U.S. flag

An official website of the United States government

Skip Header

2020 Census Evaluations & Experiments

2020 Census Evaluations & Experiments

Real-Time 2020 Administrative Record Census Simulation (Brown, et al.)

This project will conduct several real-time administrative record census simulations in 2020. It will use all administrative records ingested by the Census Bureau as of a certain date that provide information about the Census Day population. The project will be conducted in real-time in 2020, which will show how long it takes to execute an administrative record census and will highlight the most time-consuming parts of the process.

Administrative Record Dual-System Estimation (Mule, et al.)

This project will conduct an evaluation to determine if dual system estimates could be generated without conducting an independent post-enumeration survey. While the decennial census would continue to serve as the first source, this analysis would use administrative records as the second source. This evaluation would be able to assess if population coverage estimates of similar quality can be generated without having to conduct costly independent listings and independent interviews.

Extending the Decennial Census Environment to the Mailing Materials (Coombs, et al.)

This project will experiment with tapping into the unique environment surrounding the decennial census through the materials we use to contact households and to request self-enumeration. Specifically, the project will test the effect of nonmonetary inserts that promote the 2020 Census on self-response rates as well as mailing materials that incorporate elements and images developed by the 2020 Census communications campaign.

Contact Strategies Tailored to Populations Missed in an Administrative-Records-Only Census (Bates, et al.)

This project involves a series of geographically targeted contact strategy experiments that are tailored to three population segments known to be underrepresented in government administrative records. These experiments explore a mixture of interventions, such as those with a track record of success among hard-to-count populations as well as untested interventions possible only in a decennial census environment. Treatments may include incentives, targeted messaging, mode targeting, text message contact reminders, and customized web-instrument landing pages.

Social Media Evaluations on the Census Integrated Partnership and Communications Campaign (Garcia Trejo, et al.)

This project will explore experiments designed to better understand how social media— specifically Facebook—can be leveraged to spread awareness of, educate people on, and ultimately promote participation in the 2020 Census. Several experimental treatments will be examined, such as exploiting Facebook messages, social recruitment, “virtual” badges, or aneducational awareness campaign to determine whether they influence participation in the 2020 Census. The exact experiments to be included will depend on the level of engagement and availability of the Facebook Civic Engagement Team.

2020 Census Paid Media Experiments (Walejko, et al.)

This project involves conducting experiments to directly measure the impact of paid media on self-response, particularly for population groups that are underrepresented in administrative records. The experiments will measure the effects of local advertising buys for television, print, and radio; digital advertisements; and Spanish-language advertisements. The experiments will involve delayed advertising in the early months of the decennial communications campaign followed by as many advertisements as needed to “catch up” these groups (all markets will receive the same amount of advertising but at different times).

Evaluations of the Reengineered Address Canvassing Operation (Johnson)

This evaluation will focus on selected components of the reengineered Address Canvassing operation. Specifically, it will estimate certain types of errors that can occur during In-Field Address Canvassing and compare these estimates with results from previous studies. In addition, the evaluation will investigate the effectiveness of the In-Office Address Canvassing Interactive Review and the triggering process.

Research on Coverage of Underrepresented Populations in Anticipation of a Records-Based Census (Bruce, et al.)

The project will conduct modeling, evaluation, and experimental research during the 2020 Census to help understand potential similarities and differences between under-covered populations using traditional census data collection methods and records, and will evaluate innovations in the 2020 Census that targeted hard-to-count populations to understand how these innovations worked and what challenges were encountered. This proposal has several components meant to complement each other and to fill in gaps of understanding that we have about coverage of hard-to-count populations and the reasons they are missed.

Preparing for a Records-Based Census: Measuring Race, Ethnicity, Language, and Other Difficult Concepts (Ellis, et al.)

This project seeks to provide insights to improve the accuracy of a records-based, person-level census. The research is related to the measurement of hard-to-measure items, including race and ethnicity, from hard-to-count populations (including those who speak languages other than English) in support of a 2030 records-based census that includes a supplemental electronic survey of people either not covered in the administrative records or with record quality likely to be poor. The central issue in this proposal is the identification and reduction of measurement error for hard-to-measure items.

Evaluating Privacy and Confidentiality Concerns of Complete and Partial Respondents by Mode (Fobia, et al.)

This project will involve assessing respondents’ privacy and confidentiality concerns about responding to the census generally, as well as assessing concerns of certain types of respondents with a follow-up questionnaire. We will ask questions that surround three themes: 1) beliefs and knowledge about the census’s privacy and confidentiality practices, 2) opinions on the use of administrative records, and 3) concerns about particular census questions. Targeted respondents will include those with complete and partial web responses, as well as some mail responses and telephone responses.

Evaluation of the Optimization of Self-Response in the 2020 Census (Bentley, et al.)

This project seeks to understand the net impacts of the Optimizing Self-Response innovation area in the 2020 Census. In particular, the focus is on evaluating the quantitative impacts of the mailing strategy and the overall influence of the internet response option—especially the non-ID option. The evaluation will involve two experimental treatments to measure the impact of the 2020 Census innovations for self-response. A sample of housing units will receive the 2010 Census mail strategy and a sample of households will have their mail contact strategy switched between Internet Choice and Internet First.

Nonresponse Followup Crowdsourcing (Michael, et al.)

This project investigates the ability to significantly reduce enumeration costs though crowdsourcing information about vacant units though existing internet-based self-response systems. The study is based on a simple concept—significantly reduce nonresponse follow-up costs through the use of crowdsourcing (information contributed by the general public using the internet and without compensation). This will help identify vacant housing units sooner in the survey life cycle through the use of a vacant/not-vacant proxy at the beginning (advance proxy) rather than at the end of the process. After the user completes and submits their internet-based self-response form, a sample of respondents will be invited to access an application that shows a map centered around their home (based on the address provided), along with a message about how this will save taxpayer money. We will ask users to select any vacant housing units (houses, apartments, etc.) in their area.

Evaluation of 2020 Census Reengineered Field Operations (TBD)

This project does not yet have an approved proposal. The DROM Working Group has approved a space for this study under the assumption that the Census Bureau is expected to evaluate this major innovation area and how it performed in the 2020 Census. This study will be developed and assigned to a team.

Page Last Revised - December 16, 2021
Is this page helpful?
Thumbs Up Image Yes Thumbs Down Image No
255 characters maximum 255 characters maximum reached
Thank you for your feedback.
Comments or suggestions?


Back to Header