preceding the survey. Discouraged workers, a subset of the marginally attached, were not looking for work because they believed no jobs were available for them.
Occupation, industry, and class of worker. This informa- tion for the employed applies to the job held in the refer- ence week. Persons with two or more jobs are classified in the job at which they worked the greatest number of hours. The unemployed are classified according to their last job. Begin- ning in 2003, the occupational and industrial classification of CPS data is based on the 2002 Census Bureau occupational and industrial classification systems, which are derived from the 2000 Standard Occupational Classification (SOC) and the 2002 North American Industry Classification System (NAICS). (Consistent data are available back to 2000. Earlier data use a different classification system.)
White, Black or African American, and Asian. These are terms used to describe the race of persons. Beginning in 2003, people in these categories are those who selected that race group only. (Previously, respondents identified a group as their main race.) People in the remaining race categories— American Indian or Alaska Native, Native Hawaiian or Other Pacific Islanders, and people who selected more than one race category—are included in the estimates of total employment and unemployment but are not shown separately because the number of survey respondents is too small to develop esti- mates of sufficient quality. In the enumeration process, race is determined by the household respondent. More informa- tion on the 2003 changes in questions on race and Hispanic ethnicity is available on the BLS Web site at http://www.bls. gov/cps/rvcps03.pdf.
Hispanic or Latino ethnicity. This refers to persons who identified themselves in the enumeration process as being Spanish, Hispanic, or Latino. Persons whose ethnicity is identified as Hispanic or Latino may be of any race. More information on the 2003 changes in questions on race and Hispanic ethnicity is available online at http://www.bls.gov/ cps/rvcps03.pdf.
Usual weekly earnings. Data represent earnings before taxes and other deductions, and include any overtime pay, commis- sions, or tips usually received (at the main job, in the case of multiple jobholders). Earnings reported on a basis other than weekly (for example, annual, monthly, hourly) are converted to weekly. The term “usual” is as perceived by the respon- dent. If the respondent asks for a definition of usual, inter- viewers are instructed to define the term as more than half the weeks worked during the past 4 or 5 months. Data refer to the
sole or primary job of wage and salary workers (excluding all self-employed persons regardless of whether their businesses were incorporated).
Median earnings. These figures indicate the value that di- vides the earnings distribution into two equal parts, one part having values above the median and the other having values below the median. The medians shown in this publication are calculated by linear interpolation of the $50 centered interval within which each median falls.
Family. A family is defined as a group of two or more persons residing together who are related by birth, marriage, or adop- tion; all such persons are considered as members of one fam- ily. Families are classified either as married-couple families or as families maintained by women or men without spouses. A family maintained by a woman or a man is one in which the householder is never married, or is widowed, divorced, or separated.
Children. Data on children refer to one’s own children and include sons, daughters, stepchildren, and adopted children. Not included are nieces, nephews, grandchildren, other re- lated children, and all unrelated children living in the house- hold.
Reliability of the Estimates Statistics based on the CPS are subject to both sampling and nonsampling error. When a sample, rather than an en- tire population, is surveyed, there is a chance that the sample estimates may differ from the “true” population values they represent. The exact difference, or sampling error, varies depending on the particular sample selected, and this vari- ability is measured by the standard error of the estimate. There is about a 90-percent chance, or level of confidence, that an estimate based on a sample will differ by no more than 1.6 standard errors from the “true” population value because of sampling error. BLS analyses are generally conducted at the 90-percent level of confidence.
All other types of error are referred to as nonsampling error. Nonsampling error can occur for many reasons, in- cluding the failure to sample a segment of the population, inability to obtain information for all respondents in the sample, inability or unwillingness of respondents to provide correct information, and errors made in the collection or pro- cessing of data.
A full discussion of the reliability of data from the CPS and information on estimating standard errors is available at http://www.bls.gov/cps/documentation.htm#reliability.