Presidential election minus 13 days

With a fortnight to go, Barack Obama looks in big trouble on national polling averages, but retains breathing space on electoral college projections. The vagaries of polling methodologies might have something to do with this.

With less than two weeks to go, it’s high time for another presidential election thread – especially now that I’ve been inspired to put pen to paper by a fascinating article from Peter Kellner of YouGov, a British polling firm which has been sticking its oar into the American campaign.

The broad picture painted by the mountain of opinion polling is that a handy lead to Barack Obama disappeared after the first debate, and that to the extent that he is still favourite it is because he maintains slender leads in key swing states. According to RealClearPolitics, Mitt Romney now has a 0.5% lead on aggregated national polling after trailing by 0.2% two days ago. However, Nate Silver of FiveThirtyEight gives Obama a 70.3% chance of victory by virtue of state polling which shows, among many other things, an adjusted 1.9% lead to Obama in the likely crucible of the election, Ohio.

Until now, my favourite explanation for Obama’s stronger performance on electoral college projections has been that America’s decaying industrial “rust belt” is over-represented in the list of key states, which includes Wisconsin, Michigan and Pennsylvania together with Ohio. Romney’s image as a rapacious capitalist has by all accounts been especially damaging to him in these areas, owing to their long history of mass lay-offs and economic decline. This was illustrated when the General Motors bailout emerged yesterday in the context of what was supposed to be a debate about foreign policy, with Romney again haunted by his assertion from 2008 that the government should, as the New York Times subeditors helpfully paraphrased it, “let Detroit go bankrupt”. However, Kellner points to an intriguing alternative explanation involving polling methodology, with encouraging implications for Obama.

In the United States as in Australia, polling generally involves contacting random samples of respondents, the composition of which differs entirely from one poll to the next. However, the alternative approach, known as panel surveying, is to call back on the same set of respondents to determine how many are changing their minds. As Nate Silver observes, there are good reasons why this method is not generally favoured: the fact of being surveyed on multiple occasions may influence the way respondents behave, and a biased sample will produce consistently biased results, rather than random variation in the direction of errors from one poll to the next. The virtue of the approach is that it provides a more stable footing for evaluating changes over time, which is especially useful in the event of a significant shift such as that which the polls appeared to detect after the first debate.

As Kellner explains, YouGov fortuitously conducted just such a survey on a vast scale both before and after the debate. Whereas the RealClearPolitics aggregate saw a 4.3% lead to Obama on September 29 turn into a 1.3% lead to Romney by October 13, the panel survey found next to no change, with the small number of respondents switching from Obama to Romney matched by an equal share going the other way. What did emerge though was a crucial distinction in response rates from one survey to the next. Whereas the first survey elicited 33,000 responses, YouGov was only able to get 25,000 to complete the survey after the debate. This included 80% of those who indicated support for Romney the first time, against only 74% of the Obama supporters. That meant the raw numbers became immensely more favourable for Romney, and remained so after the data was weighted in the normal fashion according to demographics (by age, gender, region and race).

However, when weighting was further done according to party identification – so that responses from those identifying as Republican, Democrat or independent carried equal weight from one poll to the next – the effect of the differential response rates washed out, along with all but sliver of the swing to Romney. Responses are weighted in this fashion by YouGov as well as Rasmussen, but not by most other American pollsters. The argument against this approach (which, amusingly enough, has most often been heard from liberal critics of Rasmussen, which is renowned for its Republican lean) goes that party identification can change sharply in response to specific events, and that weighting for it negates their impact on voting intention. However, YouGov’s evident failure to find large numbers of individuals who changed their tune after the debate (allowing for the previously noted qualification that panel respondents may be shy about admitting they have changed their minds) suggests that, on this occasion at least, party identification weighting might have produced more meaningful results.

Nate Silver was moved to hypothesise that a lack of such weighting might cause polls to exaggerate bounces which occur in response to focusing events such as party conventions and clear debate victories. This is not to say that the poll shift to Romney isn’t meaningful, as the surge of enthusiasm which made Republicans more forthcoming when pollsters came calling could equally translate into higher turnout, with very real consequences for the outcome. However, Kellner offers a compelling counter-argument: that as the campaign intensifies with the approach of polling day, the enthusiasm gap and its attendant advantage to Romney will diminish. This may well be reflected in Obama’s lead in the swing states, where campaigning is already quite intense enough.

Author: William Bowe

William Bowe is a Perth-based election analyst and occasional teacher of political science. His blog, The Poll Bludger, has existed in one form or another since 2004, and is one of the most heavily trafficked websites on Australian politics.

294 comments on “Presidential election minus 13 days”

Comments Page 4 of 6
1 3 4 5 6
  1. “@fivethirtyeight: 7 polls released in Ohio in past 48 hours: Obama +2, Obama +3, Obama +3, Obama +3, Obama +5, Obama +5, Obama +5. #notthatcomplicated”

  2. Looks like the jobs report WILL be released on Friday, after some speculation it would be held off due to Sandy.

    That’s a pretty big moment.

  3. Looks like the jobs report WILL be released on Friday, after some speculation it would be held off due to Sandy.

    That’s a pretty big moment.

    Indeed – last roll of the dice for Mitt – if it’s a wash then Obama’s home

  4. Good idea on the tipping contest.

    1. Electoral vote tally
    2. National popular vote to the nearest 0.5% for each candidate.
    3. Seat composition of the new Senate*
    4. Seat composition of the new House
    5. Winner and vote tally (to nearest 0.5%) in Ohio and Florida.

    Any other suggestions?

    *Note that, with Senate composition, independents should be classed as independents, regardless of which party they may support for a majority.

  5. The stupid thing is it’s a one-day snapshot of 140 businesses only. From a workforce of over 100 million.

    Huge margin of error.

  6. [I like it Corey. What are we thinking for cut-off point? I was thinking Saturday 6.00pm, but doesn[t matter.]

    Whenever’s good for you guys. I am happy to lock my final prediction in on Saturday…

  7. [Carey Moore
    Posted Thursday, November 1, 2012 at 10:35 pm | PERMALINK
    Good idea on the tipping contest.

    1. Electoral vote tally
    2. National popular vote to the nearest 0.5% for each candidate.
    3. Seat composition of the new Senate*
    4. Seat composition of the new House
    5. Winner and vote tally (to nearest 0.5%) in Ohio and Florida.

    Any other suggestions?]

    I think we should make predictions on the most interesting 10 states, which I see as being the following:
    1. Minnesota
    2. Wisconsin
    3. Nevada
    4. Ohio
    5. Colorado
    6. Virginia
    7. New Hampshire
    8. Iowa
    9. Florida
    10. North Carolina

    …in no particular order!

    The trouble with ECV predicitons is there are so many ways to get there, we need an accurate prediction of each pivotal state don’t you think?

    Also, lets all agree that King wins Maine and caucuses with the Democrats and just consider him in the Dem numbers!!!

    Other than that….I am in! 🙂

  8. Senate predictions (draft 1) = 54

    That is made up of 47 safe Senate seats, including Maine Independent King, plus:
    Mass: Dem (Warren) +5
    Conn: Dem (Murphy) +5
    Missouri: Dem (McCaskill) +5**
    Wisconsin: Dem (Baldwin) +2
    Virginia: Dem (Kaine) +1
    Indiana: Dem (Donn) +1*
    Montana: Dem (Tester) +1

    Nevada: Rep (Heller) -1
    Nth Dakota: Rep (Berg) -3
    Arizona: Rep (Flake) -3
    Nebraska: Rep (Fisher) -5

    (negative means Republican wins it)

    * Thanks go to Rep candidate Richard-rape-is-God’s-will-Mourdock
    ** Thanks go to Rep candidate Todd-rape-doesn’t-cause-pregnancy-Akin

  9. Nice one, Mod Lib. Cannot fault your prediction at the moment. Will have a look at the Senate numbers a little closer tomorrow, as well as other prediction things.

    I am already thinking about 2016… haha sorry!

  10. @ezraklein: Obama is up .1% if RCP average. Remember when, last week, Romney had polling momentum? He’s lost ground since then http://t.co/XUJpoihs

    “@ezraklein: Someone should go run an analysis of spikes in the word “momentum” in political press and poll movement, I bet correlation is negative.”

    “@ezraklein: Mechanism: Press sees poll movement, calls momentum, but momentum isn’t obviously real in politics, and reversion to fundamentals is”

    “@breakingpol: New WaPo-ABC tracking poll: 48.56% Obama; 48.49% Romney – @washingtonpost http://t.co/qyPvEsU7”

  11. [Simon Cullen Tony Abbott is promising dedicated Parliamentary sitting days for the repeal of legislation if he wins the election]

  12. Dick Morris: “Romney will win with 330+ electoral votes. He will take Ohio, Iowa, Colorado, Michigan and Pennsylvania. All of the polls are completely false.”

    Brilliant.

  13. @nytimes: Bloomberg Endorses Obama, Saying Hurricane Sandy

    Dems must be pretty happy about this. I’d would guess they were wondering how they could, post Sandy, get the climate change meme going without looking opportunistic. Then along come a credible ex-republican and does it for them.

