Comparing the Selection of All Household Members to a Subsample of Household Members: Can Less be More?

The decision to select a subsample of eligible members of a sampled household (HH) is influenced by a number of factors including burden on the HH, data quality, cost, and the sampling variance of survey estimates. Design effects quantify the influence of a complex sampling design on the variance of survey estimates. Selecting a subsample of eligible persons within a sampled HH can have counteracting impacts on design effects. On one hand, subsampling in multi-person HHs increases the design effects attributable to unequal weighting. Conversely, subsampling could reduce the design effects attributable to clustering because the potential intra-household correlation among respondents in the same HH is reduced or eliminated. If the reduction in correlation is greater than the increase caused by unequal weighting, subsampling can achieve the same sampling variance as selecting all eligible HH members with less cost and burden. We present the results of a simulation study that evaluates the design effects associated with subsampling HH members on personal victimization rates based on the 2008 National Crime Victimization Survey which selected all persons 12 and older in a sampled HH.