By failing to survey cellphone-only voters, pollsters could be undercounting Barack Obama's support

[Douglas Carpenter]

from salon.com


http://www.salon.com/opinion/feature/2008/07/14/cell_phone/?source=newsletter

snip:

"By law, cellphone users cannot be called by an automatic dialing system (to prevent obnoxious telemarketing), and cellphone numbers are not part of the normal random-digit-dialing residential-exchange universe. Survey companies prefer to conduct polls using automatic dialing, but to find cellphone-only voters, they must employ the less-efficient hand-dialing method. Cellphone users must be sampled separately and at greater cost in time and money. This means that polls utilizing the cheaper and more efficient means of making survey calls do not include cellphone interviews.

And as survey respondents, these voters are less cooperative anyway. Even if they are contacted, they are less likely to take a call, or to arrange a call-back, than land-line households -- further increasing the cost of reaching them.

Many survey companies have looked at these impediments and decided that it is simply not worth the extra effort and cost to track down cellphone users. (I am not going to name names, but one should assume that polls conducted by robo-calls undercount cellphone-only voters.) The pollsters' rationalizations hinge on the theory that a sampling of similarly profiled land-line voters -- younger, better-educated, more transient -- will yield similar results. But polling has certainly missed trends, and segments of the population, before. The Literary Digest never stopped to think in 1936 that its readership might not reflect the views of the entire country when its poll predicted a victory for Republican challenger Alf Landon over incumbent Franklin Roosevelt.

This year, the increasingly inexcusable failure to count a growing pool of voters could prove mathematically embarrassing. Let's say that with the campaigns' increased focus on the Web, Facebook, phone-texting and other targeted ways to communicate to younger Americans, voter turnout rises and this cellphone-only universe climbs from under 10 percent of the electorate to something closer to 20 percent. If these voters' preference is 60-40 for Obama, they alone will increase his national total by 2 percentage points. And those could easily be conservative projections. In fact, Gallup Poll results from earlier this year (prior to Obama's designation as the presumptive Democratic nominee) had a 4-point swing in favor of Obama once cellphone-only respondents were folded into the overall sample.

After 2000 can any public or private polling organization willingly use a sampling methodology that understates a candidate's support by 4 points, or more than 3 million voters.

http://www.salon.com/opinion/feature/2008/07/14/cell_phone/?source=newsletter

[mod mom]

1. Glad to read someone in the media is covering this.

[nc4bo]

2. Me too. My home doesn't even have jacks for a landline. We're straight cellphone peeps. n/t

[jenmito]

3. Gallup polls cell-phone users:

"Survey Methods

For the Gallup Poll Daily tracking survey, Gallup is interviewing no fewer than 1,000 U.S. adults nationwide each day during 2008.

The general-election results are based on combined data from July 10-12, 2008. For results based on this sample of 2,635 registered voters, the maximum margin of sampling error is ±2 percentage points.

Interviews are conducted with respondents on land-line telephones (for respondents with a land-line telephone) and cellular phones (for respondents who are cell-phone only)..."

http://www.gallup.com/poll/108766/Gallup-Daily-Support-McCain-Obama-Stays-the-Zone.aspx

[Gman]

4. I agree with this for this election

this was cited as a bias in 00 and 04. I think in those years the error was negligible. However, this year, given Obama's great strength with the youth vote, and given that kids today don't usually go out of their way to have a landline, there is serious reason to doubt the sampling. Of course, this also assumes the youth are going to turn out in November like never before and that the size of the youth vote in relationship to the overall vote is significant enough to move Obama's actual numbers a significant amount.

[jobycom]

5. That's probably a valid point, but probably overstated as well.

The formulas pollsters use take a lot of varied demographics into account, based on historical turnout patterns, and on turnout expectations based on poll questions, so most people who are cell-only (like me) are included in other demographics as well. Unless there is some expectation that cell phone users will vote as a solid block, or as a recognizable demographic that takes prominence over any other income, gender, ethnic, or regional demographic they also fit into, then not skipping them won't affect things much.

But as the article points out, with Obama using high tech promotional methods, he may be creating such a demographic. They will still pick up that demographic by making hand calls on cell phones, but their formulas may not account for that, and since it's easier to robo-call, their sampling of land-liners will be more extensive, so more reliable, than their sampling of cell phone users.

The bigger problem, though, is the classic question of whether pollsters catch demographics changes as they happen. As with war, you are always polling last term's election, because the formulas are based in part on last term's turnout. If a new demographic pops up--in this case, a high-tech demographic that might be voting as a group independent of other groups people belong to--they may not notice it right away, and may not notice it for several cycles. Their numbers will just be off.

This cell-phone bias could work either way, too. Say they randomly sample white males between 35 and 40 in a middle income bracket--a typical Republican base--but since they aren't filtering for cell phone use or high tech criteria--most of their sample would also fit into this cell phone bracket. So they are more pro-Obama, and when plugged into the whole formula, they may make the entire graphic look more pro-Obama than they are.

The reason I say it's probably overstated is because this cell-phone group is captured in polling in other demographics, so it's not likely to be a large percentage over a long period over several polls. Rather, it will cause some polls to be wildly inconsistent with others, and we won't know which are right until it's over.

Yeah, I write too much. Sue me. :) No one reads my posts anyway.