Definition
This variable indicates the sample components, 1910.
The IPUMS offers two samples of the 1910 U.S. census: the 1910 1% sample and the 1910 1.4% sample with oversamples.
The two 1910 IPUMS samples include different combinations of data from seven independently drawn component samples:
a 1-in-100 national sample (SAMP1910 = 1)a 1-in-5 Alaskan sample (SAMP1910 = 2)a 1-in-5 Hawaiian sample (SAMP1910 = 3)a 1-in-5 sample of the American Indian schedules (SAMP1910 = 4)a 1-in-250 national sample (SAMP1910 = 5)a Black oversample of selected counties (SAMP1910 = 6)a Hispanic oversample of selected counties (SAMP1910 = 7)The 1.4% sample with oversamples consists of all records from all seven samples, with appropriate weights assigned. Since each of the component samples employs slightly different sampling rules and sampling densities, users must apply weighting variables to get accurate statistics when using this sample.
The 1910 1% sample consists of a data from the first sample and a subset of the data from samples 2-4. To make the sample self-weighting (i.e., all records have the same weight), we selected approximately 5% of the records from each of the 1-in-20 samples. The 1% sample has significantly fewer cases than the 1.4% sample with oversamples, but it does not require the use of weights. All cases in the 1% sample represent approximately 100 people in the population.
Component samples 1-4 were produced at the University of Minnesota between 2001-2006. Component samples 5, 6, and 7 were produced at the University of Minnesota, the University of Texas, and the University of Pennsylvania in the 1980s and 1990s. Samples 5, 6, and 7 were previously available via the IPUMS Extract system as the "1910 General sample," the "1910 Black Oversample," and the "1910 Hispanic Oversample."
