Is Gallup Heading for Another Big Miss?

Based on the latest results from the HuffPost Pollster poll tracking model, with less than three weeks left until Election Day, the presidential race between Barack Obama and Mitt Romney is extremely close with both candidates estimated to have the support of about 47 percent of the electorate. The realclearpolitics.com average of national polls released over the past 10 days shows an identical result, a 47-47 tie. And the results of recent polls in the key swing states appear to be consistent with this picture of an extremely close presidential race.

There is, of course, some variation in the results of national polls that have been released in the past week or two but all of them show the margin between Romney and Obama to be within two or three points one way or the other. All of them with one exception, that is -- the Gallup tracking poll. The Gallup tracking poll alone among national polls, including the usually Republican-leaning Rasmussen poll, shows Mitt Romney with a large lead over Barack Obama among likely voters -- a seven point lead in the results released on October 18 and a six point lead in the results released on October 19.

Gallup is, without question, the biggest outlier among all of the national polls on the 2012 presidential election. But this is not the first time that Gallup has found itself in that position. Two years ago, Gallup was by far the biggest outlier in its forecast of the Republican margin in the 2010 midterm congressional elections. Gallup's final estimate of the Republican lead among likely voters in 2010 was 15 points. Only Rasmussen at 12 points was even close to Gallup. The average GOP lead across all of the national polls was about seven points, which was very close to the actual Republican margin in the national popular vote.

So what's going on with the Gallup tracking poll and why is it such a big outlier? Part of the explanation, as Mark Blumenthal pointed out in a recent post , is almost certainly Gallup's complicated likely voter screen which gives considerable weight to voter attention and enthusiasm. As a result of this screen, the Gallup tracking poll has been showing a very wide gap between the preferences of all registered voters and likely voters -- a 5-6 point difference in margin. In recent days, Gallup has been showing a very close race among registered voters but a big Romney lead among likely voters.

In 2010, the same large gap was evident in Gallup's polling and in the end the actual Republican margin in the House elections was considerably closer to Gallup's results for registered voters than to its results for its likely voters. It is entirely possible that the same thing is happening this year.

But beyond just the impact of Gallup's likely voter screen, there is another factor that may explain why Gallup is once again a big outlier. Despite some recent changes in its sampling procedures designed to make its initial sample of adults more representative of the U.S. adult population, Gallup's likely voter sample appears to be substantially under-representing non-white voters. Although Gallup does not report the racial composition of its likely voter sample (or any of its other samples), based on the results presented in their October 16 report on the standing of the presidential candidates among whites and non-whites, one can use interpolation to estimate the racial composition of the likely voter sample. The results show that about 80 percent of Gallup's likely voter sample consisted of non-Hispanic whites while about 20 percent consisted of non-whites.

Gallup's estimate that only 20 percent of this year's likely voters are non-white is far lower than the 26 percent non-white share of voters found in the 2008 exit poll or even the 23 percent share found in the 2004 exit poll. It is actually very close to the 19 percent share found in the 2000 exit poll. So according to the Gallup tracking poll, the racial composition of the 2012 electorate will be similar to that of the 2000 electorate despite the dramatic increase in the nonwhite share of the voting age population that has occurred in the past 12 years.

The fact that the Gallup tracking poll is a big outlier when it comes to estimating the standing of the presidential candidates this year is, by itself, a very good reason to view their findings right now with deep skepticism. The apparent under-representation of non-whites in their likely voter sample only reinforces that conclusion. The next two-plus weeks will tell whether the Gallup tracking poll continues to produce results that are far outside of the range of other national polls or whether its results move closer to the polling mainstream.