Exit Polls Lousy Predictors

Somebody, whether Drudge or some other site, will likely leak the election results sometime this afternoon.  While they’re impossible to ignore, you should do exactly that.

Rasmussen reminds us:

The bottom line is that in every state we polled–Colorado, Florida, Missouri, North Carolina, Ohio and Virginia– Democrats are a lot more eager to take exit polls than Republicans. In five of the six states, a majority of Democrats say they would be Very Likely to participate in the exit polling process. At the same time, in five of the six states, fewer than 40% of Republicans would be willing to do the same. In every state, Republicans are at least twice as likely as Democrats to say that they are not at all willing to take an exit poll.

Unaffiliated voters tend to align more closely to Republicans in all six states in both willingness and unwillingness to participate in exit polls.

Bill McInturff, McCain’s pollster and my wife’s employer, makes the same point and adds additional points:

1. Historically, exit polls have tended to overstate the Democratic vote.

2. The exit polls are likely to overstate the Obama vote because Obama voters are more likely to participate in the exit poll.

3. The exit polls have tended to skew most Democratic in years where there is high turnout and high vote interest like in 1992 and 2004.

4. It is not just the national exit poll that skews Democratic, but each of the state exit polls also suffers from the same Democratic leanings.

5. The results of the exit polls are also influenced by the demographics of the voters who conduct the exit polls.

So, the results will skew Democratic and give very wrong impressions. In 2000 and 2004, they incorrectly pointed to Democratic wins. In 2008, they will likely incorrectly point to an Obama landslide — or at least exaggerate the margin of victory in states that barely swing Democrat.

We’re all going to be hungry for information later in the day, especially after the perennial reports about long lines and huge turnout start trickling in. But we’re just going to have to wait for the returns.

UPDATE: Democrat Nate Silver issues essentially the same warning in Ten Reasons Why You Should Ignore Exit Polls.

FILED UNDER: Campaign 2008, Public Opinion Polls, US Politics, , , , , , , , ,
James Joyner
About James Joyner
James Joyner is Professor and Department Head of Security Studies at Marine Corps University's Command and Staff College and a nonresident senior fellow at the Scowcroft Center for Strategy and Security at the Atlantic Council. He's a former Army officer and Desert Storm vet. Views expressed here are his own. Follow James on Twitter @DrJJoyner.

Comments

  1. Triumph says:

    All I can hope for at this point is that Bush has a plan to make sure that the election goes the right way.

    Given Obama’s ties to terrorism and his anti-Americanism, it seems like Bush has the authority as the Commander-in-Chief to deal with the situation.

    The mechanics of the Electoral College are interesting and give Bush a legal way of saving the country. After states certify the votes for their respective electors, the Certificates are given to the President of the Senate (aka Cheney!). It is then Cheney’s job to present them to a joint session of Congress.

    If Bush and Cheney want to protect the country, Cheney simply has to sit on the Certificates and they can stay on as the chief executives.

  2. rodney dill says:

    I guess we’ll just have to patiently await the advent of Obama’s Sprinkle ’round Boo Hoo economics

  3. Bithead says:

    Somebody, whether Drudge or some other site, will likely leak the election results sometime this afternoon. While they’re impossible to ignore, you should do exactly that.

    In agreement, I’ll remind us of the exit polls in Ohio in 2004, which had John Kerry running away with the thing in that state.

  4. […] the incredible unreliability of early exit poll results — recall the bizarre results in 2004 which had Kerry with massive leads in Virginia, Florida, […]

  5. Bithead says:

    Amazingly, James, I just noted this on Drudge’s site: (Copied here because the link won’t be active tommrow, if past be prolouge)

    McCAIN CAMPAIGN MEMO: READING THE EXIT POLLS
    BILL McINTURFF, INTERNAL POLLSTER
    Mon Nov 03 2008 16:53:14 ET

    As we have seen in previous election cycles, the exit poll results do leak early and that ends up influencing the coverage of the race before even the first state polls close at 6:00 PM Eastern.

