Overview of the HCUP Nationwide Inpatient Sample (NIS)—1999

The HCUP Nationwide Inpatient Sample (NIS) is a unique and powerful database of hospital inpatient stays. Researchers and policymakers use the NIS to identify, track, and analyze national trends in health care utilization, access, charges, quality, and outcomes. Participation of statewide data organizations make the NIS possible.

The Healthcare Cost and Utilization Project (HCUP) is a family of health care databases and related software tools and products developed through a Federal-State-industry partnership. The Agency for Healthcare Research and Quality (AHRQ) sponsors HCUP.

Contents

Summary
Overview of NIS Data
NIS Data Sources, Hospitals, And Inpatient Stays
State-Specific Restrictions
Contents of CD-ROM Set
NIS Data Elements
Sampling of Hospitals Included in the NIS
Stratification Variables
Getting Started
NIS Data Files
NIS Documentation
Other HCUP Products
Data
HCUPnet
Tools
Summary of NIS Data Use Limitations
Publications
Table 1: Summary of NIS Releases
Table 2: Summary of NIS Data Sources, Hospitals and Inpatient Stays, 1988-99
Table 3: Data Elements in the NIS Inpatient Core Files, 1999
Table 4: Data Elements in the NIS Hospital Weights Files, 1999
Table 5: Bed size Categories, by Region
Table 6: NIS Documentation CD-ROM

Summary

The Nationwide Inpatient Sample (NIS) is part of the Healthcare Cost and Utilization Project (HCUP), sponsored by the Agency for Healthcare Research and Quality (AHRQ).

The NIS is a database of hospital inpatient stays. Researchers and policymakers use the NIS to identify, track, and analyze national trends in health care utilization, access, charges, quality, and outcomes.

The NIS is the largest all-payer inpatient care database that is publicly available in the United States, containing data from approximately 7 million hospital stays. The 1999 NIS contains all discharge data from about 1,000 hospitals located in 24 States, approximating a 20-percent stratified sample of U.S. community hospitals. The NIS is available for a 12-year time period, from 1988 to 1999, allowing analysis of trends over time.

The NIS is the only national hospital database with charge information on all patients, regardless of payer, including persons covered by Medicare, Medicaid, private insurance, and the uninsured. The NIS's large sample size enables analyses of rare conditions, such as congenital anomalies; uncommon treatments, such as organ transplantation; and special patient populations, such as children.

Inpatient stay records in the NIS include clinical and resource use information typically available from discharge abstracts. Hospital and discharge weights are provided for producing national estimates. The NIS can be linked to hospital-level data from the American Hospital Association's Annual Survey of Hospitals and county-level data from the Bureau of Health Professions' Area Resource File, except in those States that do not allow the release of hospital identifiers.

Beginning in 1998, the NIS differs from previous NIS releases: some data elements were dropped, some were added, for some data elements the coding was changed, and the sampling and weighting strategy was revised to improve the representativeness of the data.

Access to the NIS is open to users who sign data use agreements. Uses are limited to research and aggregate statistical reporting.

Return to Contents

Overview of NIS Data

The Nationwide Inpatient Sample contains all-payer data on hospital inpatient stays from States participating in the HCUP. Each year of the NIS provides information on approximately 5 million to 7 million inpatient stays from about 1,000 hospitals. All discharges from sampled hospitals are included in the NIS database.

The NIS contains patient-level clinical and resource use information included in a typical discharge abstract. The NIS can be linked directly to hospital-level data from the American Hospital Association (AHA) Annual Survey of Hospitals and to county-level data from the Health Resources and Services Administration Bureau of Health Professions' Area Resource File (ARF), except in those States that do not allow the release of hospital identifiers.

