Of the 32 pollsters in FiveThirtyEight's now famous polling regression analysis,
Ann Selzer (right) is rated the most accurate. The site's founder, Nate Silver, writes that early in the cycle, Selzer & Co.
"nailed both the Democratic and Republican outcomes in the Iowa caucus" while polling for the Des Moines Register. Compared to other surveys, Selzer's polls have also favored Barack Obama quite
significantly. Just this past week, for instance, her Detroit Free Press
poll gave him a whopping 13 percent lead in Michigan, the widest Obama margin in any current poll of the Wolverine State.
So why are Selzer's results skewing left? According to Silver, "Selzer thinks that a lot of pollsters may be undercounting the youth vote, and potentially also the black vote." Part of the problem is the "Cellphone Effect," as he explains:
Young voters are becoming harder and harder to reach. They are in the habit of screening their phone calls. More problematically still, a great number of them (roughly 50 percent of voters under 30) rely principally or exclusively on cellphones, which most pollsters (including Selzer) will not call.
To compensate, many agencies add weight to the young voters they are able to reach. But Selzer says those efforts rarely go far enough. That's because polling agencies are using turnout figures from the 2004 election as their benchmark, even though the youth population has grown substantially. Twenty-two percent of adults aged 18 and up are now between 18-29, a five percent jump in just four years:
They may fix the youth voter figure at 17%, regardless of what their turnout model says (and ignoring the fact that youth voter turnout increased by 52% as a share of the Democratic primary electorate). Worse yet, they may start with the 17% and then apply their likely voter model, which has the effect of double-counting young voters' lower propensity to turn out. Or they may simply not stratify their sample by age at all, which creates even worse problems.
If pollsters have failed to adapt their work to changes in youth demographics, Silver says the same problem could emerge among black and Latino voters, who have been similarily targeted in voter registration campaigns this year. Considering the electoral effects those efforts could generate, Selzer and Silver just might be onto something.
Post new comment