Dec. 20, 2021

 In November, the U.S. Census Bureau announced it would delay the release of the 2016-2020 American Community Survey (ACS) 5-year data, originally scheduled for December 2021, due to the impacts of COVID-19 on data collection. We continue to make progress towards a mid- to late-March 2022 data product release.  

Since November, we have refined our methodology to reduce the impact of the nonresponse bias due to the COVID-19 pandemic. The methodology improves the 2020 data input by comparing characteristics for responding and nonresponding households using administrative, third-party and decennial census data. The 2020 input data are then integrated with the inputs from 2016, 2017, 2018, and 2019, that were processed using the standard ACS methodology, in order to provide the basis for creating our 5-year data products. 

The Census Bureau recognizes the critical importance of the ACS 5-year data, in particular, on government and business decision-making and the need for quality ACS data for that purpose. Over the next month, the Census Bureau will conduct quality reviews to ensure that this methodology is performing appropriately at all levels of geography and that the resulting data meet our quality standards.   

We expect to provide another update early in 2022.  

November 30, 2021

The U.S. Census Bureau today released experimental 1-year estimates from the American Community Survey (ACS), one of the nation’s most comprehensive sources of population and housing information about the United States. The experimental data cover a limited number of topics for the nation, all 50 states and the District of Columbia. A technical working paper, blog and 1-Year Public Use Microdata Sample (PUMS) experimental data were also released.

The Census Bureau typically releases three different sets of ACS data estimates each year in the form of 1-year and 5-year period data sets, as well as 1-year supplemental estimates. Our release is different this year due to the impacts of the COVID-19 pandemic, which disrupted ACS data collection in 2020. Given the limitations, we were unable to collect information from certain segments of the population, as explained in the previously released blog and analytical report, An Assessment of the COVID-19 Pandemic’s Impact on the 2020 ACS 1-Year Data. 

The people who did respond to the survey had significantly different social, economic and housing characteristics from those who didn’t, resulting in nonresponse bias in the data. The Census Bureau determined the standard 2020 ACS 1-year estimates did not meet statistical quality standards and decided to ultimately release estimates as an experimental product.

The report, Addressing Nonresponse Bias in the American Community Survey During the Pandemic Using Administrative Data, details modifications to the ACS weighting procedures for the 2020 experimental data. Weighting can mitigate the effects of nonresponse bias, which occurs when the characteristics of people who complete the survey (respondents) differ from those of people who do not complete the survey (nonrespondents). The blog provides an overview of the report and experimental methodology.

The 2020 1-year PUMS files include experimental weights and data on approximately 1% of the U.S. population while protecting the confidentiality of survey respondents. The files provide population and housing characteristics down to Public Use Microdata Areas (PUMAs), which are special nonoverlapping areas that partition each state into contiguous geographic units. They are drawn after each decennial census so that they contain no fewer than 100,000 people.

The Census Bureau does not recommend comparing the 2020 ACS 1-year experimental estimates with our standard ACS estimates or the decennial census, or comparing the 2020 1-year PUMS data with standard pre-tabulated products or PUMS-based estimates from previous years. In addition, because the experimental weighting procedure was designed primarily to produce experimental estimates for states, estimates for PUMAs should be used with caution as the experimental weights are not optimized to produce estimates for these areas.

Recognizing the difficulty that the lack of standard 1-year ACS estimates will have on data user communities, the Census Bureau previously provided a list of resources offering technical data assistance. Additional resources are available in the press kit. More information on changes to the 2020 ACS 1-year release is available here. 

The Census Bureau announced in early November that the 2016–2020 ACS 5-year data release originally targeted for December 2021 had been delayed. Additional time is needed to continue refining our methodology to minimize the impact of nonresponse bias on the 5-year estimates.

November 17, 2021

What: The U.S. Census Bureau has announced a webinar to explain and answer questions about the release of estimates from the 2020 American Community Survey (ACS) 1-year data using experimental weights. The ACS is one of the most comprehensive sources of information about the U.S. population, providing key demographic, social, economic and housing statistics. The COVID-19 pandemic significantly disrupted the ability to reach people and limited their ability to participate in the 2020 ACS. Therefore, the Census Bureau will release experimental data instead of the standard 1-year data products.

