Census of Population and Housing, 1990 [United States]: Public Use Microdata Sample: 1/1,000 Sample (ICPSR 6497)
Published: Jan 18, 2006
This dataset, prepared by the Inter-university Consortium for Political and Social Research, comprises 2 percent of the cases in the second release of CENSUS OF POPULATION AND HOUSING, 1990 [UNITED STATES]: PUBLIC USE MICRODATA SAMPLE: 5-PERCENT SAMPLE (ICPSR 9952). As 2 percent of the 5-percent Public Use Microdata Sample (PUMS), it constitutes a 1-in-1,000 sample, and contains all housing and population variables in the original 5-percent PUMS. Housing variables include area type, state and area of residence, farm/nonfarm status, type of structure, year structure was built, vacancy and boarded-up status, number of rooms and bedrooms, presence or absence of a telephone, presence or absence of complete kitchen and plumbing facilities, type of sewage, water source, and heating fuel used, property value, tenure, year moved into housing unit, type of household/family, type of group quarters, household language, number of persons, related children, own/adopted children, and stepchildren in the household, number of persons and workers in the family, status of mortgage, second mortgage, and home equity loan, number of vehicles available, household income, sales of agricultural products, payments for rent, mortgage, and property tax, condominium fees, mobile home costs, and cost of electricity, water, heating fuel, and flood/fire/hazard insurance. Person variables cover age, sex, relationship to householder, educational attainment, school enrollment, race, Hispanic origin, ancestry, language spoken at home, citizenship, place of birth, year of immigration, place of residence in 1985, marital status, number of children ever born, presence and age of own children, military service, mobility and personal care limitation, work limitation status, employment status, employment status of parents, occupation, industry, class of worker, hours worked last week, weeks worked in 1989, usual hours worked per week, temporary absence from work, place of work, time of departure for work, travel time to work, means of transportation to work, number of occupants in vehicle during ride to work, total earnings, total income, wages and salary income, farm and nonfarm self-employment income, Social Security income, public assistance income, retirement income, and rent, dividends, and net rental income.
Date of Collection
Data Collection Notes
(1) To approximate weighted frequencies given by the original 5-percent PUMS, users should multiply the weight variables, HOUSWGT and PWGT1, by 50. (2) This dataset has the same hierarchical structure as the 5-percent PUMS. There is a separate record type for each of the two levels in the hierarchy: the housing level is represented by a housing record comprising 112 housing variables, the person level by a person record comprising 123 person variables. (These variable counts do not include the housing serial number, SERIALNO, and the variable denoting the record type, RECTYPE. These two variables appear on both the housing and person records). Each occupied housing unit is represented by a single housing record, followed by one or more person records, one for each person in the household. Each vacant housing unit is represented by a solitary housing record, which is not followed by any person records. Every person residing in group quarters is represented by a single housing record followed by a person record. In all, this dataset contains 361,185 records. (3) Appendix G of the codebook (PUMS maps) is available only in hardcopy form upon request from ICPSR. (4) Code 6, which denotes this 1-in-1,000 sample, has been added to the variable SAMPLE.
This dataset was extracted by ICPSR from the 5-percent PUMS using a systematic selection procedure. It contains all housing records in the 5-percent PUMS coded 37 or 87 on the subsample variable, SUBSAMPL, plus all person records associated with these housing records. The number 37 was obtained by randomly selecting a number between 0 and 99 (i.e., one of the 100 possible codes for SUBSAMPL), and the number 87 was obtained by adding 50 to 37. (See Chapter 4 of the codebook for an explanation of how SUBSAMPL may be used to select PUMS subsamples.) The 5-percent PUMS, derived from responses to the Census long-form questionnaire, is a 5-percent stratified sample of persons and housing units enumerated in the 1990 Census (housing units and their occupants, vacant housing units, and persons in group quarters). The long-form questionnaire was administered to approximately 15.9 percent of households counted by the 1990 Census.
All persons and housing units in the United States.
census enumeration data
Original Release Date
2006-01-18 File AP6497.PDF was removed from any previous datasets and flagged as a study-level file, so that it will accompany all downloads.
1995-06-05 ICPSR data undergo a confidentiality review and are altered when necessary to limit the risk of disclosure. ICPSR also routinely creates ready-to-go data files along with setups in the major statistical software formats as well as standard codebooks to accompany the data. In addition to these procedures, ICPSR performed the following processing steps for this data collection:
- Performed recodes and/or calculated derived variables.
Data in this collection are available only to users at ICPSR member institutions.
- The citation of this study may have changed due to the new version control system that has been implemented.
This study is provided by ICPSR. ICPSR provides leadership and training in data access, curation, and methods of analysis for a diverse and expanding social science research community.