Abstract:
|
High survey nonresponse provides substantial potential for nonresponse bias in population estimates. As a result, surveys increasingly rely on auxiliary information to (1) estimate nonresponse bias, (2) attempt to reduce nonresponse bias during data collection, and (3) use statistical models in weighting and estimation. All three rely on auxiliary data that are strongly correlated with key survey variables. Such data are rare in household surveys. We propose and evaluate the collection of proxy survey variables from some nonrespondents. We leverage the two-phase interview design in household interview surveys by embedding proxy measures on the household and the selected person in the screening instrument, collected from the household informant. We include two key health questions (health conditions and public health insurance) in the California Health Interview Survey screener, to potentially use in the estimation, reduction, and adjustment for nonresponse bias. We evaluate the measurement properties and causes of measurement error in these questions and the impact on each goal.
|