The webinar will examine all 2020 ACS 1-year experimental data products also released Nov. 30, including:

• Experimental data tables.
• Technical working paper: “Addressing Nonresponse Bias in the American Community Survey During the Pandemic Using Administrative Data.”
• 1-Year Public Use Microdata Sample (PUMS) File with experimental weights.
• Blog: “An Overview of Addressing Nonresponse Bias in the American Community Survey During the Pandemic Using Administrative Data.”

When: Tuesday, Nov. 30, at 2 p.m. EST 

Who: Donna M. Daily, chief, American Community Survey Office, U.S. Census Bureau 

Jonathan Eggleston, senior economist, Center for Economic Studies, U.S. Census Bureau 

Michael C. Cook, chief, Public Information Office, U.S. Census Bureau   

Access:  WebEx

The webinar will include a simultaneous audio conference and online presentation. Credentialed media and data users will be able to ask questions following the presentation.  

Toll-free number: 1-888-324-0283 
Participant passcode: 9479768

Please log in 10-15 minutes early, as some setup is required. An updated browser is recommended.  

November 10, 2021

The U.S. Census Bureau is committed to producing high-quality data. The Census Bureau recognizes the critical importance of the American Community Survey (ACS) 5-year data, in particular, on government and business decision-making and the need for quality ACS data for that purpose.  

To reflect our quality standards, the Census Bureau must delay the 2016-2020 ACS 5-year data release originally targeted for December 2021. Additional time is needed to continue refining our methodology so that we can minimize the impact of nonresponse bias due to the COVID-19 pandemic. Our current plan targets a March 2022 release date. We expect to provide an update in December.

October 27, 2021

The U.S. Census Bureau released an analytical report in advance of publishing experimental data from the American Community Survey (ACS). The report, An Assessment of the COVID-19 Pandemic’s Impact on the 2020 ACS 1-Year Data, describes how the pandemic disrupted ACS data collection in 2020 and gives data users insights into why the Census Bureau decided to release the 2020 ACS 1-year estimates as an experimental product. The Census Bureau ultimately determined the standard 2020 ACS 1-year estimates did not meet our statistical quality standards. 

In addition, the Census Bureau also posted the 2020 ACS 1-year Sample Size and Data Quality page, as well as supporting documentation to help users prepare for the release.  These quality measure tables include sample size, coverage rates, response rates, and item allocation rates.  

Continue to visit the 2020 ACS 1-Year Experimental Data Release page over the coming months for the most up to date information about this release, including FAQs addressing top questions related to this release.

January 14, 2021

2015-2019 ACS 5-Year Public Use Microdata Sample (PUMS)

We are pleased to announce the release of the 2015-2019 American Community Survey (ACS) 5-year Public Use Microdata Sample (PUMS) files.

The ACS 5-year PUMS files show the full range of population and housing unit responses collected on individual ACS questionnaires for a subsample of ACS housing units and group quarters persons (approximately five percent of the United States population).

PUMS files allow data users to conduct a custom analysis, though the files also tend to be more complicated to use. Working with PUMS data generally involves downloading large datasets onto a local computer and analyzing them using statistical software such as R, SPSS, Stata, or SAS.

PUMS data can be accessed via data.census.gov and the Census Bureau's FTP site. 

Visit our new Microdata section on the ACS website to find all resources related to PUMS files.  This section contains access to PUMS data, the PUMS Handbook, How-to instructions, FAQs and PUMS documentation.  The PUMS Technical Documentation page is updated with the 2019 release to include the PUMS ReadMe, subjects in the PUMS, data dictionary, code lists, Accuracy of the PUMS, and PUMS Estimates for User Verification.

2015-2019 ACS 5-Year Variance Replicate Estimate Tables

We are pleased to announce the release of the 2015-2019 ACS 5-year Variance Replicate Estimate Tables. 

These tables allow advanced users to calculate margins of error (MOEs) when collapsing data within a table or across geographies. This method provides a more accurate MOE than available approximation formulas.  

To access these estimates, visit the Variance Replicate Tables Data page or through the Census Bureau's FTP site.

The Variance Replicate Tables Documentation page is also updated to include technical documentation, a table and geography list, and table shells.