The NIS is designed to approximate a 20-percent sample of U.S. community hospitals, defined by the AHA to be "all nonfederal, short-term, general, and other specialty hospitals, excluding hospital units of institutions." Included among community hospitals are specialty hospitals such as obstetrics-gynecology, ear-nose-throat, short-term rehabilitation, orthopedic, and pediatric institutions. Also included are public hospitals and academic medical centers. Excluded are short-term rehabilitation hospitals (beginning with 1998 data) long-term hospitals, psychiatric hospitals, and alcoholism/chemical dependency treatment facilities.

This universe of U.S. community hospitals is divided into strata using five hospitals characteristics: ownership/control, bed size, teaching status, urban/rural location, and U.S. region.

The NIS is a stratified probability sample of hospitals in the frame, with sampling probabilities proportional to the number of U.S. community hospitals in each stratum. The frame is limited by the availability of inpatient data from the data sources.

To improve the representativeness of the NIS, the sampling and weighting strategy was modified beginning with the 1998 data. The full descriptions of this process can be found in the special report on Changes in NIS Sampling and Weighting Strategy for 1998, which will be available from AHRQ in late 2001. To facilitate the production of national estimates, both hospital and discharge weights are provided, along with information necessary to calculate the variance of estimates. Detailed information on the design of the NIS is available in the year-specific special reports on Design of the Nationwide Inpatient Sample found on the NIS Documentation CD-ROM.

NIS data sets are currently available for multiple years, as shown in Table 1. Each release of the NIS includes:

• Data in ASCII format on CD-ROM.
• Patient-level hospital discharge abstract data for 100 percent of discharges from a sample of hospitals in participating States.
• 5 million to 7 million inpatient records per year.
• 800-1,000 hospitals per year.
• Two 10 percent subsamples of discharges from all NIS hospitals.
• Discharge-level weights to calculate national estimates for discharges.
• Hospital Weights File to produce national estimates for hospitals and to link the NIS to data from the American Hospital Association Annual Survey of Hospitals.
• NIS Documentation and tools, also on CD-ROM—including file specifications, programming source code for loading ASCII data into SAS and SPSS, and value labels.

Select Table 1 for a summary of NIS releases.

Return to Contents

NIS Data Sources, Hospitals, And Inpatient Stays

Table 2 summarizes the data sources, number of hospitals, and number of inpatient stays in NIS data.

Return to Contents

State-Specific Restrictions

Some data sources that contributed data to the NIS imposed restrictions on the release of certain data elements or on the number and types of hospitals that could be included in the database. Detailed information on these State-specific restrictions is available in the special report on Sources of NIS Data and State-specific Restrictions on the NIS Documentation CD-ROM.

Return to Contents

Contents of CD-ROM Set

There are two types of files included in the NIS:

• Data files.
• Documentation and tools files.

Data Files. Three types of ASCII formatted data files are included in the NIS:

• Inpatient Core File: This inpatient discharge-level file contains data for 100 percent of the discharges from a sample of hospitals in participating States.
• Subsample Inpatient Core Files: Each of these discharge-level files contain all data elements from the Core File, for a 10 percent subsample of discharges from the NIS; these can be combined to create a 20 percent NIS subsample. These files can be useful for testing programs or validating models.
• Hospital Weights File: This hospital-level file contains one observation for each hospital included in the NIS and contains weights and variance estimation data elements, as well as linkage data elements. The unit of observation is the hospital. The HCUP hospital identifier (HOSPID) provides the linkage between the NIS Inpatient Core files and the Hospital Weights file.

Return to Contents

Documentation and Tools Files.

• Documentation: Complete file documentation, variable notes, and summary statistics are provided in a series of Portable Document Format (*.pdf) files. These files are detailed in Table 6.
• SAS source code: Code is included for the format library for the variables and for loading ASCII data into SAS format.
• SPSS source code: Code is included for the variable library and for loading ASCII data into SPSS format.
• Labels: Labels for the Clinical Classifications Software (CCS), formerly called the Clinical Classifications for Health Policy Research (CCHPR), and for the Diagnosis-Related Groups (multiple versions).
• File Specifications: Record layouts for all data files.

