Presidential Polls: Within the Margin of Error?

The Wall Street Journal's Politics and Campaign section had an analysis posted October 17 that casts doubt on the large lead Senator Obama enjoys over Senator McCain in some national polls. In "Some Surveys Indicate Tighter Presidential Race," the Journal says that while some newspaper and television network polls show Obama with a commanding lead, "...other surveys tell a somewhat different story, suggesting the presidential race is still close, and the Republican has even gained ground in recent days."

For example, the Real Clear Politics average posted the morning of October 17 showed Senator Obama leading Senator McCain by nearly 7 percentage points. But within that average, individual polls varied wildly. Of the 13 polls rolled up into the RCP average, 6 showed an Obama lead of 5 points or less. Of those 6, one poll was at 2 points, one poll was at 3 points, and three polls were at 4 points. Only two of the individual polls showed Obama with a double digit lead, like the recently published CBS News / New York Times poll that gave Obama a 14 point lead.

Why the differences? According to the Journal, "Pollsters are facing new challenges this year, trying to gauge whether the electorate is changing, and how much."

In addressing methodology, the Journal's analysis says those polls assigning a wide lead to Obama "...tend to assume that a growing proportion of voters are Democrats, and a shrinking percentage Republicans. They also point to a big increase in turnout, particularly among voters under the age of 30. Surveys showing a closer race assume less change in party affiliation in particular."

Going further to demonstrate poll variance, the Journal cites an LA Times poll where Obama has a 9 point lead and a Pew Poll where Obama has a 7 point lead, but then cites an IBD-TIPP poll where the Obama lead is less than 4 points, and recent Rasmussen and Zogby polls that show an Obama lead of 4 and 5 points, respectively.

The Journal quotes editor in chief of the Gallup Daily Frank Newport as saying, "Clearly, the race has tightened."

Another problem with the polls, the Journal says, lies in their determination of likely voters. As an example, the Journal points to the Gallup daily tracking poll: "Gallup actually conducts two separate daily polls, one that includes all surveyed adults who say they will vote, and a second that is more restricted, using a decades-old methodology that determines 'likely voters' in part by examining historical models on the types of voters who have showed up at the polls."

The variation? The first poll shows Obama leading McCain by 6 points. The second? The gap narrows to 2 points.

Another problem shows up in determination of party affiliation. For example, the Journal says, Rasmussen weights polls so that Democrats outnumber Republicans 39 percent to 33 percent. Zogby uses a ratio of 38 percent Democrats and 36 percent Republicans.

John Zogby says, "What troubles me is when I see some of my colleagues have 27% of the respondents that are Republicans. That's just not America, period." Zogby goes on to say that party affiliation remains constant "day-to-day, and it never fluctuates by eight points in a short time period."

Is the race within the margin of error? I would say that's highly unlikely. But I would also say that I think it's going to be a lot closer than many believe.