• Overview
• Concepts
• Data sources
  • Data collection
  • Confidentiality
  • Quality control
  • Additional data sources
• Design
• Calculation
• Presentation
• History
• More Info

• Methods Home
• About
• Programs
• Glossary
search

Handbook of Methods Occupational Employment and Wage Statistics Data Sources

Occupational Employment and Wage Statistics: Data Sources

Data collection

The Occupational Employment and Wage Statistics (OEWS) survey is a cooperative effort between the U.S. Bureau of Labor Statistics (BLS) and the state workforce agencies (SWAs). BLS funds the survey and provides the procedures and technical support, while the SWAs collect most of the data. OEWS estimates are constructed from a probability sample of about 1.1 million establishments. Each year, 2 semiannual panels of approximately 186,000 to 189,000 sampled establishments are contacted, one panel in May and the other in November. Responses are obtained online or by mail, email, telephone, or personal visit. For a given panel, most sampled establishments initially receive a letter or email with instructions for reporting their data electronically. At approximately 4-week intervals, nonrespondents receive up to three additional mailings of a survey questionnaire or letter with instructions for reporting electronically. Nonrespondents may also be contacted by phone or email. For more information about OEWS data collection, see the OEWS survey respondents webpage.

Confidentiality

BLS has a strict confidentiality policy that ensures the survey sample composition, lists of reporters, and names of respondents will be kept confidential. Additionally, the policy assures respondents that published figures will not reveal the identity of any specific respondent and will not allow the data of any specific respondent to be inferred. The most relevant statute that governs BLS confidentiality is the Confidential Information Protection and Statistical Efficiency Act (CIPSEA). Each published estimate is screened to ensure that it meets these confidentiality requirements. To further protect the confidentiality of the data, the specific screening criteria are not listed in this publication. For additional information, please visit the BLS confidentiality pledge and laws webpage.

Quality control

The OEWS survey is a federal–state cooperative effort that enables states to conduct their own surveys. A major concern in a cooperative program such as OEWS is accommodating the needs of BLS and other federal agencies, as well as state-specific publication needs, with limited resources while simultaneously standardizing survey procedures across all 50 states, the District of Columbia, Guam, Puerto Rico, and the Virgin Islands. Controlling sources of nonsampling error in this decentralized environment can be difficult. One important quality control tool used by the OEWS survey is a computerized survey data management system, which was developed to provide a consistent and automated framework for survey processing.

To ensure standardized sampling methods in all areas, the sample is drawn in the BLS national office. Standardizing data processing activities, such as validating the sampling frame, allocating and selecting the sample, refining mailing addresses, addressing envelopes and mailers, editing and updating questionnaires, conducting electronic review, producing management reports, and calculating estimates, have resulted in the overall standardization of the OEWS survey methodology. This has reduced the number of errors in the data files as well as the time needed to review them.

Several editing and quality control procedures are used to reduce nonsampling error:

• Follow-up email, mail, and telephone solicitation of nonrespondents, especially critical or large nonrespondents
• Review of collected data to verify its accuracy and reasonableness
• Adjustments for atypical reporting units on the data file
• Validation of unit matching and donor profiles
• Quality review of estimates before publication

Additional data sources

Although most data are collected through the process outlined above, additional data sources are used for both the collection and processing of the data.

Data collected through a census

A census of the executive branch of the federal government and the U.S. Postal Service (USPS) is collected annually from the U.S. Office of Personnel Management (OPM), the Tennessee Valley Authority, and USPS. Data from only the most recent year are retained for use in OEWS estimates.

A census of state government establishments, except for schools and hospitals, is collected annually every November. Data from only the most recent year are retained for use in OEWS estimates.

A census of Hawaii’s local government is conducted each November. With the exception of schools and hospitals, all local-government-owned establishments in Hawaii are included. A census of public- and private-owned hospitals is taken over a 3-year period.

BLS data sources

Data from the BLS Quarterly Census of Employment and Wages (QCEW), the database of businesses reporting to the state unemployment insurance programs, are used to adjust the employment estimates to represent the entire population covered by the OEWS survey. Population employment for each in-scope establishment—including establishments that receive modeled data—is set to equal the average of its May and November QCEW employment for the two most recent survey panels used in the estimates.