in a landslide. I don’t believe Obama can win even 70% of the Dem vote and I believe that McCain will carry 95% of the Rep vote and over 50% of the Independent vote.

    As always, turnout will factor in.

  10. momdear1 says:

    They cooked the poll books in Kenya to make it look like Raila Odinga, Obama’s cousin and fellow tribe member, had a big lead, then, when Odinga lost by a wide margin, Odinga’s Muslim allies used the difference in the pol numbers and the elections numbers to go on a Jihad, murdering over 1,000 Non Muslims (Christians) , burning over 800 Christian churches, and leaving over 500,000 homeless. Obama raised over $1 million for Odinga’s campaign, sent his political advisers to Kenya to run Odinga’s campaign, and Obama has a designated Senate stafer who is his “connection” for constant contact with Odinga since the elected Kenyan President was forced to make Odinga Prime Minister. . . What makes any of you think they aren’t laying the ground work to do same thing here? We have already had Dem big wigs, including James Carville, warning of “unrest” and “civil unrest actions” if this election is “stolen” from Obama.. After all, the polls say he has a big lead. People are creatures of habit. If they did it in Kenya, they will do it here. Not only is Bill Ayers one of Obama’s neighbors, but Louis Faranan is also a neighbor. Can we expect “The Army” of Farakan’s Nation of Islam, The New Black Panthers, to lead this civil unrest and declare Jihad on white America? Don’t count it out. The New Black Panthers are well armed with AK47s and other modern equipment. This is just a word of warning. They did it in Kenya and the same people are laying the groundwork to do it here.

    We have already had terrorist attacks against McCain’s offices (molotav cocktails, threats, slashed tires, etc.) Secret service agents have been sent to call on people who respond negatively to Obama’s campaign callers, intense illegal investigations of anyone who appears to be publicly anti Obama like Joe the Plumber, and at least one news source has been the butt of censorship for asking questions everyone else is afraid to ask. . Does anyone see a pattern here? Do I fear these people being in control of government tax and law enforcement agencies. You Betcha!

  11. missy1 says:

    Reading through some of the bigger pro-Hillary blogs, the comments lead me to believe they may have made a decision to give polsters as well as exit polling, faulty information. There have been many, many comments like that in the several blogs I’ve been watching.

    In the comment section in Frogg’s contribution above, one commenter worried about riots caused by the incorrect information they are giving out, should Obama lose, and thought they better start giving out correct information.

  12. ivehadit says:

    momdear, you are right on the money. As I understand it, o was advising odinga, btw.

    There is definitely a groundwork being laid, especially for the cheating, imho. What I wonder is how the Secret Service and the FBI are handling all this. As far as I can see this o and his thugs would not pass one single security check for the White House. Am I wrong?

    I wish we could have a commercial with just this: an FBI agent being asked the question-Would o pass the security check?

  13. Frogg says:

    Stunning results in early voting in California. Smile redstaters

    Sunday, October 26, 2008 at 01:15PM CDT

    California has begun early voting already as well as mail-in balloting. The number of people who have gone in to vote in person has been extensive. The results so far prove what we had always suspected. The polls are being proven as totally unreliable. Although the results of early balloting have not been disclosed,of course,how many Republicans and how many Democrats have voted has been revealed.

    The results are simply shocking. The polls showed Barack Obama with an 18 point lead in California just a few days ago. The results thus far are the complete opposite. In the most liberal state in the entire country,the results are that 99,000 Republicans have voted and 96,000 Democrats voted. In the mail-in balloting the results so far are that 9,000 Democrats sent in their ballots and that 5,000 Republicans did so. So with nearly 210,000 people having voted,the Democrats have only a 1,000 vote advantage !


  14. Neo says:

    So AJ, would you go as far as to call, some of these “tilted” polls, a form of voter suppression ?

  15. AJStrata says:


    I would not call it voter suppression because I think Obama’s supporters are more likely to not vote if they feel he has it in the bag. There is a reason conservatives do better when we go from polls of ‘adults’ to ‘registered voters’ to ‘likely voters’ – conservatives vote. They take this seriously.

    I think Obama runs the bigger risk here. Honestly, I think they are believing their own Kool-Aid induced fantasies.

  16. […] Well, since I noticed there are two families of polls out there, and only one family will be proven right next Wednesday, I have decided to take the RCP average for the national polls and split it into the “traditional” poll of polls and the “extended” poll of polls. My original posts on what the difference is between the two families of polls are here and here. […]

  17. […] I noted in my posts on the Bi-Poller world of polls (here and here) if one groups polls by how they treat party affiliation in their final results into two categories […]

  18. […] For 10_29_08 The Nightly Bi-Poller Report For 10_28_08 The Nightly Bi-Poller Report For 10_27_08 Bi-Poller Part II […]