Star Tribune pollster: Dayton margin doubled when we included cell-phone-only voters

Last week, I wrote about whether 2010 governor’s race polls changed when people without landlines are included. Three major pollsters (SurveyUSA, the Humphrey Institute and Rasmussen) exclude voters who are cell-phone-only. However, the Star Tribune began including this quarter of the population in July.

In that first post, Humphrey Institute pollster Joanne Miller explained why her survey still excludes cord-cutters: cost, plus meta-surveys suggesting the effect is small and can be shrunk by weighting responses from landliners who also have cell phones.

After the story ran, reader Bill Gleason asked a good question: Did including cell phone results change the Strib survey?

Yes, says Larry Hugick of New Jersey-based Princeton Survey Research Associates, the Strib’s pollster.

The 561-registered-voter landline sample — the kind traditional pollsters use, weighted to match demographics — showed DFLer Mark Dayton leading Republican Tom Emmer by 5 points, 41 percent to 36. Independence Party nominee Tom Horner received 11 percent.

However, when 270 cell-phone-only voters were included, Dayton’s margin doubled to 10 points: 40-30 over Emmer, with Horner getting 13 percent.

This seems to confirm a DFL talking point that excluding cell-phone-only voters makes the GOP look stronger than it is. But even though including iPhoners and their ilk produced a stark jump in Dayton’s margin, Hugick offers important qualifiers.

First, the landline sample (561 registered voters) is smaller than the overall poll (831 registered voters) and thus has a higher margin of sampling error (6 percentage points plus or minus versus 4.5). In other words, it’s possible the gap doesn’t exist … though it may be wider.

Hugick also notes that comparing the Star Tribune’s results to the more recent Humphrey Institute survey — which showed Dayton and Emmer tied — is unwise. The Strib’s July poll surveyed registered voters; the Humphrey Institute poll measured likely voters, a cohort expected to favor the fired-up GOP.

“The July Star Tribune survey did not include the questions necessary to define a likely voter base,” Hugick says, adding this facet will be added soon. “In general, polls are in a better position to discriminate likely voters from non-likely voters closer to Election Day.”

As to the larger question, Hugick says:

“Can Minnesota pre-election polls still be reasonably accurate in estimating voter preferences with a landline-only methodology? Provided that the segment of the population that cannot be reached in landline-only polls (generally younger, less white, more mobile) have voter preferences similar to their demographic counterparts who can be reached by landlines, then the answer is “yes.”  Weighting will do the trick.

“But there is now evidence at the national level that landline-only pre-election surveys slightly underestimate support for Democratic candidates relative to Republican candidates. So demographic weighting may not be enough.”

Comments (9)

  1. Submitted by Paul Udstrand on 09/14/2010 - 10:43 am.

    Meta statistical analysis can be a fickle mistress, play with her at your own peril.

  2. Submitted by Bill Gleason on 09/14/2010 - 10:53 am.

    Fickle mistress or not, the data appears to be there to support the idea that land-line only tilts the pin-ball machine to the right (Emmer).

    Of course, as we all know, the only pin-ball game that matters is in November.

    So why does anyone care about the polls or about spinning them? Image is all. If you can make it look like your guy or gal is a winner, maybe they will be…

  3. Submitted by John Olson on 09/14/2010 - 11:04 am.

    I agree with Bill. Polls are expensive. Like an ice carving at a reception, it’s wonderful to look at, but it has a very short life.

    A lot can happen between now and election day.

  4. Submitted by Greg Kapphahn on 09/14/2010 - 11:52 am.

    I must, however, comment that among the wide range of people I know, it was, without exception, the younger members who almost universally elected to forgo landlines in favor of cell-only communications.

    Well, those younger folks together with the most forward-looking and progressive among the middle aged and older folks.

    To the extent that this is happening statewide, it has the effect of reducing the number of younger and more progressive voters reflected in landline-only polls, (since they cannot be reached by landline) perhaps to the extent of rendering them inaccurate.

    Whether that effect can be extrapolated around depends entirely on how accurate are the assumptions upon which those extrapolations are based. I have yet to see factual statistics regarding how many people have given up their landlines or never had them connected in the first place, but perhaps such statistics exist. If they don’t then attempts to extrapolate results in landline-only polls to include the opinions of missing cell phone-only citizens are little more than guesses.

    For that reason, I remain convinced that only polls which actually include calling cell phone-only citizens can be considered to be reasonably accurate for the moment in time during which that particular snapshot is taken.

  5. Submitted by Rich Crose on 09/14/2010 - 12:06 pm.

    The under 25 demographics are notoriously apathetic voters so it is difficult to count on them. You’d have to put legalizing marijuana on the ballot to get some of them into a voter booth.

    But with cell phones now going into their 20th year, there are a lot of 25-35 age range dropping their land-lines. Without them, the polls aren’t worth much.

  6. Submitted by Brian Simon on 09/14/2010 - 12:20 pm.

    I agree the landline vs mobile phone sample skew is interesting, but am also interested in how the ‘likely’ vs registered voters skew numbers. How much does our turnout fall in off-year (i.e. non-POTUS) elections? I’m still skeptical that unenthused DFL/Independent voters will sit this one out. Yes, the under 25 group will likely have the lowest turnout; but don’t the rest of us obligatorily trudge to the polls, unenthused about the candidates though we might be?

  7. Submitted by Bill Gleason on 09/14/2010 - 12:22 pm.

    Well some data is better than none, and the Strib data at leasts indicates that there is a significant difference between land-line only and cell only voter preferences.

    The reason I hesitate to extrapolate is that I have not, nor ever will, use a cell. And I am pretty much a lefty…

  8. Submitted by Dennis Tester on 09/14/2010 - 04:12 pm.

    The cellphone v. landline controversy is irrelevant.

    The kids who came out for Obama aren’t coming out for Mark Dayton. Their parents and grandparents will decide this election.

  9. Submitted by B Maginnis on 09/14/2010 - 09:17 pm.

    Thankfully, I am not in Greg Kappahn’s “wide range”.

Leave a Reply