Hi,
I’m interested in studying annual changes in marriage rates at the county-level. For years preceding 2020, I have used 1 year ACS estimates provided through the Census API. For 2020, it appears that 1 year estimates have not been released.
Since the 5 year estimates may not be appropriate for studying annual changes, I was planning to use PUMA microdata and aggregate to the county-level. Is this the only option or is there some other Census data I can use for 2020?
Thank you!
My understanding of your question is that you would like to estimate marriage rates at the U.S. county-level in years prior to and including 2020 and that you have used ACS 1-year summary files accessed via the Census API so far.
The COVID-19 pandemic had major impacts on the collection of the 2020 ACS data. The 2020 ACS 1-year data are experimental, and use an experimental weighting scheme to address deficiencies in the public use microdata sample (PUMS) and experimental estimates instead of the standard 1-year estimates or summary files. The Census Bureau advises against making comparisons between the 2020 ACS 1-year PUMS file and any other ACS or Census data products. While the Census Bureau addressed the known data quality issues present in the 2020 data file, the Census Bureau notes that full extent of data quality issues is not yet known and may not be adequately accounted for in the experimental weights. Please see this documentation about the ACS and COVID-19 for more information.
You can access the PUMS data via IPUMS USA and summarize individual responses about marriage to create summary statistics, though you will not be able to identify all counties in the US.
In IPUMS USA, the variable MARST gives each person’s marital status. MARST is available in all samples from 1880 through 2021, except the 2010 Decennial Census (marital status is instead available in ACS samples from 2010).
Counties are not identified in public-use microdata from 1950 onward. IPUMS identifies counties, where possible, from other low-level geographic identifiers. You can read more about how counties are identified in the description tab of the COUNTYFIP variable, and view a list of identified counties from 1950 and later.
For reference, IPUMS NHGIS provides summary files, as you are familiar with from the Census API. However, like the Census API, NHGIS does not include 2020 ACS 1-year summary data.