BLS Handbook of Methods

Chapter 2.
Employment, Hours, and Earnings from the Establishment Survey

Data Sources and Collection Methods

Sample data
Each month, the State agencies cooperating with BLS, as well as BLS Data Collection Centers, collect data on employment, payrolls, and paid hours from a sample of establishments. Data are collected through various automated collection modes and by mail. Touch-tone data entry (TDE) serves as the primary type of electronic reporting, although a large number of reports are collected via direct electronic file transmission (EDI), and a small but growing number are received via the Internet (Web). Additionally, many respondents report via computer-assisted telephone interviews (CATI) or FAX. Table 1 summarizes the distribution of the CES sample by collection mode.

Sample enrollment. Each year, new sample units are enrolled in the CES survey to account for the births of new firms, to realign the sample distribution with the universe distribution, and to rotate a portion of the sample. Approximately 40,000 sample units are enrolled each year. New enrollments generally report via CATI for a number of months and then may be converted to one of the automated reporting modes such as TDE, FAX, or Web.

Data reporting. Each month, the respondents extract the requested data from their payroll records, which are maintained for a variety of payroll, tax, and accounting purposes. Data are collected for the pay period that includes the 12th of each month. The CES forms shown at the end of this chapter provide information on CES data concepts and definitions.

All firms with 1,000 employees or more are asked to participate in the survey, as is a sample of firms across all employment sizes. In 2003, the CES sample consisted of about 160,000 businesses and government agencies that represented approximately 400,000 individual worksites drawn from a sampling frame of UI tax accounts. The sample rotation plan allows most firms to report for 4 years and then be rotated out of the sample for a similar period.

A CES reporting form (BLS form 790 series) is provided to all CES respondents except those that report via electronic file. For units that report via CATI, TDE, or Web, the form provides a convenient means to record their data each month. For units that report via mail, the form is submitted each month by the respondent, edited by the State agency, and returned to the respondent for use again the following month. The CES report form has been used since 1930, but there have been substantial changes in its design and in the data collected over this timespan. Six variations of the basic CES form currently are used. The variations tailor the data items, concepts, and definitions for each major industry sector. Separate forms are used for natural resources and mining, construction, manufacturing, service-providing industries, public administration, and educational services.

The design of the CES form is particularly important in maintaining continuity and consistency in reporting from month to month. The use of a single form for the entire year allows the respondent to compare the latest data submitted with the data submitted in prior months.

All reported data, regardless of method of collection, are edited by the State agency or the BLS Data Collection Center each month to ensure that the information is correctly reported and that it is consistent with the data reported by the establishment in earlier months. The State agencies and Data Collection Centers electronically transmit the data to the BLS central office in Washington, DC, where the data are further edited to detect processing and reporting errors that might have been missed in the initial editing. When questionable reports are discovered at any stage of the editing process, the collection site responsible for the initial collection of the data contacts the respondent for clarification or correction. The staff of the BLS Washington office prepares national estimates of employment, hours, and earnings using the edited data. The State agencies also use the data to develop State and area estimates.

Benchmark data
Since 1940, the basic source of benchmark information for “all employees” has been the periodic tabulations compiled by State Employment Security Agencies from reports filed by establishments covered under State UI laws. The State agencies receive quarterly reports from each employer subject to the UI laws; these reports show total employment in each month of the quarter and the total quarterly wages for all employees. The State agencies submit tabulations of these reports to the BLS Washington office each quarter. (See chapter 5.)

For the few industries exempt from mandatory UI coverage, other sources are used for benchmark information. For example, data on employees covered under Social Security laws, published by the U.S. Census Bureau in County Business Patterns, augments the UI data for religious organizations, private schools, and interns and trainees in hospitals. The Surface Transportation Board, the Federal agency charged with regulating interstate surface transportation, provides data for interstate railroads.

The UI data for State and local government employment are supplemented as necessary with Census Bureau data derived from the Census of Governments for local elected officials and certain other groups. A short description of the benchmark process is given in the section on estimating procedures for employment, below.

All estimates back to the most recent benchmark month are subject to revision each year when new benchmarks become available. National benchmarks are published 11 months after the benchmark month (March). For example, the revised estimates based on the March 2003 benchmarks were released in February 2004. The interbenchmark revision period extended from April 2002 through February 2003. Estimates based on the new benchmark level also were released in February of 2004 for the postbenchmark period—April 2003 through January 2004. Subsequent estimates also are based on the 2003 benchmark levels until release of the 2004 benchmark.

To determine the appropriate revisions, the new benchmarks for March are compared with the estimates previously made for that month. The differences represent: 1) Estimating errors that accumulated since the previous benchmark revision and 2) corrections to establishments’ industry classification. These differences are assumed to have accumulated at a regular rate. The all-employee estimates are wedged, or tapered, in order to smooth out the differences between the new and old benchmarks. Estimates for the 6 months subsequent to the benchmark month are revised by applying the previously computed sample movement and new factors reflecting firm births and deaths to the new benchmark level. (See the section on estimating procedures for a discussion of the treatment of firm births and deaths in the CES program.) Estimates for women workers and production workers are recomputed using the revised all-employee estimates and the previously computed sample ratios of these workers to all employees. Estimates for the months after the benchmark include the sample updates and new birth/death factors, as well as the effects of linking from a new benchmark level.

Next: Sample Design