Cross-posted from Future Majority.
One of the bigger points of contention this year in the (horridly geeky) world of polling was whether or not excluding cellphone-only users skewed the poll results. Throughout the cycle, PEW slowly but surely crept closer to saying "yes" to that question. Now that the results are in, they are finally making that judgment official.
According to a new report, polling that excluded cell-only showed a bias towards John McCain of 2.3 percentage points:
An analysis of six Pew surveys conducted from September through the weekend before the election shows that estimates based only on landline interviews were likely to have a pro-McCain tilt compared with estimates that included cell phone interviews. But the difference, while statistically significant, was small in absolute terms – smaller than the margin of sampling error in most polls. Obama’s average lead across the six surveys was 9.9 points among registered voters when cell phone and landline interviews were combined. If estimates had been based only on the landline samples, Obama’s average lead would have been 7.6 points, indicating an average bias of 2.3 percentage points. Limiting the analysis to likely voters rather than all voters produces similar results. Obama’s average lead among likely voters was 8.2 points across all six surveys versus 5.8 points in the landline sample.
When it came to young voters, the differences were much starker, though sample sizes make the numbers a little more fuzzy. Ultimately, polls that accounted for cell-only young people hit much closer to the final numbers among 18 - 29 year-olds on election night:
In Pew’s polling this fall, there was a gap of similar size in Obama’s advantage between cell-only young voters and those reached by landline, though this difference was not statistically significant given the relatively small sample of young cell-only voters. Among cell-only voters under 30, Obama led by 38 points (66%-28%); among those in the landline sample, Obama’s lead was 29 points (61%-32%).
Perhaps as a result of this pattern, Obama ran slightly better in Pew’s dual frame samples of young voters than in the weighted landline samples alone. As with overall voter estimates, the differences are small but statistically significant. Obama led McCain by 33 points (63%-30%) in the full dual-frame sample,
compared with his 29-point advantage in the landline sample.
The sample difference among likely voters under 30 was even larger. Obama led in the full dual frame sample by about 33 percentage points; in the landline sample his lead was 26 points. According to the national exit poll, Obama won this age group by 34 points, 66%-32%.
Lots of other juicy information out there for the data geeks about the demographics of cell-only, dual-use, and landline-only voters.