Hostname: page-component-6898cfcb55-w5hgh Total loading time: 0 Render date: 2026-11-11T19:00:36.198Z Has data issue: false hasContentIssue false
  • English
  • Français

Introduction—Assessments of the 2004 Presidential VoteForecasts

Published online by Cambridge University Press:  06 April 2005

James E. Campbell
James E. Campbell
Affiliation:
University at Buffalo, SUNY
Rights & Permissions [Opens in a new window]

Extract

In the 2004 presidential election, 121.1 million ballots were cast for the major partycandidates. President George W. Bush received 51.24% of these votes to Senator John Kerry's48.76%. As Bush prepares for his second term, we know how the candidates performed. How didthe election forecasters do?

Information

Type
Symposium
Information
PS: Political Science & Politics , Volume 38 , Issue 1 , January 2005, pp. 23 - 24
Copyright
© 2005 by the American Political Science Association

In the 2004 presidential election, 121.1 million ballots were cast for the major party candidates. President George W. Bush received 51.24% of these votes to Senator John Kerry's 48.76%. As Bush prepares for his second term, we know how the candidates performed. How did the election forecasters do?

Evaluating election forecasts is not as easy as it would seem. Except when extremely lucky, forecasts are always to some extent inaccurate. There are always errors in the measurement of predictors, specification of the models, and unanticipated events in the campaign. Still, not all forecasts are equally inaccurate. How can the accuracy of forecasts be fairly judged? In my introduction to this election's forecasts (2004), I suggested several benchmarks. First, the average error (from 1948 to 2000) of naively guessing either a tie vote or the mean in-party vote (the null model) is 4.8 percentage points. The average error in Gallup's preference polls conducted from after the conventions to Labor Day (around the time that the fall campaign gets underway and many of the forecasts are made) is about 3.9 to 4.4 percentage points. Finally, polls conducted just before Election Day have an average error of about 2 points (1.6 since 1956).

Using these benchmarks in a roughly qualitative way, we can grade forecasts with errors of less than 2 percentage points as “quite accurate,” errors between 2 and 3 points as “reasonably accurate” (closer to the accuracy of the final polls than the pre-campaign polls), errors between 3 and 4 points as “fairly accurate,” errors between 4 and 5 points as “inaccurate,” and errors in excess of 5 points as “very inaccurate.”

From a collective standpoint, 2004 was a good year for the seven forecasts presented in the October PS. Two forecasts (Wlezien and Erikson, Lewis-Beck and Tien) were in the quite accurate range; two (Abramowitz, Campbell) were in the reasonably accurate range; and one (Norpoth) was in the fairly accurate range.1

The errors were: Wlezien and Erikson .5% and 1.7%, Lewis-Beck and Tien 1.3%, Abramowitz 2.4%, Campbell 2.5%, Norpoth 3.5%, Holbrook 4.9%, and Lockerbie 6.4%. Due to a coding mistake, Holbrook's forecast was 56.1% for Bush, not his originally reported 54.5%. The forecasting model by Cuzan and Bundrick, a progeny of Ray Fair's model but including a fiscal policy component, predicted a Bush vote of 52.8% in May and revised this downward to 51.1% in August. Both forecasts are in the quite accurate range. Also, my convention bump forecast was off by 1.5 points, placing it within the quite accurate range.

One (Holbrook) was in the inaccurate range and one (Lockerbie) was very inaccurate. This was joined in the stratosphere of errors by the prediction from the leading forecasting model in economics. The venerable economist Ray Fair's late July forecast of a 57.5% Bush vote was a whopping 6.3 percentage points greater than the actual vote (Fair 2004).

Of course, 2004 is only one election. It would be imprudent to read too much into either a very accurate or inaccurate forecast for a single year. Nevertheless, for the most part, 2004 was good news for the forecast models. In the following essays, each forecaster or team of forecasters provides an assessment of how their model fared this year and what might be learned from the 2004 forecast.

SYMPOSIUM AUTHORS' BIOS

Alan I. Abramowitz is Alben W. Barkley Professor of Political Science at Emory University. He is author of Senate Elections (University of Michigan Press, 1992) and is currently researching party realignment in the U.S. and its consequences for presidential and congressional elections.

James E. Campbell is professor of political science at the University at Buffalo, SUNY. He is the author of numerous articles and several books including The American Campaign: U.S. Presidential Campaigns and the National Vote (Texas A&M University Press, 2000). He co-edited Before the Vote: Forecasting American National Elections (Sage, 2000). The morning after the 2000 election he appeared on AM Buffalo to discuss the election with film legend Mickey Rooney.

Robert S. Erikson is professor of political science at Columbia University. His research on American elections has been published in a wide range of scholarly journals. He is coauthor of The Macro-Polity (Cambridge University Press), Statehouse Democracy (Cambridge), and American Public Opinion (Allyn and Bacon). He is the former editor of the American Journal of Political Science and the current editor of Political Analysis.

Thomas M. Holbrook is professor of political science and director of graduate studies at the University of Wisconsin, Milwaukee. He is author of Do Campaigns Matter? (Sage, 2003).

Michael S. Lewis-Beck is F. Wendell Miller Distinguished Professor and Chair of Political Science at the University of Iowa. He has authored or co-authored over 110 articles or books, including Forecasting Elections. Lewis-Beck has forecast U.S., French, British, Hungarian, and German elections.

Brad Lockerbie is associate professor of political science at the University of Georgia. His research focuses on the role economics plays in political behavior.

Helmut Norpoth is professor of political science at Stony Brook University. He has authored or coauthored numerous articles on voting and public opinion, and co-edited Economics and Politics: The Calculus of Support. On many occasions, he has assisted the New York Times with its Election-Day analysis.

Charles Tien is associate professor at Hunter College and deputy executive officer of political science at the Graduate Center, CUNY. His research has been published in American Politics Research, Public Choice, Public Opinion Quarterly, and other journals.

Christopher Wlezien is reader in comparative government and fellow of Nuffield College, Oxford University. His research and teaching interests encompass a range of fields in American and comparative politics, and his articles have appeared in various journals and books. He recently co-edited (with Mark N. Franklin) The Future of Election Studies (Pergamon) and currently is completing a book with Robert S. Erikson on The Timeline of Election Campaigns.

References

Campbell James E. 2004. “Introduction: The 2004 Presidential Election Forecasts.” PS: Political Science & Politics 37 (October): 733– 5.Google Scholar
Fair Ray C. 2004. “A Vote Equation and the 2004 Election.” http://fairmodel.econ.yale.edu/vote2004/index2.htmGoogle Scholar