This study is provided by ICPSR. ICPSR provides leadership and training in data access, curation, and methods of analysis for a diverse and expanding social science research community.

National Election Pool General Election Exit Polls, 2006 (ICPSR 4684) RSS

Principal Investigator(s):


This data collection consists of election data collected through questionnaires completed by voters as they left their polling places on election day, November 7, 2006, as well as through pre-election telephone interviews conducted between October 27, 2006 and November 5, 2006, in states with large populations of absentee and early voters. Part 1 contains national data collected from a sample of 250 polling locations representing all 50 states. Parts 2-33 contain data collected from individual state surveys conducted in 32 states including Arizona, California, Connecticut, Florida, Georgia, Hawaii, Illinois, Maine, Maryland, Massachusetts, Michigan, Minnesota, Missouri, Montana, Nebraska, Nevada, New Jersey, New Mexico, New York, North Dakota, Ohio, Pennsylvania, Rhode Island, Tennessee, Texas, Utah, Vermont, Virginia, Washington, West Virginia, Wisconsin, and Wyoming. Both the national and state surveys asked a series of questions about electoral choices in the relevant gubernatorial, senatorial, and congressional elections, how long prior to the election voters decided on their candidate, the factors that influenced their choice, whether they supported state-specific proposals such as raising the minimum wage and banning same-sex marriage, and how confident they were that votes in their state would be counted accurately. Views were sought on the war in Iraq, illegal immigration, the economy, the Democratic and Republican parties, and whether respondents approved of the way President George W. Bush was handling the presidency. Other questions addressed respondents' financial situation, for whom they voted in the 2004 presidential election, and whether they identified themselves as born-again or evangelical Christians. In addition, national sample respondents gave their opinions on the direction of the country, the Bush Administration, the United States Congress, and whether life would be better for the next generation of Americans, while individual state respondents gave their opinions of local politicians. Demographic variables include age, sex, race, ethnicity, education level, household income, marital status, sexual orientation, labor union membership, religious affiliation, frequency of religious attendance, political party affiliation, political philosophy, and whether children lived in the household.

Access Notes

Study Description


National Election Pool, Edison Media Research, and Mitofsky International. National Election Pool General Election Exit Polls, 2006. ICPSR04684-v1. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2007-05-04. doi:10.3886/ICPSR04684.v1

Persistent URL:

Export Citation:

  • RIS (generic format for RefWorks, EndNote, etc.)
  • EndNote XML (EndNote X4.0.1 or higher)

Scope of Study

Subject Terms:   Bush Administration (George W., 2001-2009), Bush, George W., candidates, congressional elections, election forecasting, exit polls, gubernatorial elections, Hispanic or Latino origins, illegal immigrants, Iraq War, national economy, national elections, presidential elections, presidential performance, referendum, state elections, terrorism, United States Congress, voter preferences, voter turnout, voters, voting behavior, voting precincts

Geographic Coverage:   Alabama, Alaska, Arizona, Arkansas, California, Colorado, Connecticut, Delaware, Florida, Georgia, Hawaii, Idaho, Illinois, Indiana, Iowa, Kansas, Kentucky, Louisiana, Maine, Maryland, Massachusetts, Michigan, Minnesota, Mississippi, Missouri, Montana, Nebraska, Nevada, New Hampshire, New Jersey, New Mexico, New York (state), North Carolina, North Dakota, Ohio, Oklahoma, Oregon, Pennsylvania, Rhode Island, South Carolina, Tennessee, Texas, United States, Utah, Vermont, Virginia, Washington, West Virginia, Wisconsin, Wyoming

Time Period:  

  • 2006

Date of Collection:  

  • 2006-10-27--2006-11-07

Unit of Observation:   individual

Universe:   Voters casting a ballot in the 2006 United States general election.

Data Types:   event/transaction data, survey data

Data Collection Notes:

The data available for download are not weighted and users will need to weight the data prior to analysis. Unweighted tabulations will be seriously misleading and should not be used.

Additional information about sampling, interviewing, and sampling error may be found in the codebook.

The formats of several variables were adjusted to fit the width of the values present in these variables.

In 2006, as in previous midterm elections, statewide exit polls were not conducted in every state. Therefore, a combined data file representing the results from all 50 states and the District of Columbia similar to the one generated in 2004 was not able to be produced.

Precincts from all 50 states were eligible to be selected in the national sample, but through the random selection process, four states (Hawaii, South Dakota, Vermont, and Wyoming) did not come up with a precinct in the final sample.

The CASEID variable was created for use with online analysis.


Sample:   The statewide exit poll samples were selected in two stages. First, a probability sample of voting precincts within each state was selected that represented the different geographic areas across the state and the vote by party. Precincts were selected with a probability proportionate to the number of voters in each precinct, with the exception of precincts with large minority populations, which were sampled at a higher rate that other precincts in some states. Second, within each precinct, voters were sampled systematically throughout the voting day at a rate that gave all voters in a precinct the same chance of being interviewed. The national sample was formed from a subsample of exit poll precincts in each of the 32 states that conducted state surveys, as well as from a sample of precincts in the 18 states without state surveys. In states with large populations of absentee and early voters, pre-election telephone interviews were conducted of people who said they had either already voted by mail using an absentee ballot or had voted in person at an early voting location. Households in all telephone polls were selected using random-digit dialing (RDD). On election day, the results from the absentee/early voter telephone surveys were combined with the data from the exit polls to ensure that those two groups were represented in the data in the same proportion as in the actual vote totals.

Weight:   The data contain a weight variable (WGT) that should be applied in all analyses. Unweighted tabulations will be seriously misleading and should not be used. The exit poll results are weighted to reflect the complexity of the sampling design and take into account the different probabilities of selecting a precinct and of selecting a voter within each precinct. For example, minority precincts that were selected at a higher rate received a smaller weight than other precincts of the same size. An adjustment was made for voters who were missed or refused to be interviewed, which was based on their observed age, race, and sex. Respondents were also weighted based upon the size and distribution of the final tabulated vote within geographic regions of the state or the nation. The telephone survey results were weighted before being combined with the exit poll data to reflect the probabilities of selection and to reflect demographic characteristics in that state. The demographic weighting was based on all respondents 18 years of age or older selected in the sample regardless of whether they voted absentee/early or not.

Mode of Data Collection:   on-site questionnaire, telephone interview

Extent of Processing:  ICPSR data undergo a confidentiality review and are altered when necessary to limit the risk of disclosure. ICPSR also routinely creates ready-to-go data files along with setups in the major statistical software formats as well as standard codebooks to accompany the data. In addition to these procedures, ICPSR performed the following processing steps for this data collection:

  • Created online analysis version with question text.


Original ICPSR Release:  

Found a problem? Use our Report Problem form to let us know.