Principal Investigator(s): National Election Pool; Edison Media Research; Mitofsky International
The data were collected through face-to-face and telephone interviews conducted with voters in twenty-two states that held primaries and one state that held a caucus to choose the Democratic candidate for president of the United States. The candidates were Senator and former United States Ambassador Carol Moseley Braun, retired United States Army General Wesley Clark, New Hampshire Governor Howard Dean, Senator John Edwards, Senator Dick Gephardt, Senator John Kerry, United States Representative Dennis Kucinich, Senator Joe Lieberman, and Reverend Al Sharpton. Early and absentee voters were polled via the telephone during the week leading up to an individual state's primary. Election day voters were interviewed in person as they exited polling places on their state's primary days. Respondents were asked which candidate they voted for in the primary, when and why they decided on that candidate, and what one quality and one issue mattered most in choosing that candidate. They were polled on the candidates and the candidates' likelihood of defeating the incumbent, President George W. Bush. Also, they were asked whether they voted for the candidate who they thought had the best chance of defeating George W. Bush or the candidate they agreed with most on important issues, whether they had seen candidates' campaign ads and/or Web sites, and whether they were confident their vote would be counted accurately. Respondents were asked to assess the condition of the nation's economy, their personal financial situation compared to four years ago, their level of concern about another terrorist attack occurring in the United States, and the safety of the country as a result of military action in Iraq. Additional opinions were gathered concerning the Bush administration and its policies and decisions and United States Senator John McCain from Arizona. Further questions addressed topics such as whether the tax cuts implemented under the Bush administration should be adjusted or eliminated and whether respondents worried that someone in their household would lose their job. Background information on respondents includes age, education, frequency of religious service attendance, Hispanic descent, labor union membership status within the household, marital status, personal voting history, political ideology, political party affiliation, race, religious orientation, sex, sexual orientation, total household income in 2003, and whether anyone in the household had served in the military.
These data are available only to users at ICPSR member institutions. Because you are not logged in, we cannot verify that you will be able to download the data.
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.
WARNING: Because this study has many datasets, the download all files option has been suppressed, and you will need to download one dataset at a time.
National Election Pool, Edison Media Research, and Mitofsky International. National Election Pool Democratic Presidential Preference Primary Exit Polls, 2004. ICPSR04183-v1. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2005-06-02. doi:10.3886/ICPSR04183.v1
Persistent URL: http://doi.org/10.3886/ICPSR04183.v1
Scope of Study
Subject Terms: Bush Administration (George W., 2001-2009), Bush, George W., candidates, Clark, Wesley, Dean, Howard, Democratic Party (USA), Edwards, John, election forecasting, exit polls, gay marriage, Gephardt, Dick, homosexual relationships, Iraq War, Kerry, John, Kucinich, Dennis, Lieberman, Joe, marriage, Moseley-Braun, Carol, NAFTA, national economy, national elections, national security, presidential candidates, presidential elections, primaries, primary elections, Sharpton, Al, tax cuts, terrorist attacks, trade, trade relations, vote count, voter preferences, voter turnout, voters, voting behavior
Geographic Coverage: Arizona, California, Connecticut, Delaware, Florida, Georgia, Iowa, Louisiana, Maryland, Massachusetts, Mississippi, Missouri, New Hampshire, New York, Ohio, Oklahoma, Rhode Island, South Carolina, Tennessee, Texas, United States, Vermont, Virginia, Wisconsin
Date of Collection:
Unit of Observation: individuals
Universe: United States voters on Primary Day 2004 in 23 states.
Data Types: survey data
Data Collection Notes:
One key variable, known as the "backside" variable, exists on all surveys that used a two-sided questionnaire. It can be found in column 16 of all states except Iowa. When BACKSIDE = 1, there was at least one response on the reverse side of the questionnaire, indicating that the respondent turned the questionnaire over. This allows the researcher who is analyzing a question that appears on the reverse to omit respondents who did not turn the questionnaire over. For all respondents where BACKSIDE = 2, responses to any question that appeared on page 2 of the questionnaire are coded as system missing in the SPSS file and are blank in the ASCII file.
In New Hampshire, there were two separate versions of the exit poll questionnaire. Each respondent received only one version. Respondents were randomly assigned to receive each version, with approximately half of the respondents in each precinct answering each version. Some questions were common to both versions, but many appear only on one version.
Sample: The samples were selected in two stages. First, a probability sample of voting precincts within each state was selected that represents the different geographic areas across the state and the partisan make-up of the state. Precincts were selected with a probability proportionate to the number of voters in each precinct. Each voter in a state had the same chance to be selected. There was one exception. In some states, precincts that had large minority populations were sampled at a higher rate than other precincts. The sample weighting adjusts the representation of these precincts to their correct share of the total vote. 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.
Weight: The data contain weights that should be applied in all analyses.
Mode of Data Collection: personal interview, telephone interview
Original ICPSR Release: 2005-06-02
Related Publications (?)
- Citations exports are provided above.
Export Study-level metadata (does not include variable-level metadata)