I want to extract a census variable for the years 1990 and 2000. Among the options in the data extract, I am configured to select two data sets from Source Tables: “2000 Census: SF 3b - Sample-Based Data [Block Groups]” and “2000 Census: SF 1b - 100% Data [Blocks & Block Groups]”.
I am wondering if I should recalculate the variables (for example, the number of households without a car) using sampling weights for the variables included in “2000 Census: SF 3b - Sample-Based Data [Block Groups]”. Thank you!
IPUMS NHGIS provides summary data from the U.S. census, American Community Survey, and other sources. Summary data are tabulations based on the microdata (person-level data) collected by the Census Bureau. The estimates provided in the tables that are based on samples, rather than full population censuses, are already weighted by the Census Bureau; IPUMS NHGIS provides the summary data product exactly as it is originally released by the Census Bureau. It is not advisable or necessary to apply sampling weights with these summary data.