    However, we want to remind the campaign that the media’s own post-election study of the exit polls in 2004 showed that the exit polls overstate the Democratic candidate’s support. Therefore, we would discourage a rush to judgment based on the exit polls and wait until there has been a representative sampling of actual tabulated results from a variety of counties and precincts in a state.

    Here are the key points to keep in mind when the exit poll data starts being leaked:

    1. Historically, exit polls have tended to overstate the Democratic vote.

    2. The exit polls are likely to overstate the Obama vote because Obama voters are more likely to participate in the exit poll.

    3. The exit polls have tended to skew most Democratic in years where there is high turnout and high vote interest like in 1992 and 2004.

    4. It is not just the national exit poll that skews Democratic, but each of the state exit polls also suffers from the same Democratic leanings.

    5. The results of the exit polls are also influenced by the demographics of the voters who conduct the exit polls.

    After the 2004 election, the National Election Pool completed a study investigating why the exit polls that year showed John Kerry over performing 5.5 net points better than the actual results showed him to have done. Their conclusion was that the primary reason the exit polls was that Kerry voters and Democrats were more likely to participate in the exit polls.

    “Our investigation of the differences between the exit poll estimates and the actual vote count point to one primary reason: in a number of precincts a higher than average Within Precinct Error most likely due to Kerry voters participating in the exit polls at a higher rate than Bush voters. There has been partisan overstatements in previous elections, more often overstating the Democrat, but occasionally overstating the Republican.

    We believe that this will hold true this year. The recent Fox News survey showed that 46% of Obama voters said they were very likely to participate in the exit polls, while just 35% of McCain supporters are.

    In fact, even the 2004 exit poll report noted that higher turnout nationally and higher levels of voter interest in both 1992 and 2004 correlated with greater Within Precinct Error.

    The overstating of the Democratic vote did not only occur in the national exit polls, but also occurred in the state exit polls. The 2004 exit poll report cited that the Kerry vote was overstated by more than one standard error in 26 states, while the Bush vote was overstated in just four states. So we should also expect the individual state exit polls on Tuesday to be more Democratic as well.

    So given that turnout is expected to be even higher than 2004 and that Democrats are more likely to participate in the exit polls, this means we should expect greater fluctuation and variation in the exit polls from the actual election results.

    The 2004 exit poll report also showed that the greatest error in the exit poll came in precincts where the interviewer was younger. The completion rates were lower and the refusal rates and Within Precinct Error was higher when the interviewers were under the age of 35.[6] Complicating this is that nearly half the interviewers were under the age of 35, including 35% who were 18-24 and another 15% were 25-34.

    Conclusions

    Based on the previous exit poll results, we should expect once again that Tuesday’s exit poll data could overstate the Obama vote and under represent the McCain vote.

    It is important that the campaign make sure the media realizes this, so that when the exit polls do leak, people do not overreact to the early exit poll data. Rather than looking at the exit polls, we should wait until we start seeing actual election results from key precincts and counties to gauge who won the election.

    I await the commentary from the usual suspects, complaining you’re in the bag for McCain, James.

  6. Independent says:

    If Bush and Cheney want to protect the country, Cheney simply has to sit on the Certificates and they can stay on as the chief executives.

    So… you’re advocating a coup, rather than allowing the result of a democratic election to stand?

    Some of us gritted our teeth in 2000 and accepted that whether we liked it or not, Bush was going to be our President. And in 2004, we sucked it up again.

    If McCain could win it, I would’ve accepted that, too. I don’t think he will – but we’ll know that soon enough (hopefully).

    What is not a good idea is more of Bush, esp. by revolutionary methods.

    If McCain loses, why don’t you try being a grown-up about the whole thing and hope for a result you’ll agree with more next time?

