Exit Polling From Edison Media Research and Mitofsky International
Edison Media Research not only provides exit polling services to the National Election Pool, we also use our national network of over 8,000 interviewers to conduct Commercial Exit Polls to measure consumer opinions, advertising and marketing effectiveness, and point-of-sale data. Our rigorous training and sampling methodology ensures the most representative sampling possible, and is often more efficient and cost-effective than telephone or Internet surveying.
For more information about Edison's Consumer Exit Polling services, click here.
What is the National Election Pool (NEP)?
The National Election Pool is a consortium of ABC News, Associated Press, CBS News, CNN, Fox News and NBC News. It was formed in 2003 in order to provide information on Election Night about the vote count, election analysis and election projections. NEP contracted with Edison Media Research and Mitofsky International (Edison/Mitofsky) to make projections and provide Exit Poll analysis. In addition, the NEP retained the Associated Press to conduct a tabulation of the vote throughout the country.
What does the Associated Press provide to the NEP?
The AP collects voter returns from all counties in the United States and from cities/towns in the New England states. They provide tabulations for each state for Senate and Governor, and congressional district tabulations for U.S. House of Representatives. They also provide tabulations for selected state referenda and initiatives. Regular AP clients are offered a more comprehensive vote count for many additional political contests.
What does Edison/Mitofsky provide to the NEP?
Edison/Mitofsky conducts statewide Exit Polls throughout the country as well as a National survey. In addition, Edison/Mitofsky collects the vote count in a sample of precincts in each state. Edison/Mitofsky provides Exit Poll analysis and projections for President, U.S. Senate, Governor as well as selected U.S. House, and state referenda and initiatives.
What is an Exit Poll?
Exit Polls are interviews with voters after they have cast their votes at their polling places. A sample of precincts are scientifically selected to collectively represent a state, or for the national Exit Poll, the nation. An interviewer gives every nth voter exiting the polling place a questionnaire to complete. There are questions about demographics such as gender, age, race, and issues related to the person's vote choice in different contests. Participation is voluntary and anonymous. The interviewing starts when the polls open and continue throughout the day until about an hour before the polls close.
Who decides what questions to ask on the Exit Poll?
All questions asked on state and national questionnaires are prepared by the six members of the National Election Pool.
How many polling places will be in your sample?
Sample sizes vary from state to state.
How do you select sample precincts?
Precincts are selected as a stratified probability sample of each state. The purpose of stratification is to group together precincts with similar vote characteristics. A recent past election was used to identify all precincts as they existed for that election. The total vote in each precinct and the partisan division of the vote from this past race are used for the stratification. In addition, counties are used for stratifying the precincts. The total vote also is used to determine the probability of selection. Each voter in a state has approximately the same chance of being selected in the sample.
Who makes projections of the winning candidates?
Projections are made by Edison/Mitofsky and transmitted to each of the NEP members and subscribing news organizations. Edison/Mitofsky does not provide its information to the public. Each of the members has its own analysts who review the Exit Poll results and the tabulated data as it is collected. Each news organization makes its own decision about what to report to the public. All decisions are made after careful review by the analysts and are not automatic decisions made by a computer.
How are projections of winners made?
Projections of a winning candidate are based on models that use votes from three different sources -- Exit Poll interviews with voters, vote returns as reported by election officials from the sample precincts, and tabulations of votes by county. The models make estimates from all these vote reports. The models also indicate the likely error in the estimates. The best model estimate may be used to make a projection if it passes a series of tests.
When will projections be made?
Projections of a winning candidate are only made after all the polls in a state are closed and when the best model estimates show a clear winner. There will be no projections before the last polls in a state are closed.
How do absentee votes affect projections?
In a number of states significant numbers of voters cast their ballots before Election Day. They either cast an absentee ballot or they vote at voting locations set-up for voters in the weeks leading up to the election. The results of these absentee/early voters' interviews are combined with the Election Day Interviews. Instead, they are interviewed by telephone shortly before the election. They are asked the same questions as voters interviewed in the Exit Polls on Election Day.
What is the Margin of Error for an Exit Poll?
Every number estimated from a sample may depart from the official vote count. The difference between a sample result and the number one would get if everyone who cast a vote was interviewed in exactly the same way is called the sampling error. That does not mean the sample result is wrong. Instead, it refers to the potential error due to sampling. The margin of error for a 95% confidence interval is about +/- 3% for a typical characteristic from the national Exit Poll and +/-4% for a typical state Exit Poll. Characteristics that are more concentrated in a few polling places, such as race, have larger sampling errors. Other non sampling factors may increase the total error.
How many people will it take to conduct the Exit Polls and collect the vote at the Edison/Mitofsky sample precincts?
For a national election, almost 3,000 people will be required to do the job at Edison/Mitofsky. This includes Exit Poll interviewers, telephone operators to take their calls at election headquarters, reporters at the sample precincts to get the vote, developers to program the computers, systems specialists, election researchers, technical support at all sites, analysts reviewing the computations, support staff to manage the Exit Polls and management of the project. In addition the Associated Press will staff its operation with thousands of additional people.
Are these current models and procedures going to assure the public that there will be no mistakes?
Since Edison/Mitofsky began conducting exit polls for the National Election Pool in 2003, the news organizations using the Edison Mitofsky data have not made a single mistake in deciding a winner in any race.