Predicting the Coverage of Address-Based Sampling Frames Prior to Sample Selection

In 2009, RTI conducted a field study for the National Survey on Drug Use and Health (NSDUH) aimed at investigating the cost implications and coverage properties of a sampling frame based on address-based sampling (ABS) in area-segments with adequate ABS coverage and field enumeration (FE) elsewhere. Data for this study were based on a probability sample of 200 segments and 3,878 eligible dwelling units from the NSDUH. We found that accurately predicting ABS coverage at the area-segment level prior to sample selection simultaneously lowers costs and improves frame coverage.