    I bet you claim to be some kind of patriot most of the time, too… but the second someone you don’t approve of wins an election you want to trash the place!

    Pathetic and weak is what you really are, “Triumph”.

  7. Michael says:

    Pathetic and weak is what you really are, “Triumph”.

    No, Triumph is satirical.

  8. Triumph says:

    Pathetic and weak is what you really are, “Triumph”.

    Sure, dude. You can cast your lot in with terror all you want.

    If it weren’t for Bush’s invasion of Iraq, we would all be speaking Arabic right now. As he said at the time, Saadam was an immanent threat. Saadam was on the verge of invading the east coast and only with Bush’s bravery were we able to stop the Presidential Guards from marching down Pennsylvania Avenue.

    It would have been 1814 again–only worse: Uday and Qusay would be top generals and the country would have been in a state of lockdown.

    Obama loves these terror-types; Bush instills the fear of Allah into them. I would much rather have my freedom secured by giving Cheney the unprecedented power of calling an “election” than be sent off to a gulag by Obama and his Kenyan overlord, Adewale Ogunleye.

  9. Steve Plunk says:

    I’m hesitant to say it but Triumph’s satire is tiresome. It does nothing to advance mature debate on the subjects at hand. It confuses new visitors and bores many of us regulars. I’m not looking to insult him or pick a fight but somebody has to point out the obvious.

  10. Michael says:

    I’m hesitant to say it but Triumph’s satire is tiresome. It does nothing to advance mature debate on the subjects at hand. It confuses new visitors and bores many of us regulars. I’m not looking to insult him or pick a fight but somebody has to point out the obvious.

    The problem is that he’s moving too far away from true satire, and is instead just doing troll mimicry. When he is on his game, his satire actually points out flaws in the argument and beliefs he is pretending to support. He’s either getting bored or lazy, either way he needs to get it together or quit.

  11. Triumph says:

    He’s either getting bored or lazy, either way he needs to get it together or quit.

    Tough crowd… tough crowd..

    You guys remind me of my Doctor. I went to see my doctor. I said, “Doctor, every morning when I get up and look in the mirror… I feel like throwing up. What’s wrong with me?” He said, “I don’t know but your eyesight is perfect.”

    Boy, boy…lemme tell you… Well, he’s not as bad as my shrink. My psychiatrist told me I was crazy and I said I want a second opinion. He said “okay, you’re ugly too.”

    I have it even worse at home. I asked my wife if she enjoys a cigarette after sex and she said, “No, one drag is enough.”

    But, I do have one thing going for me. I have good looking kids. Thank goodness my wife cheats on me.

    I should have known something was up, I tried to take her out for a nice dinner. I made a toast on her birthday to ‘the best woman a man ever had.’ The waiter joined me.

    But, you know, she’s got her own problems. My wife has to be the worst cook. I’ve got the only dog who begs for alka-seltzer.

    Well, I probably inherit my troubles from my family. I think I got bad genes. I come from a stupid family. During the civil war my great uncle fought for the West.

    Thank you, thank you…I’ll be here all week….

  12. Independent says:

    Thanks for the explanations, folks… I was not familiar enough with Triumph’s methods to distinguish him from those who sound quite similar while being completely and sadly serious.

    It’s been a long campaign.

  13. Brian says:

    Keep ’em coming Triumph. I’m lazy and tired myself.

  14. Bithead says:

    I’m hesitant to say it but Triumph’s satire is tiresome

    I’m not…

  15. Triumph says:

    Keep ’em coming Triumph. I’m lazy and tired myself.

    When all else fails, I can always count on my Catskills act to bail me out…

  16. Anderson says:

    It is then Cheney’s job to present them to a joint session of Congress.

    Look for a RedState diarist to make this argument in all seriousness.

  17. […] Exit polls are meaningless for prediction, of course, but they’re all we’ve got right now. […]

  18. […] Exit Polls Lousy Predictors […]