Article Undercoverage Rates and Undercoverage Bias in Traditional Housing Unit Listing

Many face-to-face surveys use field staff to create lists of housing units fromwhich sam-plesareselected.However,housingunit listing isvulnerabletoerrorsofundercoverage: Somehousing units aremissed and have no chance to be selected. Such errors are not routinely measured and documented in survey reports. This study jointly investigates the rateof undercoverage, the correlates of undercoverage, and thebias in survey data due to undercoverage in listed housing unit frames.Workingwith theNational Survey of Family Growth, we estimate an undercoverage rate for traditional listing efforts of 13.6percent.We find thatmultiunit status, rural areas, andmapdifficulties strongly cor-relatewithundercoverage.We findsignificantbias inestimatesof variables suchasbirth control use,pregnancies, and income.Theresultshave important implications forusers of data from surveys based on traditionally listed housing unit frames