The 131st Annual Meeting (November 15-19, 2003) of APHA

Abstract #58060

Steven B. Cohen, PhD and Trena Ezzati-Rice, MS. Center for Cost and Financing Studies, Agency for Healthcare Research and Quality, 2101 E. Jefferson Street, Suite 500, Rockville, MD 20852, 301-594-6171, scohen@ahrq.gov

The capacity to conduct detailed analyses of the health care expenditure experience of the population each year, and to examine patterns over time, are two major features of the Medical Expenditure Panel Survey. The MEPS was designed to produce annual estimates of the health care utilization, expenditures, sources of payment and insurance coverage of the U.S. civilian non-institutionalized population. The scope and depth of this data collection effort reflects the needs of government agencies, legislative bodies, and health professionals for the comprehensive national estimates needed in the formulation and analysis of national health policies. The survey design and related estimation specifications feature targeted statistical and methodological strategies to improve the accuracy of resultant health care expenditure estimates. Prior studies have demonstrated that one percent of the civilian non-institutionalized population are associated with over twenty five percent of the medical expenditures incurred in a given year. As a consequence of the highly skewed nature of the health care expenditure distribution, additional efforts are committed to ensure the accuracy of estimates that characterize individuals that incur high levels of health care services and expenditures. This paper provides a summary of the statistical and methodological strategies adopted in MEPS to improve the accuracy of resultant healthcare expenditure estimates. In addition, the capacity of estimation strategies to adjust for survey attrition are assessed with respect to national healthcare expenditure estimates and their transitions over time.

Learning Objectives:

• The participants will be informed about the appropriate statistical methods and procedures to consider when conducting longitudinal analyses using complex survey data. They will also learn how to implement estimation strategies to support longitudinal analyses, which also adjust for survey attrition. Analysts and researchers that attend the session will be able to better evaluate research papers that focus on analyses of trends using longitudinal data, to assess whether appropriate analytical techniques to minimize bias in estimates have been adopted. The session will also provide substantive information to health services researchers on national statistics that relate to the distribution of health care expenditures and their time trends.

Keywords: Statistics, Migrant Workers

Presenting author's disclosure statement:
Organization/institution whose products or services will be discussed: Department of Health and Human Services Agency for Healthcare Research and Quality
I have a significant financial interest/arrangement or affiliation with any organization/institution whose products or services are being discussed in this session.
Relationship: Employment