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.

California Special Election Exit Poll and Phone Survey, 2003 (ICPSR 4187) RSS

Principal Investigator(s):


Most of the data in the California Special Election Exit Poll and Phone Survey, 2003, were collected through interviews conducted with voters exiting polling places in California on the day of the gubernatorial recall election. Early and absentee voters were polled via the telephone from September 29, 2003, through October 5, 2003. Respondents were polled for their vote in the recall election, when they decided to vote for that choice, their opinions of Governor Gray Davis, their choice for governor if Gray Davis were removed from office, the most important factor in choosing their candidate, and for whom they would vote if there were only two candidates for governor, Cruz Bustamante (Democrat) and Arnold Schwarzenegger (Republican). Respondents were also asked to give their opinions of candidates Bustamante, Tom McClintock (Republican), and Arnold Schwarzenegger, and whether or not the latter addressed the issues in adequate detail. Other candidates included Peter Miguel Camejo (Green Party) and Arianna Huffington (Independent). Specific questions about the voting process concerned problems with the voting equipment and opinions of the recall process. Respondents were asked questions about state issues such as their vote on Proposition 54 (banning state and local governments from classifying anyone by race or ethnicity), the condition of the state economy, whether the budget deficit could be resolved without raising taxes, issuing driver's licenses to illegal immigrants, and the California law extending domestic partner benefits to homosexual couples. Additional questions queried respondents on their position on abortion and how George W. Bush was handling his job as president of the United States. Background information includes age, education, frequency of voting in previous elections, household income in 2002, labor union membership within the household, political ideology, political party affiliation, race, sex, sexual orientation, and whether the respondent is of Mexican or Hispanic descent.

Access Notes

Study Description


National Election Pool, Edison Media Research, and Mitofsky International. California Special Election Exit Poll and Phone Survey, 2003. ICPSR04187-v1. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2005-07-29. doi:10.3886/ICPSR04187.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, George W., Davis, Gray, domestic partnership, elections, exit polls, gays and lesbians, gubernatorial elections, illegal immigrants, Schwarzenegger, Arnold, state elections, state government, state politics, voter interest, voter preferences, voting behavior

Geographic Coverage:   California, United States

Time Period:  

  • 2003-09--2003-10

Date of Collection:  

  • 2003-09-29--2003-10-07

Unit of Observation:   individuals

Universe:   California voters who voted in the gubernatorial recall election of 2003.

Data Types:   survey data

Data Collection Notes:

Variable RCLGOV is a cross-tabulation of the variables RECALL and REPLACE. Based on running the cross tabulation between the two variables, Value 9, which previously did not have a code, was coded as "Missing."

Questionnaires in Spanish as well as in English were available in every precinct in which Hispanics represented 20 percent or more of the total population.

A blank represents an omission or a non-response to an item. However, a blank can also represent that the respondent was not asked the question.


Sample:   The samples were selected in two stages. First, a probability sample of voting precincts within the state was selected that represented 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. Within each precinct, voters were sampled systematically throughout the voting day at a rate that gives all voters in a precinct the same chance of being interviewed.

Weight:   Weights should be applied in all analyses. The exit poll results are weighted to reflect the complexity of the sampling design. The weighting takes into account the different probabilities of selecting a precinct and of selecting a voter within each precinct.

Mode of Data Collection:   personal interview, telephone interview


Original ICPSR Release:  

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