This analysis is based on data from the 1997-2000 Medical Expenditure Panel Survey Household Component (MEPS-HC), which involved a nationally representative sample of the civilian, noninstitutionalized U.S. population and was conducted by the Agency for Healthcare Research and Quality (17). The MEPS-HC sample is drawn from respondents to the previous year's National Health Interview Survey (NHIS). The NHIS uses a stratified, multistage probability cluster sampling design to obtain a representative sample of the U.S. population and oversamples persons of African-American and Hispanic ethnicity (18). The MEPS-HC data include sampling weights that reflect the sampling frame and adjustments for household nonresponse. The MEPS-HC provides data on demographic characteristics, health status, insurance coverage, and the utilization of health care services for all individuals in sampled households. Household respondents provided information on the names of all outpatient medications used by each household member and the names and locations of the pharmacies where each medication was obtained (19). They were also asked for permission to request records from these pharmacies. Pharmacy providers were asked to provide the data necessary to assign a National Drug Code, which is specific for manufacturer, ingredients, strength, package size, quantity dispensed, total charge, and sources of payment. The linkage rate between information provided by respondents and data obtained from pharmacies was 67% in 1997, 79% in 1998, 79% in 1999, and 77% in 2000. The Agency for Healthcare Research and Quality performed detailed matching, imputation, consistency checks, sensitivity checks, and reconciliation algorithms (19).