PPS Subsampling from NHIS to MEPS: Effect on Precision of MEPS Estimates

• Activity Number: 406
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Sadeq R. Chowdhury*+ and Robert Baskin and Steven R. Machlin
• Companies: AHRQ/DHHS and AHRQ, DHHS and AHRQ
• Keywords: MEPS ; PPS ; Subsampling ; Variance

Abstract

The annual sample of Medical Expenditure Panel Survey (MEPS) is selected from the responding households to the prior year's National Health Interview Survey (NHIS). The selection probability in MEPS varies considerably due to variations in both NHIS selection probability and response propensity. The resulting high variability in the MEPS base weight contributes to the variance of MEPS estimates. Since 2010, a probability proportional to size (PPS) subsampling from NHIS to MEPS has been introduced where the size measure is used as the NHIS household weight. The purpose of the PPS subsampling is to reduce the variation in MEPS base weight and thereby increase the precision of the MEPS estimates. This talk will present the results of an evaluation of this PPS subsampling scheme on the precision of MEPS estimates.