Return to Contents

NIS Data Elements

All releases of the NIS contain two types of data: inpatient stay records and hospital information with weights. Table 3 and Table 4 identify the data elements that can be found in the inpatient stay and hospital weights files, respectively. This is not complete documentation for the data; please refer to the NIS Documentation CD-ROM for full documentation on all data elements and for the record layout.

Return to Contents

Sampling of Hospitals Included in the NIS

The hospital universe is defined by all hospitals that were open during any part of each calendar year and were designated as community hospitals in the AHA Annual Survey of Hospitals.

For more information on how hospitals in the data were mapped to hospitals as defined by the AHA, refer to the special report: HCUP Hospital Identifiers. For a list of all data sources, refer to: Sources of NIS Data and State-Specific Restrictions. For more detailed descriptions of the sampling design, refer to the year-specific special reports Design of the HCUP Nationwide Inpatient Sample. All reports can be found on the NIS Documentation CD-ROM.

Return to Contents

Stratification Variables

To help ensure generalizability, five hospital sampling strata were defined based on hospital characteristics contained in the AHA Annual Survey of Hospitals. The stratification variables are:

• Geographic Region—Northeast, Midwest, West, or South. This is based on the U.S. Census regions.
• Location—urban or rural. A metropolitan statistical area is considered urban.
• Teaching Status—teaching or non-teaching. A hospital is considered to be a teaching hospital if it has an AMA-approved residency program, is a member of the Council of Teaching Hospitals (COTH) or has a ratio of full-time equivalent interns and residents to beds of .25 or higher.
• Control—government nonfederal (public), private not-for-profit (voluntary) or private investor-owned (proprietary). When there were enough hospitals of each type to allow it (southern rural, southern urban non-teaching, and western urban non-teaching), hospitals were stratified as public, voluntary, and proprietary. For smaller strata (north central rural and western rural hospitals) a collapsed stratification of public versus private was used, with the voluntary and proprietary hospitals combined to form a single 'private' category. For all other combinations of region, location and teaching status, no stratification based on control was advisable given the number of hospitals in these cells.
• Bed size—small, medium, or large. Bed size categories are based on hospital beds, and are specific to the hospital's location and teaching status, as shown in Table 5. Bed size cutpoints were chosen so that approximately one-third of the hospitals in a given region and location/teaching combination would be in each bed size category (small, medium, or large).

Rural hospitals were not split according to teaching status, because rural teaching hospitals were rare.

To further ensure geographic representativeness, implicit stratification variables included State and three-digit ZIP Code (the first three digits of the hospital's five-digit ZIP Code). The hospitals were sorted according to these variables prior to systematic random sampling.

Return to Contents

Getting Started

NIS information is provided on two CD-ROMs. The NIS data files are on CD-ROM No. 1 and the NIS documentation and tools are on CD-ROM No. 2.

Return to Contents

NIS Data Files

In order to load NIS data onto your PC, you will need 4 gigabytes of space available. Because of the size of the files, the data are distributed as self-extracting PKZIP® compressed files. To decompress the data, you should follow these steps:

1. Create a directory for the NIS on your hard drive.
2. Copy the self-extracting data files from the NIS Data Files CD-ROM into the new directory.
3. Unzip each file by running the corresponding *.exe file.
   • Type the file name within DOS or click on the name within Windows® Explorer.
   • Edit the name of the "Unzip To Folder" in the WinZip® Self-Extractor dialog to select the desired destination directory for the extracted file.
   • Click on the "Unzip" button.

The ASCII data files will then be uncompressed into this directory. After the files are uncompressed, the *.exe files can be deleted.

Return to Contents

NIS Documentation

NIS documentation files on the Documentation CD-ROM provide important resources for the user. Refer to these resources to understand the structure and content of the NIS and to aid in using the NIS. Many of the documentation files are provided in portable document format (*.pdf) files. Files with the *.pdf extension can be viewed, searched, and printed using the Adobe® Acrobat® Reader.

