Affiliations: [a] Agency for Health Care Policy and Research, 2101 E.
Jefferson Street, Suite 500, Rockville, Maryland 20852, USA
Note: [1] The views expressed in this paper are those of the authors and no official
endorsement by the Department of Health and Human Services or the Agency for
Health Care Policy and Research is intended or should be inferred. The
authors wish to thank Ms. Susan Czechowicz, AHCPR, for her most helpful
statistical support, and Ms. Suzanne Worth, Social and Scientific Systems,
Inc., for her excellent programming support.
Abstract: There is a growing need to obtain State-level estimates of the uninsured
population to assist in the formulation of appropriate health care policies
directed to this population subgroup. However, reliable estimates of these
parameters at the State level are rarely directly obtainable from national
sample surveys. This evaluation focuses on alternative small area estimation
strategies that are applicable to data from the 1987 National Medical
Expenditure Survey (NMES-2). These techniques use model based estimators that
combine national survey data on variables of interest, with auxiliary data and
population characteristics of subnational areas to yield estimates for these
subnational areas. A comparison of the accuracy of these small area estimators
is presented. Prior to making State-level estimates of the uninsured, the
alternative strategies are used to estimate Medicaid recipients, and comparisons
are then made with actual program statistics.
