CEN

Decennial Census Long Form Sample

Description

The Decennial Census Long Form Sample is a 1-in-6 sample of all households in the U.S.. The questions asked of this sample include age, race, sex, educational attainment, income, place of work, occupation, household relationships, housing unit characteristics, etc.. Because these files are large, processing with them can be very time and resource intensive. In cases where there is no valid response for an individual (or household where applicable), the item is filled in using a system of allocation. Allocation consists of using the response of a similar observation to fill in a missing item. A great deal of documentation of the Decennial Census is available. Brief descriptions are available on the Census Bureau,s web site (www.census.gov). The publicly available documentation that is most relevant for the CES long-form files is: Census of Population and Housing, 1990: Public Use Microdata Sample U.S. Technical Documentation/ prepared by the Bureau of the Census -- Washington, DC: The Bureau, 1992. For the 2000 Dec. Census, see The PUMS documentation provides descriptions of how the data was collected, processed, and recoded. For most variables, there are general and specific discussions of the variables included. This documentation also includes some item specific code lists. The CES long-form files usually contain the most detailed code available for an item. For example, the long form files contain a 3-digit race code that covers more than 800 races or tribes, compared to the more standard 2-digit race code that covers 63 races or tribes. The codebook for the PUMS available through ICPSR (see above URL) are very similar to this technical documentation.