0 votes
asked ago by (35.2k points)
March 1 -- The Census Bureau invites public comment to OMB on its proposal for the Ask U.S. Panel (“the Panel”), a probability-based nationwide nationally representative survey panel for tracking public opinion on a variety of topics of interest to numerous federal agencies and their partners, and for conducting experimentation on alternative question wording and methodological approaches. The Ask U.S. Panel may also be used to collect nationwide rapid-response data to address emerging data needs. Public comments are due by March 31, 2022.
 
The Ask U.S. Panel (“the Panel”) will be a nationally representative survey panel for tracking public opinion on a variety of topics of interest to numerous federal agencies and their partners, and for conducting experimentation on alternative question wording and methodological approaches. The Panel may also be used to collect national-representative rapid-response data, as a complement to that currently collected by the Household Pulse Survey. The Panel will be developed through a multi-year effort. The first two years will focus on developing the overall design and conducting a large-scale field Pilot Test. Nationally representative data collection based on a probability sample of U.S. adults will begin in the third year. The current request is limited to the Pilot Test. A future request will contain details for the full Panel.

A key objective of the Panel will be to produce representative and reliable statistics on a rapid turnaround suitable for use by federal agencies. Ultimately, the Panel seeks to make it possible to release data that meets standards of the Federal Statistical Agencies and the Office of Management and Budget (OMB). At the same time, the Panel will ensure availability of frequent data collection for nationally representative estimates on a variety of topics and a variety of subgroups of the population.

The Panel is an interagency effort, with representatives from Census, the Department of Agriculture's Economic Research Service, the Bureau of Labor Statistics, the National Center for Health Statistics, the National Center for Science and Engineering Statistics, the National Center for Education Statistics, the Department of Defense, Department of Transportation, Department of Labor and the Social Security Administration guiding its design, content and methodological rigor, that will be used to meet data needs across the Federal Statistical System.

Data will be collected in two distinct phases. In Phase 1, a pilot, consisting of approximately ten percent of the final panel (1,700 people) will be recruited and surveyed as a proof-of-concept to refine methods. In Phase 2, the full panel will be recruited and surveyed using methodology refined during Phase 1. This 30-day notice seeks clearance for the Phase 1 Pilot. A future 30-day notice will outline specific plans for Phase 2.  
 
In Phase 1, ten percent of the panel (1,700 people) will be recruited and surveyed as a proof-of-concept to refine methods. In Phase 2, the remainder of the panel (17,000 people) will be recruited and surveyed using methodology refined during Phase 1. This package describes both sets of data collection.
 
The programs that provide essential statistical information for use by governments, businesses, researchers, and the public are carried out by independent agencies and spread across several departments within an agency. These agencies are referred to as Federal Statistical Agencies and they serve the public by providing independent, non-partisan data about the country. This clearance request aims to pilot test methods for an online research panel that could be available for robust public opinion, methodological research, and rapid-response data collection for the common good.  

This long-term objective supports the recommendations of the Commission on Evidence Based Policymaking (https://www2.census.gov/adrm/fesac/2017-12-15/Abraham-CEP-final-report.pdf) in several ways:  

Promotes a multi-year learning agenda that supports the generation and use of data as evidence;
Enables coordination of the public sector’s evidence-building activities; and
Streamlines the approval processes for new data collections and uses existing flexibilities in procurement policy.

The statistical community at large has been struggling with near-real-time measurement of key areas, including:

Privacy and confidentiality opinions and preferences;
Public attitudes towards data collection and use of administrative records;
Methodological choices regarding online instrument design decisions;
Survey design choices regarding wording and contact timing;  
Messaging strategies to increase response rates; and
Novel data collection needs due to emerging national events, like the COVID-19 pandemic.

OMB Standard 1.4 from the Office of Management and Budget, Standards and Guidelines for Statistical Surveys, requires Federal Agencies to appropriately pretest data collection instruments prior to fielding them. The Panel will eventually offer a platform on which to conduct pretests with a nationally representative audience.

Existing commercial online panel alternatives typically fail to meet OMB’s standards for transparency, which require sufficient detail on data collection and estimation methods to allow reproducibility, and sufficient detail on data quality and representativeness to enable OMB to evaluate the fitness for purpose.
 
Access to a pool of pre-recruited panel members, including historically undercounted populations, will help researchers at the Census Bureau (Census) and other Federal Agencies better understand public opinion related to federal data collection, including administrative data matching, privacy, and confidentiality, and will facilitate methodological testing. The Panel will consist of an entirely new, representative probability sample of U.S. adults who are not members of an existing survey panel. The addition of targeted subgroups and general replenishment to supplement the existing panel will likely be desirable in the future.  

The Pilot will answer critical methodological questions about ability to recruit and retain historically undercounted population groups in the panel. The Pilot will provide proof of concept for the use of tablets by non-internet households, the use of alternate (in-person, phone, text) nonresponse follow-up, and the effects of those methodologies on retention. Results from the Pilot will be used to refine the methodology a future full panel.  

The baseline survey will pilot collecting demographic data that would later be used to assess representativeness of the panel and to understand potential nonresponse bias in future surveys. Items on the baseline survey would also be available for weighting adjustment and subsampling in future surveys.

The first topical survey that will be used as a proof-of-concept will be developed from the Census Barriers, Attitudes and Motivators Survey (CBAMS). The CBAMS questionnaire will be adapted from that used prior to the 2020 Census and will be used to measure intercensal mindsets towards the Census Bureau and Census Bureau data collections. The Pilot topical survey will be a field test of the survey instrument to be used to observe barriers, attitudes, and motivators towards the Census Bureau. This questionnaire will be submitted through a future 30-day notice.  
 
We received a total of seven comments. Two comments were not substantively related to this data collection. One commenter focused on the distinction in representation between urban and rural participants in the panel. We will address this concern by analyzing pilot test data and, based on the outcome of this analysis, potentially incorporating the findings into future plans (to be presented in future 30-day notices). Another commenter recommended that the Census Bureau use this new platform to investigate the undercount of young children. Consideration will be given to this topic for inclusion in a Pilot Test topical survey that will be presented in a future 30-day notice.

Several commenters suggested that the current effort is duplicative of existing products in the marketplace. According to OMB, existing commercial online panel alternatives typically fail to meet OMB’s standards for transparency, which require sufficient detail on data collection and estimation methods to allow reproducibility, and sufficient detail on data quality and representativeness to enable OMB to evaluate the fitness for purpose. This panel is not duplicative of existing commercial online panel alternatives, since it is being designed in a manner that will meet OMB’s standards for transparency by providing sufficient detail on data collection and estimation methods to allow reproducibility as well as sufficient detail on data quality and representativeness to enable OMB to evaluate fitness for purpose. Results from the pilot test will be presented in any subsequent requests for data collection to OMB via additional 30-day public notices.
 
Ask U.S. Panel Phase 1 Pilot proposal: https://www.reginfo.gov/public/do/PRAViewICR?ref_nbr=202202-0607-008 Click IC List for pilot survey instrument, View Supporting Statement for technical documentation. Submit comments through this site.
FR notice inviting public comment: https://www.federalregister.gov/d/2022-04222

For AEA members wishing to submit comments, "A Primer on How to Respond to Calls for Comment on Federal Data Collections" is available at https://www.aeaweb.org/content/file?id=5806

Please log in or register to answer this question.

...