Nonprofit, nonpartisan journalism. Supported by readers.


Obama up only 3 in Minnesota? Is that plausible?

Obama support has basically stayed flat — 47 percent now, 48 percent a month ago — even as Romney has gained 4 points.

I’ve already used the words “shock poll” once this cycle, so let’s call Sunday’s Star Tribune Minnesota Poll showing President Obama’s lead dwindling to 3 percentage points a “startle poll.” The gap — down 5 points in a month — is the smallest any pollster has showed … including a 4-point margin that Republican SuperPAC America’s Future Fund claimed two weeks ago.

So Republicans got confirmation for their confirmation bias and DFLers cling to Nate Silver’s observation that new Strib pollster Mason-Dixon skews Republican — surely the first time the Minnesota Poll has been accused of that.

If we all cherrypicked our favorite polls, there’d be an endless supply of Lambic Kriek. But if you want to play that game, let’s really play it. I’m going to offer you a choice of three polls; you have to pick before you learn the horse-race result. To help, here are a few objective stats:

  • In 2008, Obama won by Minnesota by 10 percentage points.
  • In 2008, 40 percent of Minnesota voters identified as Dems, 36 percent as Republicans, for a +4D partisan skew.
  • In 2011, 32.3 percent of Minnesota adults were wireless phone only.

Poll A:

  • Doesn’t call wireless phones.
  • Final-week 2008 poll was Obama +16.
  • October 2012 poll partisan skew: +9 Dem.

Poll B:

  • 23 percent wireless phone respondents.
  • Final-week 2008 poll: Obama +3.
  • October 2012 poll partisan skew: +10 Dem.

Poll C:

  • 20 percent wireless phone respondents.
  • Final-week 2008 poll: Obama +8.
  • October 2012 poll partisan skew: +5 Dem.

So which did you pick?

The first poll is from Public Policy Polling, run by Democrats, which showed Obama leading Romney by 10 Oct. 6-9. The second is SurveyUSA, employed by Republican-owned KSTP-TV, which showed the president up by 10 Oct. 12-14. The final poll is Mason-Dixon’s, the Strib’s pollster, whose Oct. 23-25 survey has it Obama 47-44.

DFL friends currently blending the polls (plus a St. Cloud State +8 Obama survey and Rasmussen’s +5) to show the president up by 5+ points must also acknowledge the timeline’s direction: five successive surveys show Obama’s lead flat or falling.

Is this a bad time to mention that in 2008, Minnesota voters who decided on Election Day broke for John McCain 52-43?

This isn’t to say Obama will lose or the trend is inexorable, only that the Strib’s number isn’t really an outlier if you look at the fundamentals. Every model-constructing pollster makes a barrelful of assumptions — yet all but the most propagandistic stay in business because they get fairly close to the pin on a fairly regular basis.

Digging too deep into a poll’s particular demographic slices is a mug’s game — sampling error (a.k.a. “+/- X points”) climbs as subgroup sample size shrinks. But a little thing jumps out at me comparing the Strib’s September and October survey.

Obama support has basically stayed flat — 47 percent now, 48 percent a month ago — even as Romney has gained 4 points. Yet there are 7 percent undecided voters in both surveys. So where did the Republican’s gains come from?

You’re forgiven for not knowing because this guy gets very little coverage: libertarian candidate Gary Johnson. He had 5 percent support in the Strib’s September poll, but 2 percent now.

Poll-readers often ignore single-digit third-party candidates, focusing more on undecideds. But undecided voters can park themselves in the third-party camp until something closer to Election Day — a strong debate, a tightening race — pushes them toward a likely winner.

Five percent is a big number for a minor party candidate. In Minnesota, Johnson would have to match Ralph Nader in 2000, and his campaign doesn’t seem to have that kind of mojo. Then again, libertarians are nothing if not passionate, and did swamp the GOP caucuses for Ron Paul earlier this year.

Among the Strib’s competitors, PPP doesn’t include Johnson as an option — not coincidentally, their early-October Obama number is highest at 53 percent, and their Romney number (43) was tops until Sunday’s Strib poll. SurveyUSA does include Johnson, who had 4 percent in mid-October. Both polls, however, showed Obama leading by 10.

St. Cloud State has Johnson at 2; Rasmussen has “other” with 1.

