OBJECTIVES: This paper compares the private health plans that enroll Medicare beneficiaries—known as Medicare Advantage (MA) plans— in cost to the traditional Medicare fee-for-service (FFS) program by employing a series of methodological approaches based on propensity score matching to address the moral hazard and adverse selection issues. METHODS: The Healthcare Cost and Utilization Project (HCUP) State Inpatient Databases (SID) were used in this analysis. We use hospital inpatient data for 2008 and 2009 from California, Florida, Massachusetts, New York, Tennessee and Wisconsin.  The SID provide detailed diagnoses and procedures, total charges and patient demographics for all participating states. Our key covariate of interest is MA enrollment and the total costs associated with each hospital visit. To obtain costs, we applied hospital specific HCUP cost-to-charge ratios. We adjusted these costs with the CMS area wage index. We obtained information about hospital characteristics using the American Hospital Association Annual Survey Database; and county level information from the Area Resource File.  We estimate a baseline risk-adjusted cost model to compare the total health care costs two cohorts in inpatient settings. To assess the robustness of our baseline results, we re-estimated our risk-adjusted cost model following various propensity score matching methods.   RESULTS: Inpatient cost for MA enrollees was generally lower than the inpatient cost for Medicare FFS beneficiaries when moral hazard and adverse selection was controlled. For example, our estimate shows that the total health care costs per inpatient visit for MA enrollees are higher by 2.6% in Florida, and lower by 12.6% in California when compared to Medicare FFS. We also observed the prevalence of many chronic conditions among MA enrollees was generally lower than among Medicare FFS beneficiaries. CONCLUSIONS: We found wide geographic variations in hospital inpatient costs, and in prevalence of chronic conditions between MA enrollees and Medicare FFS beneficiaries.