ANES 2020 Time Series Study (ICPSR 38034)

Version Date: Jul 13, 2021

Cite this study |

Principal Investigator(s):
American National Election Studies; University of Michigan; Stanford University

Series:

https://doi.org/10.3886/ICPSR38034.v1

Version V1

Slide tabs to view more

Alternate Title

American National Election Study, 2020: Pre- and Post-Election Survey

Summary

This study is part of the American National Election Study (ANES), a time-series collection of national surveys fielded continuously since 1948. The American National Election Studies are designed to present data on Americans' social backgrounds, enduring political predispositions, social and political values, perceptions and evaluations of groups and candidates, opinions on questions of public policy, and participation in political life. As with all Time Series studies conducted during years of presidential elections, respondents were interviewed during the two months preceding the November election (Pre-election interview), and then re-interviewed during the two months following the election (Post-election interview). Like its predecessors, the 2020 ANES was divided between questions necessary for tracking long-term trends and questions necessary to understand the particular political moment of 2020. The study maintains and extends the ANES time-series 'core' by collecting data on Americans' basic political beliefs, allegiances, and behaviors, which are so critical to a general understanding of politics that they are monitored at every election, no matter the nature of the specific campaign or the broader setting. This 2020 ANES study features a fresh cross-sectional sample, with respondents randomly assigned to one of three sequential mode groups: web only, mixed web (i.e., web and phone), and mixed video (i.e., video, web, and phone). The new content for the 2020 pre-election survey includes coronavirus pandemic, election integrity, corruption, impeachment, immigration and democratic norms. The pre-election survey also includes protests and unrest over policing and racism. The new content for the 2020 post-election survey includes voting experiences, anti-elitism, faith in experts or science, climate change, gun control, opioids, rural-urban identity, international trade, transgender military service, social media usage, misinformation, perceptions of foreign countries and group empathy. Phone and video interviews were conducted by trained interviewers using computer-assisted personal interviewing (CAPI) software on computers. Unlike in earlier years, the 2020 ANES did not use computer-assisted self interviewing (CASI) during any part of the interviewer-administered modes (video and phone). Rather, in interviewer-administered modes, all questions were read out loud to respondents, and respondents also provided their answers orally. Demographic variables include respondent age, education level, political affiliation, race/ethnicity, marital status, and family composition.

Citation

American National Election Studies, University of Michigan, and Stanford University. ANES 2020 Time Series Study. Inter-university Consortium for Political and Social Research [distributor], 2021-07-13. https://doi.org/10.3886/ICPSR38034.v1

Export Citation:

  • RIS (generic format for RefWorks, EndNote, etc.)
  • EndNote

Funding

National Science Foundation (SES-1835721, SES-1835022)

Subject Terms

Geographic Coverage

Smallest Geographic Unit

none

Distributor(s)

Inter-university Consortium for Political and Social Research
Hide

Time Period(s)

2020-08-18 -- 2020-11-03, 2020-11-03 -- 2021-01-04

Date of Collection

2020-08-18 -- 2020-11-03, 2020-11-03 -- 2021-01-04

Data Collection Notes

  1. For further information please see the ANES Data Center website.

Hide

Study Purpose

The main goal of the ANES Time Series studies is to allow a broad cross-section of scholars, citizens, policy makers, and journalists to analyze high quality survey data pertinent to important electoral questions such as voters' choice and turnout, public opinion and political participation, and other related matters.

Study Design

Data collection for the ANES 2020 Time Series Study pre-election interviews began in August 2020 and continued until Election Day, Tuesday (November 3). Post-election interviews began soon after the election and continued through the end of December. This field period began earlier than the traditional ANES field period, which typically starts the day after Labor Day and concludes the day before Election Day.

The ANES 2020 Time Series Study features a fresh cross-sectional sample, with respondents randomly assigned to one of three sequential mode groups: web only, mixed web (i.e., web and phone), and mixed video (i.e., video, web, and phone). The study also features re-interviews with 2016 ANES respondents (conducted by web), and post-election surveys with respondents from the General Social Survey (GSS). The current release of the dataset does not include GSS participants; data from GSS participants will be provided in a future release of the data.

Sample

The 2020 ANES survey used a contactless, mixed-mode design that was created in response to challenges related to the COVID-19 pandemic. The pandemic made face-to-face interviewing unfeasible in 2020, and no in-person interviewing was done. Instead, a sequential mixed-mode design was implemented that included self-administered online surveys, live video interviews conducted online, and telephone interviews. Further sampling information can be found in the user guide.

Time Method

Time Series: Discrete

Universe

United States citizens age 18 or older.

Unit(s) of Observation

Individual

Data Type(s)

Mode of Data Collection

Response Rates

The response rate, using the American Association for Public Opinion Research (AAPOR) formula for the minimum response rate (known as AAPOR Response Rate 1) on the pre-election interview, was 36.7 percent overall for the fresh cross-sectional component of the sample (the web-only, mixed web, and mixed video combined). The minimum response rates for the three components individually were 37.8 percent for web-only, 39.7 percent for mixed web, and 27.6 percent for mixed video. The estimated overall response rates based on the observed rate of eligibility (known as AAPOR Response Rate 3) on the pre-election interview were 42.1 percent for the web-only sample group, 44.2 percent for the mixed web group, 31.0 percent for the mixed video group, and 40.9 percent overall for the fresh cross-sectional component. The pre-election re-interview rate for the 2016-2020 panel cases was 77.9 percent. Pre-election interviews were considered sufficiently complete to be counted as completions for weighting and for calculation of the response rate when the survey was administered through item SELFGEND_GENDTYP. The estimated AAPOR Response Rate 1 for the pre-election interview without the sufficient partial interviews was 37.1 percent for web-only, 39.0 percent for mixed web, 27.3 percent for mixed video, and 36.1 percent overall for the fresh cross-sectional component. Post-election re-interviews were completed with 90.0 percent of pre-election participants overall. These re-interview rates were 94.0 percent for the ANES 2016 sample group, 88.1 for the web-only group, 88.7 for the mixed web group, 84.6 for the mixed video group, and 87.9 overall for the fresh cross-sectional component.

Hide

Original Release Date

2021-07-13

Version History

2021-07-13 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:

  • Checked for undocumented or out-of-range codes.

Hide

Weight

The preliminary release of the dataset includes 14 draft post-stratified weight variables. A description of these weights is included in the user guide/codebook.

Weights should be used in analyses to accurately represent the population. For correct standard errors, users should employ procedures that take into account the complex sampling design.

Hide

Notes