You must have the Adobe® Acrobat® Reader software on your computer to access the NIS documentation. If you do not have Adobe® Acrobat® Reader software on your computer, see the DOCUMENTATION.README.TXT file on NIS Documentation CD-ROM for instructions on installing or obtaining the software.

The Acrobat® Reader™ provided on the NIS Documentation CD-ROM is for IBM®-compatible microcomputers running Microsoft Windows 95 or higher. More information and Acrobat® Reader™ software for other platforms (DOS, Windows® 3.1, Macintosh®, Sun™ Systems, etc.) may be obtained free of charge from the Adobe Home Page at http://www.adobe.com. For further assistance in installing and running the Adobe® Acrobat® Reader on your computer platform, please consult your local support personnel.

Table 6 describes the documentation and tools files that can be found on the NIS Documentation CD-ROM and illustrates the structure of the directories and subdirectories on the CD.

Return to Contents

Other HCUP Products

The AHRQ Web site is a source of information about HCUP databases and aggregate statistics from HCUP: (http://www.ahrq.gov/data/hcup/).

Return to Contents

Data

Nationwide Inpatient Sample (NIS) releases are available from the National Technical Information Service (NTIS); call NTIS for prices or to order at 800-553-6847 or (703) 605-6000. All NIS releases are available on CD-ROM; NIS Release 1 may also be purchased on magnetic tape. Order by PB number.

• NIS, Release 1, 1988-1992 (PB95-503710).
• NIS, Release 2, 1993 (PB96-501325).
• NIS, Release 3, 1994 (PB97-500433).
• NIS, Release 4, 1995 (PB98-500440).
• NIS, Release 5, 1996 (PB99-500480).
• NIS, Release 6, 1997 (PB2000-500006).
• NIS, 1998 (PB2001-500092).
• NIS, 1999 (PB2002-500020).

State Inpatient Databases (SID) are hospital databases from data organizations participating in HCUP. The SID contain the universe of the inpatient discharge abstracts in the participating HCUP States, translated into a uniform format to facilitate multi-State comparisons and analyses. Together, the SID encompass about 60 percent of all U.S. community hospital discharges. For more information, visit http://www.ahrq.govhttp://www.hcup-us.ahrq.gov/sidoverview.jsp or call the HCUP Central Distributor.

State Ambulatory Surgery Databases (SASD) are databases from data organizations in participating HCUP States, that capture surgeries performed on the same day in which patients are admitted and released. The SASD contain the ambulatory surgery encounter abstracts in participating States, translated into a uniform format to facilitate multi-State comparisons and analyses. All of the databases include abstracts from hospital-affiliated ambulatory surgery sites. Some contain the universe of ambulatory surgery encounter abstracts for that State, including records from both hospital-affiliated and freestanding surgery centers. Composition and completeness of data files may vary from State to State. For more information, visit http://www.ahrq.gov/data/hcup/http://www.hcup-us.ahrq.gov/sasdoverview.jsp or call the HCUP Central Distributor.

Kids' Inpatient Database (KID) is a unique database of hospital inpatient stays for children 18 years of age and younger. The KID was specifically designed to permit researchers to study a broad range of conditions and procedures related to child health issues. KID files for 1997 data are available through the AHRQ-sponsored HCUP Central Distributor (contact information below). For more information, visit http://www.ahrq.gov/data/hcup/http://www.hcup-us.ahrq.gov/kidoverview.jsp or call the HCUP Central Distributor.

