The U.S. Census Bureau has a long history of evaluating population coverage in decennial censuses. Formal evaluations began with the 1940 census. Almost everything we know about the size of the coverage error, trends in census coverage and differences among subgroups of the population comes from the Census Bureau's own evaluation programs.
Two principal methods are used to measure coverage in censuses. One method derives coverage estimates from post-enumeration surveys using dual system estimation. The other method is called Demographic Analysis (DA). DA represents a macro-level approach, where population estimates are developed for the census date by aggregating various types of demographic data.
A coverage measurement program is essential for measuring the effectiveness of any census, including the 2020 Census, in terms of data quality. It is necessary to produce coverage measures to determine if the goals for 2020 were met and to determine how future censuses can be improved.
This web site and its links provide an overview of these two methods, documentation of their implementation in past censuses, and documentation of their use in the 2020 Census.