The Occupational Employment Statistics (OES) survey is a cooperative effort between the Bureau of Labor Statistics (BLS) and the State Workforce Agencies (SWAs). BLS funds the survey and provides the procedures and technical support, while the State Workforce Agencies collect most of the data. OES estimates are constructed from a probability sample of about 1.1 million establishments. Each year, two semiannual panels of approximately 180,000 to 200,000 sampled establishments are contacted, one panel in May and the other in November. Responses are obtained by mail, online, email, telephone, or personal visit. For a given panel, most sampled establishments initially receive either a survey questionnaire or instructions for reporting their data electronically. Nonrespondents receive up to three additional mailings and may be contacted by phone or email. A sample survey form is available at https://www.bls.gov/respondents/oes/pdf/forms/uuuuuu_fillable.pdf. Instructions for electronic submission are available at https://www.bls.gov/respondents/oes/instructions.htm.
BLS has a strict confidentiality policy that ensures that 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 which 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 regarding confidentiality, please visit the BLS website at www.bls.gov/bls/confidentiality.htm.
The OES survey is a Federal-State cooperative effort that enables states to conduct their own surveys. A major concern regarding a cooperative program such as OES is the accommodation of 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 computerized quality control tool used by the OES survey is the Occupation and Wage Data Network (OWDN) system. It was developed to provide a consistent and automated framework for survey processing and to reduce the workload for analysts at the State, regional, and national levels.
To ensure standardized sampling methods in all areas, the sample is drawn in the 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 employment estimates, have resulted in the overall standardization of the OES survey methodology. This has reduced the number of errors in the data files as well as the time needed to review them.
Several edit and quality control procedures are used to reduce nonsampling error. Follow-up mailings, emails, and phone calls are sent out to nonresponding establishments to improve the survey response rate, especially those that are critical or large. Completed survey questionnaires are checked for data consistency and reviewed to verify the accuracy and reasonableness of the reported data.
Other quality control measures used in the OES survey include:
follow-up mail and telephone solicitations of nonrespondents, especially critical or large nonrespondents
review of data during collection to verify its accuracy and reasonableness
adjustments for atypical reporting units on the data file
validation of the benchmark employment figures and the benchmark factors
validation of the analytical tables of estimates at the NAICS 3/4/5/6 level
response analysis studies conducted to assess respondents’ comprehension of the questionnaire
Although most data are collected through the process outlined above, additional data sources are used for both the collection and processing of the data.
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 the U.S. Postal Service. Data from only the most recent year are retained for use in OES estimates.
In each area, 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 OES 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.
Data from the BLS Quarterly Census of Employment and Wages (QCEW) are used in occupational employment benchmarking. A ratio estimator is used to calculate estimates of occupational employment. The auxiliary variable for the estimator is the average of the latest May and November employment totals from the QCEW.
Data from the BLS National Compensation Survey (NCS) are used to compute mean wage rates for all workers in any given wage interval. Although smaller than the OES survey in terms of sample size, the NCS program, unlike OES, collects individual wage data. The mean hourly wage rate for interval L (the upper, open-ended wage interval) is calculated without wage data for pilots. This occupation is excluded because pilots work fewer hours than workers in other occupations. Consequently, their hourly wage rates are much higher.
Data from the Bureau’s Employment Cost Index (ECI) survey are used to develop wage-aging factors. The ECI survey measures the rate of change in compensation for 11 major occupational groups on a quarterly basis. Aging factors are used to adjust OES wage data from prior survey reference periods to the current survey reference period.