HCUP Central Distributor. Many HCUP State Partners allow the public release of the State Inpatient Databases (SID) and State Ambulatory Surgery Databases (SASD) through the AHRQ-sponsored HCUP Central Distributor. In addition, the KID is released through the Central Distributor. Information on how to obtain uniformly-formatted HCUP files from States not participating in the HCUP Central Distributor is also available from the HCUP Central Distributor:

HCUP Central Distributor
Social and Scientific Systems, Inc.
Phone: (866) 556-4287 (toll-free)
Fax: (301) 986-8051
E-mail: hcup@s-3.com

Return to Contents

HCUPnet

HCUPnet is a Web-based query tool for identifying, tracking, analyzing, and comparing statistics on hospitals at the national, regional, and State level. With HCUPnet, you have easy access to national statistics and trends and selected State statistics about hospital stays. HCUPnet guides you step-by-step to obtain the statistics you need. HCUPnet generates statistics using the Nationwide Inpatient Sample (NIS), the Kids' Inpatient Database (KID), and the State Inpatient Databases (SID) for those States that have agreed to participate. HCUPnet can be found at: http://hcupnet.ahrq.gov/.

Return to Contents

Tools

AHRQ Quality Indicators (QIs) are clinical performance measures for use with readily available inpatient data. Methods and software for the AHRQ Quality Indicators can be downloaded from http://www.qualityindicators.ahrq.gov/data/hcup/qinext.htm.

Clinical Classifications Software (CCS), formerly known as the Clinical Classifications for Health Policy Research (CCHPRs), are classification systems that group ICD-9-CM diagnoses and procedures into a limited number of clinically meaningful categories. Methods and software can be downloaded from http://www.hcup-us.ahrq.gov/toolssoftware/ccs/ccs.jsp.

Comorbidity Software assigns variables that identify comorbidities in hospital discharge records using ICD-9-CM diagnosis codes (International Classification of Diseases, Ninth Revision, Clinical Modification). Methods and software can be downloaded from http://www.hcup-us.ahrq.gov/toolssoftware/comorbidity/comorbidity.jsp.

Return to Contents

Summary of NIS Data Use Limitations

All users of the NIS must sign a data use agreement and send a copy to AHRQ.

Authorized users of HCUP data agree to the following limitations:*

• Cannot use the data for any purpose other than research or aggregate statistical reporting.
• Cannot re-release any data to unauthorized users.
• Cannot identify nor attempt to identify any individual.
• Cannot link HCUP data to data from another source that identifies individuals.
• Cannot report information that could identify individual establishments.
• Cannot use the data concerning individual establishments for commercial or competitive purposes involving those establishments.
• Cannot use the data to determine rights, benefits, or privileges of individual establishments.
• Cannot identify nor attempt to identify any establishment when its identity has been concealed on the database.
• Cannot contact establishments included in the data.
• Cannot attribute to data contributors any conclusions drawn from the data.
• Must acknowledge the "Healthcare Cost and Utilization Project (HCUP)" in reports.

Any violation of the limitations in the data use agreement is punishable under Federal law by a fine of up to $10,000 and up to 5 years in prison. Violations may also be subject to penalties under State statutes.

*Specific provisions are detailed in the Data Use Agreement for Nationwide Inpatient Sample.

Return to Contents

Publications

HCUP Research Notes report aggregate statistics and detailed analyses using HCUP data. To request copies, contact the AHRQ Publications Clearinghouse at (800) 358-9295 or send a postcard to: AHRQ Publications Clearinghouse, P.O. Box 8547, Silver Spring, MD 20907 or access copies online .

Return to Contents

More Information about NIS

For more information about NIS, contact:

Healthcare Cost and Utilization Project (HCUP)
Agency for Healthcare Research and Quality
Phone: 866-290-HCUP (4287), toll-free
E-mail: hcup@ahrq.gov

Current as of March 2002

Internet Citation:

Overview of the HCUP Nationwide Inpatient Sample (NIS)—1999. March 2002. Agency for Healthcare Research and Quality. http://www.ahrq.gov/data/hcup/nisintro.htm

Return to HCUP
Data & Surveys
AHRQ Home Page
Department of Health and Human Services