Controlling the American Community Survey to intercensal population estimates

Abstract

The US Census Bureau has proposed the use of demographic projections as population controls for the American Community Survey at a fine level of geographic and demographic stratification. These projections are known to be imperfect. Bias and variance of post-stratification estimators with imperfect population controls at various levels of aggregation are considered. The bias and variance are computed with respect to the "model" (including data generation and demographic projection) or with respect to the "design" (including coverage, sampling, response and demographic projection). Bias and variance depend in a complex way on the interactions of demographic projection errors with undercoverage error and nonresponse. Numerical examples illustrate that in the presence of imperfect demographic projections, control at higher levels of aggregation may be better in terms of bias than control at a fine level of post-stratification.