A few other random observations:

  • The Strib continues to be the only independent media poll showing men favoring Romney (51-40). PPP’s survey, 16 days older, had Obama winning 50-45 and SUSA (11 days old) had it 47-43. (St. Cloud State also differs with the Strib; Rasmussen’s crosstabs are pay walled.) The polls are generally in sync regarding women: All three show 52-56 percent backing the president and 37-41 percent backing Romney.
  • In that 2008 exit poll — based on 2,350 actual voters, a better sample than any pre-election survey — 13 percent were over 65. The Strib’s sample doubles that — to 26 percent. PPP is at 20 percent, SurveyUSA 19 percent, St. Cloud State 17 percent. Analysts don’t expect young voters to be as motivated as they were in 2008, and the population has aged, so the 65+ share may go up. Still, the Strib’s seems like a big jump.
  • The Strib’s shifting partisan skew — from +13D in September to +5D — goes the furthest to explain Obama’s decline. The paper’s concluding poll-story paragraph states — somewhat self-servingly — “party self-identification fluctuates as events sway voters’ opinions.” True, but probably not by that much, especially when +13D was higher than any other survey. More accurate to say, “Sampling error can also make a poll over- or undercount the actual partisan difference.”
  • When Nate Silver says a poll “skews Republican” he doesn’t mean it’s wrong — he’s comparing it to polling peers. It’s a good way to evaluate, but it’s not synonymous with correct/incorrect.

Comments (11)

  1. Submitted by Tim Milner on 10/29/2012 - 10:58 am.

    A question for David

    How do these various polls account for people, like myself, who answer the phone but refuse to take the poll once we learn that is what the call is about? Is a person’s unwillingness to respond to the poll contained within the statistical error reported? Or, do the companies increase the sample size they are calling to insure they get a certain number of responses?

    I ask this question because I think there are more and more people, like myself, who are becoming unwilling to take the poll calls. At least in my case, because we g=have been getting deluged with poll calls. 3 weekends ago, I must have received close to a dozen opinion poll calls!! (Never understood how I could be so lucky to be “randomly selected” so many times in one weekend. I’ll leave that question up to the stats guys)

    If a lot of people are refusing to take the polls, does that not offer potential for a much larger error than what is being reported?

    Just wondering.

    • Submitted by David Brauer on 10/29/2012 - 11:26 am.

      Great question and a huge problem

      Pollsters are all concerned about this – response rates have dipped under 10 percent in some cases, a third of what they were a few years ago.

      As you note, the danger is a sample that differs greatly from the non-poll-answering majority.

      Some pollsters – St. Cloud State included – give themselves time to make follow-up calls to the same number. (Up to 7 times in some cases!) This preserves the integrity of the original random sample (phone numbers chosen) as much as possible.

      Pollsters have a few modeling tricks they use – weighting responses to match Census demographics and my favorite, asking voters who they voted for in the previous election, to see if their sample at least vaguely conforms with known results.

      But there are flaws aplenty here – each election’s mix changes, so you’re basing your model on the past, not the present. 

      The real question – do polling non-respondents differ from poll respondents – isn’t one where I’ve seen good data (in part because how do we know what poll respondents think!). So we’re all kind of stuck looking at past track record, over a few elections hopefully, to see the outliers and the mark-missers.

      In general, the collective wisdom is still pretty good, as Nate Silver’s model showed in 2008. My experience focusing on Minnesota is that SurveyUSA and PPP have both been pretty good (though not flawless), especially as Election Day approaches. 

      Of course, don’t forget, polls really are a snapshot in time and it’s very hard even in a final-days poll to capture what late, late deciders will do.

      Further reading:

    • Submitted by Harris Goldstein on 10/29/2012 - 01:13 pm.

      Interesting Point

      While I would not mind responding to a truly objective poll, I hang up whenever I encounter the usual telemarketer delay after I pick up the phone.

      Don’t know whether there is any “right vs. left” bias in that behavior.

  2. Submitted by Dimitri Drekonja on 10/29/2012 - 11:36 am.

    Wow, under 10% response rates– that’s pretty dismal. And we’re supposed to assume that the sample still is representative of the population it’s drawn from? In my field (medicine), a response rate of 10% would kill your survey, or at best have it published in such a low-quality journal that no one would take it seriously. I’ve had a few small survey studies published with 35% response rates; they got into second-tier journals largely because of the potential for non-responder bias. 0%…I wouldn’t have even tried to publish. Makes one suspect that the goal of these surveys is not to accurately predict the outcome, but rather to drive the narrative, since our campaigns are so ridiculously long that the cable stations need something to fill the hours.

