|
Activity Number:
|
427
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #309235 |
|
Title:
|
Investigation of Empirical Bayesian Confidence Intervals for Expenditure Data in the Medical Expenditure Panel Survey
|
|
Author(s):
|
Robert Baskin*+ and Malay Ghosh
|
|
Companies:
|
Agency for Healthcare Research and Quality and University of Florida
|
|
Address:
|
540 Gaither Road, Rockville, MD, 20850,
|
|
Keywords:
|
gamma distribution ; log-normal distribution ; complex survey
|
|
Abstract:
|
The Medical Expenditure Panel Survey (MEPS), a national probability sample survey sponsored by the Agency for Healthcare Research and Quality (AHRQ), is designed to provide nationally representative estimates of health care use, expenditures, sources of payment, and insurance coverage for the U.S. civilian noninstitutionalized population. Research has shown the expenditure data from MEPS to have a marked positive skewness. Previous work has considered using different distribution functions for the confidence intervals of mean expenditures. The current project will evaluate the use of empirical Bayes confidence intervals for subdomain means using MEPS data. A simulation is used to compare the results.
|
