The leading association
of public opinion and
survey research professionals
American Association for Public Opinion Research

Explaining Exit Polls

An election exit poll is a survey based on interviews with voters as they leave (or exit) their balloting locations. To estimate the outcome of an election in a particular constituency, a sample of its smallest voting units (often referred to as precincts or polling locations) is drawn and at least one interviewer is assigned to each sampled location on Election Day. On a pre-determined and systematic basis, the interviewer approaches people who have already voted in order to obtain an interview. For example, depending upon the expected number of voters at the sample location, the interviewer may approach every third or fifth person who leaves the voting location. The interviewer usually hands the voter a questionnaire on a clipboard and asks him or her to fill out the questionnaire, fold it up, and deposit it in a survey ballot box. In most instances the exit poll questionnaire is self-administered to protect the privacy of the voter and the confidentiality of each individual’s responses.

A regular series of national exit polls is conducted in the United States for the major national news organizations. Election exit polling began in the 1970s as separate data collection operations conducted by each of the major television networks. The separate operations were later consolidated into a single data collection enterprise in order to save money. The exit polls between 1989 and 1992 were conducted by a consortium called Voter Research & Surveys (VRS) which became Voter News Service (VNS) which conducted the exit polls from 1993 to 2002. In 2003, ABC, CBS, CNN, FOX, NBC and the Associated Press formed the National Election Pool (NEP) and all NEP exit polls since 2003 have been conducted by Edison Research.

The typical exit poll questionnaire gathers three types of data:

  • How the respondent voted in the election
  • A variety of attitudes held by the voter such as the issues that were important in determining their vote and their party affiliation
  • The demographic characteristics of the voter such as their age, gender, race and level of education
The latter two sets of information can be used to explain why respondents voted as they did and what kinds of people voted for each candidate. These exit poll questionnaires are relatively short (typically less than 25 questions) and take less than five minutes to complete.

Election night projections of the outcome of key races are based only in part on exit polls. Interviewing people as they leave their voting place overcomes a lot of the problem of respondents’ misreporting whether they voted or not when they are interviewed on the telephone. Analysts have sophisticated statistical models to make their projections that use addition data beyond that gathered in the exit polls, including historical voting data such as past turnout and the partisan division of the vote from the sample precincts in which the interviews were conducted. Computer models use this information to evaluate exit poll results as they become available, looking at whether the turnout is higher or lower than usual and whether the vote is more or Democratic or Republican than in the past.

In close races, the projection models also employ actual vote totals, first in sample precincts as it becomes available and then at the county level for all counties in a state as they become available.

It is important to note that after the votes have been counted, the exit poll results are adjusted to match the actual election outcomes. It is in this way that the final exit poll data can be used for its primary and most important purpose – to shed light on why the election turned out the way it did.

These data provide powerful explanations for why people voted the way they did – telling us which key demographic groups voted for which candidates and why. It is in this way that the so-called “mandate” of the election can be measured and reported accurately without relying on the partisan “spin” that the candidates, their campaign staffs, and political pundits typically put on interpretations of the election outcome.

Finally, exit polls do something that pre-election polls cannot do: capture the voting intent of last minute deciders. In 2012, 3% of voters made up their minds on whom to vote for on Election Day, according to the exit polls; 9% decided whom to vote for in the last few days before the election.

Exit polls face many challenges especially given the changing nature of how and when people vote. These challenges include:
  • Changes in the way people vote The share of all voters who cast their votes before Election Day using by-mail absentee ballots or in-person early voting has increased from approximately 16% of voters in the 2000 presidential election to an estimated 35% of voters in the 2012 presidential election. Telephone surveys of absentee and early voters are used to supplement the NEP’s national exit polls as well as state exit polls when there is a high proportion of absentee and early voters.
  • Selective refusal Slightly less than half of voters asked to participate in an exit poll agree to complete the questionnaire and those who refuse sometimes are different from voters who agree to be interviewed. The exit polls attempt to account for differential non-response by adjusting the data using visibly observable voter characteristics such as gender, age and race. However, if Republican voters decline to fill out an exit poll questionnaire at a higher rate than Democratic voters, the exit polls can produce a slight Democratic overstatement. As noted previously, to deal with this the exit poll results are also weighted to reflect the actual election outcomes.
  • Early leaks In the past, early and incomplete exit poll results were sometimes leaked on Election Day. Today, major news organizations have agreed not to release any exit poll data that could characterize the outcome of a race before all of the polls in that state have closed. The embargo is necessary because an exit poll sample is not representative of the entire electorate until the survey is completed at the end of the day. Different types of voters turn out at different times of the day. Since 2006, in order to prevent early leaks of exit poll data, the NEP has limited access to exit poll data to a small group of analysts in a quarantined location until a few hours before the polls close.
  • Election regulations Over the years, some state election officials have attempted to impose restrictions on how close exit poll interviewers are able to stand to the exit of the polling location. News organizations have brought suit against more than a half-dozen states that have tried to impose distance restrictions of 100 feet of more. In every case, courts have thrown out these restrictions. However, there are some states that impose interviewer distance restrictions of up to 75 feet and these distance restrictions do adversely affect response rates.
Exit surveys are used for other purposes. The technique is frequently employed to survey movie-goers, library users or museum visitors.

This information was developed by AAPOR as part of a comprehensive online journalism polling course created in partnership with NewsU, a project of the Poynter Institute and funded by the Knight Foundation. The course launched September 2007. 

Download PDF Version