  3. Submitted by brian hanf on 10/29/2012 - 11:51 am.

    Poll response rates

    Why response rates really matter to pollsters. They need so many answers in a certain amount of time. If they need to dial more numbers to get those answers it costs them more money. Their margins go down. (ie years ago 3000 dials got you 450 answers [2000 no answers], now you need closer to 20,000 dials) It’s why Survey USA is still good and cheap. They use automated systems that can ramp up faster. No learning of script by a team of callers.

    Pollsters and Ad men have made the most money in elections for years. Both have seen huge declines in income and profits the last few years.

    Grassroots firms are seeing higher incomes as they have been the first to jump into social media (nature fit for them). Look at Minnesota’s Grassroots Solutions they were a very small firm a few years ago. Now major player in the campaign world.

  4. Submitted by David DeCoux on 10/29/2012 - 12:00 pm.

    A Touch Cynical

    “Makes one suspect that the goal of these surveys is not to accurately predict the outcome, but rather to drive the narrative,”

    And I’m right there with you.

  5. Submitted by rolf westgard on 10/29/2012 - 12:23 pm.

    Get ready for the ads

    Now that we may be a swing state, get ready for the barrage of garbage ads. I am hoping Amy’s strong showing will pull in support for Obama and Congressional Democrats.

  6. Submitted by David Broden on 10/29/2012 - 01:14 pm.

    Polling or Confirming a Candidates Position

    The comments are interesting in that they really do not get to the real problems of polls today. First the issue of a valid sample is significant regardless of who sponsors the poll–new methods must be established or polls will in the future have no credibility. Second polling has become more a way for parties and candidates to confirm status not to get objective responses. Most polls ask the answer and do not ask an objective questions. If the poll asks the answer the poll is automatically skewed> In past elections I have seen this done and it enables campaigns to look great. Another missing element seems to be the breakdown of where the poll samples came from-metro– suburban– outstate– up north- south- western – red river valley etc. Even with the significant demographic changes in Mn the state continues to have an independent segment of 30+ percent—-combine that with the historical mix of GOP and DFL governors, senators, congressman, and legislatures and it is easy to see that Mn is really an independent state and when polls surprise some it is likely only representative of Mn voter views.

    Dave Broden

  7. Submitted by Gary Doan on 10/29/2012 - 02:02 pm.

    Notice less bumper stickers?

    I remember seeing Obama bumper stickers everywhere in 2008, but I’m not many at all this year. No one I know will put a Romney sticker on their car or sign in their yard, because they are worried about vandalism or violence. This may be the year of the denial vote, because I have talked to a few people that I’m sure won’t vote for Obama, but will never admit they didn’t, because they are afraid of repercussions in their profession or from friends and family, that are very aggressive and borderline antagonistic. The country is more polarized now than I have seen, since I started voting in the 1970’s, I hope that changes after this election and the country starts to mend.

  8. Submitted by Bob Lawrence on 10/29/2012 - 03:59 pm.

    2008 was a long time ago. Maybe it’s time we the people of Minnesota wake up and realize that Obama is NOT all he claimed he was and is. I for one am not ashamed to say I am voting for Romney. Especially after seeing the type of campaigning that is being done by this president. Very negative. I thought those days were gone. I guess not. I like Mitt’s style…so far.

  9. Submitted by Lynn Brooks on 10/29/2012 - 04:38 pm.

    Minnesota Conservative

    I guess I have seen the change in the past 5 years or so with Minnesota moving to the right or at least moderate-right. In fact the whole upper Midwest (Iowa, Wisconsin, and Minnesota) is moving to the right. I think part of it is the huge evangelical growth here. It used to be mainly Lutheran and Catholic churches but I’m seeing more and more of these ‘mega’ churches or evangelical churches which tend to be conservative.

    I guess maybe I can give some insight as a new Conservative who was formerly a Democrat. Yes I am religious and that influences my vote, but I’m also sick of the Democratic party using wedge issues like abortion and gay marriage to try to sway peoples votes. They make it seem like Republicans are gonna take over everything, and the truth is that things will be fine. I completely believe in the new poll and think people will be very surprised election day. We may not win but I’m guessing it will be very, very close.

    The main thing I agree with the Republican party on is personal responsibility. I strongly believe that we have the choice to lead a good moral life. And it’s not my fault or responsibility to see that others do the same. Yes we need good education but we as Minnesotans alone can do that without government intrusion. And I’m voting for Mitt Romney. And I should also mention one of my friends who also use to be a Democrat is voting for Mitt Romney also. Things are changing here.

Leave a Reply