2008 Time Series Study
About the Dataset
- Type of study: ANES Time Series Study
- Number of waves: 2 (pre-election wave, post-election wave)
- Completions: 2,322 pre-election; 2,102 post-election
- Sample: all fresh cross-section
- Modes used: face-to-face; ACASI
- Instrument format: laptop CAPI; laptop ACASI (with headphones)
- Weights: V080101/V080101a (pre); V080102/V080102a (post); V080103 (household)
- Additional files: redacted open-end responses; open-end response codes
- Associated studies or derivative files: none
Study Content Highlights
In addition to content on electoral participation, voting behavior, and public opinion, the 2008 ANES Time Series Study contains questions in other areas such as media exposure, cognitive style, and values and predispositions. Special-interest and topical content provided significant coverage of foreign policy, including the war on terrorism and the war in Iraq. In addition, the study carried expanded instrumentation on organizational membership, unemployment, the federal budget, modern sexism, and race and gender politics. The Post-Election interview also included Module 3 from the Comparative Study of Electoral Systems (CSES).
Study Design Highlights
Among many notable design features was the inclusion of African-American and Latino oversamples of respondents. The use of half-sampling was used throughout the study to “splice” core or standard questions alongside revised versions. To reduce social desirability pressures, a section of questions on select topics was, for the first time in the Time Series, self-administered [Audio Computer-Assisted Self Interviewing or ACASI]. This meant that the interviewer turned the laptop to face the respondent who could then read and/or hear questions (onscreen and/or using headphones) to enter response choices without communicating answers to the interviewer. Included in the post-election survey was an implementation of the Affect Misattribution Procedure (AMP), a method to measure implicit attitudes. In the ANES 2008 Time Series Study, the AMP method was used to measure implicit attitudes toward Blacks.
Pre-election interviews 73 minutes in length were conducted September 2 through November 3, 2008. No interviewing was conducted on Election Day, November 4. Post-election interviews 91 minutes in length were administered November 5 through December 30, 2008. Randomization, employed for selection of half-samples to reduce overall interview length, and for question order within batteries, was implemented by the Computer Assisted Interviewing (CAI) instrumentation.
59.5% is what AAPOR calls Response Rate 1 (RR1) for the survey, which is the minimum response rate. It is referred to as the “minimum” because it assumes that in all households at which the eligibility of residents was not determined, at least one eligible adult lived there. AAPOR Response Rate 3 (RR3) assumes that in households at which eligibility was not determined, the proportion of households containing an eligible adult was the same as that proportion among households at which eligibility was determined. That response rate is 63.7%. The maximum response rate, AAPOR’s RR5, is 78.2% and is computed by assuming that no eligible adult lived in any of the households in which eligibility was not determined.
For the post-election survey, the minimum rate (AAPOR RR1) is 53.9 percent; the estimated rate (AAPOR RR3) is 57.7 percent; the maximum rate (AAPOR RR5) is 70.8 percent. The re-interview rate is 90.5.
Weights Summary
There are two sets of sample weights. The first set of weights is centered at a mean of 1.0; these are variable V080101 (pre-election) and V080102 (Post-election). The second set of weights represent population V080101a (pre-election) and V080102 (Post-election). The pre-election sample weights are the product of the household non-response adjustment factor by age and education. The post-election sample weights are adjusted for attrition.
Additional Files
Texts of open-end responses from this study have been redacted and are available in a separate file from a link on this page.
Coded variables for the open-end responses for the ANES 2008 Time Series Study are not present in the study’s release data. The codings have been conducted independently by the study’s PIs, Jon Krosnick and Arthur Lupia, however all materials from the codings,including data and documentation, are posted by ANES from a link on this page.
Associated Studies or Derivative Files:
No other studies or derivative files are associated with this study. (An ANES derivative file is a file which merges together related ANES studies.)