|
Activity Number:
|
226
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 5, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #301127 |
|
Title:
|
Comparison of Imputation Adjustment Techniques on Variance Estimation in the Medical Expenditure Panel Survey (MEPS)
|
|
Author(s):
|
Robert M. Baskin+ and Marc W. Zodet*+ and Trena M. Ezzati-Rice
|
|
Companies:
|
Agency for Healthcare Research and Quality and Agency for Healthcare Research and Quality and Agency for Healthcare Research and Quality
|
|
Address:
|
540 Gaither Road, Rockville, MD, 20850, 540 Gaither Road, Rockville, MD, 20850,
|
|
Keywords:
|
multiple imputation ; replicated imputation ; Rao-Shao method ; complex survey data
|
|
Abstract:
|
MEPS is a national probability sample survey designed to provide nationally representative estimates of health care use, expenditures, sources of payment, and insurance coverage for the U.S. civilian noninstitutionalized population. Depending on the type of medical event, there are varying levels of item nonresponse on medical expenses as collected in the MEPS household interview. MEPS also collects expenditure data in the Medical Provider Component (MPC) of the survey. Missing expenditure data for health care events are completed through a weighted sequential hot deck procedure with MPC data as the primary donor source. Studies in 2004 and 2005 examined the impact of imputation on estimates of variance for MEPS health care expenditures. This study updates this research by investigating multiple imputation as a method to assess the impact of imputation on the variance estimates.
|
