Answers are grounded in this paper and cite their sources.
Summary In many countries, a key component of measuring census coverage is a post-enumeration survey. In the 2001 censuses of the UK this was called the Census Coverage Survey. The paper reviews the design of the 2001 Census Coverage Survey and develops the design for the survey in 2011, taking advantage of the experience of 2001 and the data that were generated by the 2001 process. This leads to a proposed design that is less clustered than in 2001 and has an allocation that is more skewed towards areas where coverage in the 2011 census is expected to be lowest. The updated design balances optimal allocation against maintaining a sufficient sample across all areas.
No takes yet. Share an insight, caveat, or question.
Brown et al. (2011) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: