The microdata for each year of the Linked Birth/Infant Death Data Set consists of three separate data files. The numerator/denominator file set referred to below can be used to compute infant mortality rates.
- Linked Deaths - The numerator files (such as Num85.dat.Z) include deaths to all infants born in that same calendar year for which the death certificate can be linked to a birth certificate in the denominator file.
- Linked Births - The denominator files (such as Den85.dat.Z) contain all births occurring in a given calendar year.
- Unlinked Deaths - The unlinked files (such as Unl85.dat.Z) include death certificate information for all the infant deaths that cannot be linked to a birth in the corresponding birth file.
Datasets located below are also separated into two sections:
- U.S. Data Files - Prior to 1972, data are based on a 50-percent sample of birth certificates from all States. Beginning in 1972, data are based on a 100-percent sample of birth certificates from some states and on a 50-percent sample from the remaining States. The number of States from which 100 percent of the records are used has increased from 6 in 1972 to all States and the District of Columbia in 1985.
- U.S. Territory Data - Birth data from the U.S. Territories Guam, Puerto Rico, and the U.S. Virgin Islands are available on a separate file beginning in 1994. In 1998, American Samoa and the Northern Marianas were added to the U.S. Territories files.
Demographic data include variables such as date of birth, age, and educational attainment of parents, marital status, live-birth order, race, sex, and geographic area. Health data include items such as birth weight, gestation, prenatal care, attendant at birth, and Apgar score. Geographic data includes state, county, and city of mother's residence and state and county of the place of birth. City and county data are available only for areas with a population of 250,000 or more. Check the documentation below for more detail.
Other birth data available are Natality Data, Period Linked Birth/Infant Death Data, as part of the Perinatal Mortality Data, and Matched Multiple Births Data, 1995-1998. NCHS did not produce Linked Birth/Infant Death from 1992-1994. After 1999, the Linked Birth/Infant Death data is included as part of the Perinatal Mortality Data set.
SEER provides helpful U.S. Population data for 1969 on.
Use of this data signifies agreement with NCHS data use rules. Works referring to the datasets or codebooks should contain a citation to NCHS. Published material derived from this data should include a citation such as this at the bottom of the table: "Source: National Center for Health Statistics (span of years used)"
U.S. Data Files - Raw Format
Various file types for Linked Deaths, Linked Births, and Unlinked Deaths data below are classified according to:  = source,  = sas ,  = stata,  = csv,  = desc. NCHS did not produce Linked Birth/Infant Death Files from 1992-1994
U.S. Data Files - NBER Format
These SAS, Stata, and SPSS files were created by firstname.lastname@example.org at the NBER based on the source data above to make access to the NCHS Linked Birth/Infant Death Data easier to use. NCHS did not produce Linked Birth/Infant Death Files from 1992-1994
U.S. Territory Data Files - Raw Format
Various file types for Linked Deaths, Linked Births, and Unlinked Deaths data below are classified according to:  = source,  = sas ,  = stata,  = csv,  = desc. 1983-1994 not available
U.S. Territory Data Files - NBER Format
These SAS, Stata, and SPSS files were created by email@example.com at the NBER based on the source data above to make access to the NCHS Linked Birth/Infant Death Data easier to use.
More from NBER
In addition to working papers, the NBER disseminates affiliates’ latest findings through a range of free periodicals — the NBER Reporter, the NBER Digest, the Bulletin on Retirement and Disability, the Bulletin on Health, and the Bulletin on Entrepreneurship — as well as online conference reports, video lectures, and interviews.