DOWNLOAD Disability
Status Reports

Home  /   Data Sources  /   Rehabilitation Dataset Directory: Search  /   Dataset Profile
Center for Large Data Research & Data Sharing in Rehabilitation

Rehabilitation Dataset Directory: Dataset Profile

Dataset: Medicare Provider Analysis and Review (MEDPAR)

Basic Information
Dataset full name: Medicare Provider Analysis and Review
Dataset acronym MEDPAR
Summary The MEDPAR file contains utilization of services and claims data for Medicare beneficiaries during their stay in Medicare-certified inpatient short-term hospitals, skilled nursing facilities, inpatient rehabilitation facilities, and long-term care hospitals. The data are available in two formats: a 5% format contains a random selection of 5% of total Medicare beneficiaries, and a 100% sample. These records are all from inpatient facilities (Part A) and do not have any information related to outpatient care (Part B). The claims data in MEDPAR are final after taking into account all adjustments. The dataset is useful for tracking patterns of inpatient care for patients with various medical conditions. It also contains information related to the medical and surgical procedures that patients underwent during their stays in inpatient facilities.
Key Terms Medicare, Utilization and Claims Record, Inpatient Procedure Code
Study Design Longitudinal
Data Type(s) Administrative
Sponsoring Agency/Entity Department of Health and Human Services (HHS): Center for Medicare and Medicaid Services (CMS)
Health conditions/Disability measures
Health condition(s) Any/All
Disability Measures Any/All
Measures/outcomes of interest
Topics Medical condition, Comorbidity information, Inpatient utilization, Claims, Service charges, Surgical procedure code, Diagnosis Related Group (DRG) information
Sample Population Medicare beneficiaries (inpatient ‘stay’ record)
Sample Size/Notes 15,000,000 (±) Medicare beneficiaries receiving inpatient care at various facilities
Unit of Observation Patient
Geographic Coverage National
Geographic specificity Zip Code (of beneficiary’s mailing address)
Data Collection
Data Collection Mode Administrative
Years Collected 1991-present
Data Collection Frequency Annual
Strengths and limitations
Strengths Provides a very large sample size to work with. Contains cross-sectional and longitudinal components. Can be linked with enrollment and other clinical data. Useful for health policy research.
Limitations Clinical and intervention information is limited. Requires high computational, and data analytical capabilities.
Data details
Primary Website
Data Access
Data Access Requirements Data Use agreement, $ Cost
Summary Tables/reports NA
Dataset components (where applicable) NA
Selected papers
Technical Research Data Distribution Center Medicare Provider Analysis And Review (MEDPAR) Record -- Dictionary For SAS and CSV Datasets
Other Papers

Ask Our Researchers

Have a question about rehabilitation datasets? Contact our researchers for technical assistance, log in or register.

The Rehabilitation Research Cross-dataset Variable Catalog has been developed through the Center for Large Data Research & Data Sharing in Rehabilitation (CLDR). The Center for Large Data Research and Data Sharing in Rehabilitation involves a consortium of investigators from the University of Texas Medical Branch, Cornell University's Yang Tan Institute (YTI), and the University of Michigan. The CLDR is funded by NIH - National Institute of Child Health and Human Development, through the National Center for Medical Rehabilitation Research, the National Institute for Neurological Disorders and Stroke, and the National Institute of Biomedical Imaging and Bioengineering. (P2CHD065702).

Other CLDR supported resources and collaborative opportunities:

Acknowledgements: This tool was developed through the efforts of William Erickson and Arun Karpur, and web designers Jason Criss and Jeff Trondsen at Cornell University. Many thanks to graduate students Kyoung Jo Oh and Yeong Joon Yoon who developed much of the content used in this tool.

For questions or comments please contact

© 2018 Cornell University. All rights reserved.