Data Cart

Description

HHWT indicates how many households in the population are represented by a given household in a dataset. It is necessary to apply HHWT to produce accurate household-level statistics for the "weighted" NAPP samples: those where the household records in the sample data represent differing numbers of households in the population.

Comparability

Most NAPP samples are complete-count datasets, where each record represents one household in the population. It is not necessary to use weights in those samples.

The 1901 Canada sample is a flat 1-in-20 sample in which each record represents 20 households in the national population. The use of weights is optional.

The 1871 Canada and 1875 Norway datasets are highly stratified, weighted samples. Users must use HHWT in order to calculate accurate household-level statistics. There are a large number of households with a weight of zero in 1871 Canada.

The Great Britain 1851 data are a cluster sample of parishes. HHWT is based on sampling density at the county level. For a detailed listing of counties and parishes in 1851, refer to this website. Note the sample includes no data for three counties: Flintshire (North Wales) and Selkirkshire and Kinrosshire (Southern Scotland).

For the United States 1850-1910 samples (other than the 1880 complete count dataset), HHWT is calculated by the IPUMS such that statistics match published population counts for counties and/or State Economic Areas, or SEAUS.

The Mecklenburg 1819 dataset has a highly clustered sample design of portions of territories. The weights are based on Territories in Mecklenburg (TERRIMS). NOTE: Because of a highly clustered sample design, the sample weights may not ensure representative results for all types of analyses.

If all counties of a specific State Economic Area (SEAUS) had a population of at least 10,000 persons in the reference year, then HHWT is benchmarked on each county's population.

If all counties in an SEAUS had populations fewer than 10,000, then HHWT is based on the aggregate population total for the group of counties comprising the SEAUS.

If the SEAUS contained a mix of counties above and below the 10,000 population threshold, HHWT uses the SEAUS population if the aggregated total for the counties under 10,000 does not equal or exceed 10,000. However, if the aggregated total for the counties under 10,000 does equal or exceed 10,000, then the aggregated total is used for the counties under 10,000, and the county population is used for specific counties within the SEAUS that have a population total that equals or exceeds 10,000.

In 1900-1910, some cases have HHWT values of 0. These records are part of fragmentary households that were enumerated outside of the original "sample window." When possible, data entry staff located these individuals and reunited them with the remainder of their household (i.e., the portion of the household that was within the "sample window").

Users combining complete-count and sample data should use HHWT to obtain correct totals and proportions.

Universe

Codes

This is a 4-digit numeric variable.

Availability

• Canada: 1852, 1871, 1881, 1891, 1901
• Great Britain: 1851, 1881, 1881
• Iceland: 1801, 1901
• Mecklenburg: 1819
• Norway: 1801, 1865, 1875, 1900
• Sweden: 1900
• United States: 1850, 1860, 1870, 1880, 1880, 1900, 1910