Presidential Polls in the Final Weeks of the Campaign

 Posted by  Robert S. Erikson

With about three weeks to go before the election, Obama leads McCain by about eight points. While an upset remains possible, Obama is clearly poised as the likely presidential winner. What can we expect from the polls over the next three weeks, and how well will they predict the actual outcome? 

For poll-watchers, the temptation is to treat every new poll as a decisive piece of new evidence, as if any departure from the current trend might indicate a change that will carry forward to Election Day.    But the next outlier we see will probably be an artifact of routine sampling error rather than a harbinger of true change. True change in preferences occurs slowly, especially during the final weeks of a campaign. Observe the following graph of the Bush-Kerry vote in the polls during the final 28 days leading up to the 2004 campaign  
2004 polls in last 30 days.jpg

The Polls During the Final 30 Days of the 2004 Presidential ElectionEach dot represents the poll-of-polls or average of all polls whose coverage centered on that date.  The curved blue line represents a lowess trend line. The dashed orange bar represents the Election Day outcome. 

This graph shows the poll-of- polls for the final 28 days in 2004. (Polls are assigned to the date that is the midpoint of their coverage.)   Although a trend line can be forced through the data as the wobbly curved line, the distribution of the observations shows no real pattern and is within the range that, according to sampling theory, would occur by chance if there was no actual change during the final 38 days. In other words, technically, we cannot reject the null hypothesis that all observed variation in the final month of the 2004 campaign was sampling error, with voter preferences constant throughout. (The standard deviation of the observations is a mere 1.01.)  Probably Bush was slightly ahead through this period, and the occasional poll that showed Kerry in the lead was a statistical illusion.
We can extract information about the final few weeks in the polls from elections going far back—as far back as 1944. The next graph shows the week-to-week movement in the polls leading up to Election Day and then the shift from the final week’s polls to the Election Day verdict.    Poll verdicts represent the poll-of-polls for the week, with polls assigned to a particular week according to the middle date of their polling period.    Observations are based on polls from 1944 through 2004, although not all election years are represented by polls for the given week. 
Weekly Poll Margins, 1944-2004.jpg
Weekly poll margins by lagged weekly poll margins in the latter weeks of the campaign, 1944-2004. Observations are based on weekly polls-of-polls.. For some weeks of some election years, there were no pollsThe diagonal lines represent lines of equality between the poll margin and the lagged poll margin, not regression lines.
This graph’s obvious feature is the incredible stability of the polls from one week to the next. And then the final polls predict the vote quite well, although the size of the lead in the final polls typically shrinks by about 30 percent on Election Day.    If we regress the poll verdict on the lagged verdict for weeks T-1, T-2, or T-3, the adjusted R squared is .96 or higher. If we regress the Election day verdict on the poll verdict for the final week (ignoring pre-1952 quota-sample polls), the adjusted R squared is .95. Thus, we see that in past campaigns, in the runup to the election, weekly change has come in small increments. 
Still, the slim movements from one week to another carried some meaning. As the next figure shows, from week to week the polls became increasingly accurate as a predictor of the final outcome. We also see that the poll margins exaggerate the size of the vote margins. (Cases cluster in the “West by Southwest” and the “East by Northeast” octants.)   The most remarkable fact is the near absence of cases in the off-diagonal—where the leader in the poll-of-polls ends up losing. The two exceptions of late-campaign comebacks are Truman’s famous surge in 1948 (partially an artifact of  bad polling) and 2000 (Gore’s futile popular vote comeback). 
Vote by Poll Margins, 1944-2002.jpg
 Election Day vote by poll margins in the four weeks leading up to the election, 1944-2004.  Observations are based on weekly polls-of-polls. For some weeks of some election years, there were no pollsThe diagonal lines represent lines of equality between the poll margin and the vote, not regression lines.
So where does this leave us regarding 2008? As of this writing, about three weeks before the election, Obama leads McCain by about 8 points. My back-of-the-envelope calculations based on the regression of the vote on polls on this date in earlier years suggests about an 86 percent chance of an Obama victory, giving McCain one chance in seven of pulling it out (slightly more optimistic for Obama than the current betting markets have it). . This forecast is based on polls alone, without considering how the economic crisis aids Obama.   Then there may be other unknowns this year that bear on the final outcome. So let's continue to keep an eye on the polls.  
The author is a professor of Political Science at Columbia University. The data and analysis presented here is from joint work with Christopher Wlezien of Temple University.


About this site

The mission of Princeton’s Center for the Study of Democratic Politics at the Woodrow Wilson School is to promote empirical research on democratic processes and institutions.  That broad mandate has attracted a diverse collection of faculty, students, and visitors pursuing a wide variety of research topics. However, the American electoral process has been a recurrent focus of interest for many of the scholars associated with CSDP and a frequent topic of conferences, colloquia, and other events sponsored by the Center.  As the 2008 campaign unfolds, we thought it might be helpful and fun to collect the election-related research, analyses, and offbeat insights of our extended scholarly community, both for our own edification and as a resource for others interested in how political scientists are thinking about the election.  We welcome contributions, comments, and suggestions. For more about the people and activities of CSDP, please visit our website, To post a comment, click the "speech bubble."

  — Larry M. Bartels, Director

Recent Entries

  • What the 2008 Election Meant: Politics and Governance

    On Friday, November 14, CSDP and the Brookings Institution co-sponsored the final seminar of the Election 2008 series:PanelistsJohn HarwoodChief Washington Correspondent, CNBC; Political Writer, New York...

  • How Obama Survived the Culture War

    Much of this year’s Republican presidential campaign consisted of a series of blistering attacks portraying the Democratic candidate, Barack Obama, as an elitist, a celebrity,...

  • Election Debriefing

    I’ve already seen lots of excellent political science post-mortems on the election. John Sides has had a particularly good series of posts at Monkey Cage attempting to...

  • A Few Questions for the President-Elect

    Two days after Senator Obama’s historic victory, the President-Elect has begun assembling the men and women who will guide his decision-making for the next four...

  • Campaign Effects in the 2008 Election: Money, Ads, and Mobilization

    On Friday, October 31, 2008, CSDP and the Brookings Institution held the fourth of five seminars on this year's election: Campaign Effects in the 2008 Election:...