Term
|
Definition
| Primary Sampling Unit; consists of either a city or county or a group of contiguous counties. 2007 of them are used in the Current Population Survey. |
|
|
Term
|
Definition
| Groups of PSUs sorted so that the PSUs in each stratum would resemble each other on certain demographic and economic characteristics. There are 792 strata, and they do not cross state lines. New York and Los Angeles are in strata by themselves. |
|
|
Term
|
Definition
| Ultimate Sampling Unit; consist of about 4 housing units each. Every person over the age of 16 living in a selected USU in a selected PSU is counted in the Current Population Survey. |
|
|
Term
|
Definition
| Consists of civilians who are either employed or unemployed. |
|
|
Term
|
Definition
| The percentage of the civilian labor force that is unemployed. |
|
|
Term
|
Definition
| A civilian over the age of 16 who did any paid work in the previous week, or were temporarily absent from a regular job. |
|
|
Term
|
Definition
| A civilian over the age of 16 who were not employed the previous week but were available for work and were looking for work during the past 4 weeks. |
|
|
Term
|
Definition
| A civilian over the age of 16 who is neither employed nor unemployed by Census Bureau definitions. |
|
|
Term
|
Definition
| The idea that people's responses change as a result of being interviewed, progressively biasing the sample. |
|
|
Term
|
Definition
| To compensate for under- or over-represented groups in the Survey, the Census Bureau weights the data collected to better reflect the makeup of the overall population. |
|
|
Term
|
Definition
A sampling technique where the entire population is divided into groups, or clusters, and a random sample of these clusters are selected. All observations in the selected clusters are included in the sample.
Typically used when the researcher cannot get a complete list of the members of a population they wish to study but can get a complete list of groups or 'clusters' of the population. It is also used when a random sample would produce a list of subjects so widely scattered that surveying them would prove to be far too expensive. |
|
|
Term
|
Definition
A method of estimating the standard error of a survey without having to do a second survey to compare results.
Acheived by splitting the data in half and taking the average of the two sets of data, then taking the square root of the average error squared. |
|
|
Term
|
Definition
| Current Population Survey interviewers' reports are checked, and any incomplete or inconsistent data is thrown out. |
|
|
Term
| Current Population Survey |
|
Definition
| A survey conducted by the Census Bureau, based on a nationwide probability sample of about 110,000 people who are interviewed monthly. |
|
|