  14. Romney has ticked over to $4 on sports bet. Or a 25% probability. Dick Morris should be getting on that little earner.

  15. I just love the irony that two Tea Party idiots and a hurricane which may or may not have been contributed to by AGW have been the nails in the coffin of the Repugs.

  16. @diogenes yep, the irony is fantastic

    I really want to hear someone from the Tea party explaining why an act of God, like hurricane Sandy, prevented them from winning.

  17. The jobs figures are just as likely to be bad for Obama, they’re unpredictable.

    The last hope for the GOP is 8%+ figures. Anything at 7.8 or lower is the official endgame.

  18. I suspect the Unemployment wont be much difference and if it goes up it will be due to participation increases…either way I don’t expect it will have much of an impact.

    Interestingly, if you iron out the convention bounces and the debate bounces, the race has not really changed at all for months.

  19. Some fantastic polls for Obama tonight:

    ………….Obama Romney
    Virginia 49% 44% Oct 30 Nov 01 IPSOS
    Virginia 49% 46% Oct 30 Oct 31 PPP
    Nevada 50% 46% Oct 23 Oct 29 SurveyUSA
    Ohio 47% 45% Oct 30 Nov 01 IPSOS
    Iowa 48% 49% Oct 30 Oct 30 Rasmussen
    Iowa 50% 44% Oct 28 Oct 29 Marist Coll.
    Iowa 50% 47% Oct 29 Oct 31 CallFire

    …remembering to take into account Rasmussen probable 2-4% bias towards Romney

  20. The jobs figures are just as likely to be bad for Obama, they’re unpredictable.

    The last hope for the GOP is 8%+ figures. Anything at 7.8 or lower is the official endgame.

    Forecasts range from 7.7 to 8.0% – guess well find out shortly

  21. Looking at the Colorado polls, I still have Obama in front in Colorado.

    EV.com seems to have included two ipsos tracking polls in its current poll average, both the current and previous day’s ipsos tracking poll have Romney ahead by 1 pt, so using two consecutive days of tracking polls from the one pollster in this instance favors Romney.

    EV.com also don’t use We Ask America a GOP leaning robo-pollster that actually has (ironically) the joint best poll for Obama in the last 7 days in CO, a 50-47 lead. With these differences Obama is ahead barely in CO…

  22. Mod Lib

    If you are still tuned in. I’m a bit confused about the early voting figures. I’ve had the impression from comments made on PB that Obama has been creaming Romney in the early voting. But a talking head on Lateline has just said it is favouring Romney. What is your take on it?

  23. Thanks Poliquant.

    What do you think about the concept of the undercount of Latino votes in the western states like Nevada and Colorado?

  24. poli

    [Another metric for the Geeks…. Intrade. Here are the instant implied probabilities for Obama and Romney to win. Updated every 60 seconds]

    Intrade was gamed in 2008 and Nate suspects it is being gamed again in 2012. Intrade has consistently rated Romneys chances a lot higher than all the other bookies.

    Basically, Romney or a surrogate is betting big on Romney to make it look like he’s in with a better chance than he is as Intrade is often quoted in the media.

    There is a lot of money to be made betting on Obama if you had an Intrade account.

  25. Yes, early voting is confusing me too, I wonder what Poliquant or William think about it.

    1. Overall, Romney appears to be winning
    2. In the pivotal states Obama is ahead (see the fantastic gmu site http://elections.gmu.edu/early_vote_2012.html)
    3. However, he is winning by LESS than he was winning in 2008
    4. However, however, the Republicans didnt have an early vote drive in 2008 and they do in 2012 and so it is not expected that they would improve
    5. However, however, however, in Colorado although Obama is just behind in the early vote versus being just ahead in 2008, his margin of 8.6% is bigger than this difference, ditto iowa.

    The national polls and the state polls were out of sync but now the national polls are trending to Obama (he is currently ahead on the realclearpolitics average) and the state polls are very definitely trending towards Obama (these are largely pre-Sandy bounce) so likely to get better over the weekend.

    So, all in all, I suspect the truth is that the Repub early vote is a little better as the conservatives desperate to get rid of Obama get their vote in early along with the new Repub early vote initiatives.

  26. Darn

    Obama is way ahead in early voting but he’s not as far ahead in a few states as he was in 2008. In Colorado I think he might even be behind in early voting.

Comments Page 4 of 6
1 3 4 5 6

Leave a Reply

Your email address will not be published. Required fields are marked *