Frequently Asked Questions (FAQs)

What are modeled wage estimates?

The Occupational Employment Statistics (OES) and National Compensation Survey (NCS) programs have produced estimates by borrowing from the strength and breadth of each survey to provide more details on occupational wages than either program provides individually.

The modeled wage estimates provide annual estimates of average hourly wages for occupations by selected job characteristics and within geographical location. The job characteristics include bargaining status (union and nonunion), part- and full-time work status, incentive- and time-based pay, and work levels by occupation.

How do modeled wage estimates differ from “direct” estimates?

Direct estimates are based on survey responses only from the particular geographic area to which the estimate refers. In contrast, modeled wage estimates use survey responses from larger areas to fill in information for smaller areas where the sample size is not sufficient to produce direct estimates. Modeled wage estimates require the assumption that the patterns to responses in the larger area hold in the smaller area.

Is this a new survey?

No, the existing OES and NCS surveys’ data are used to calculate modeled wage estimates for civilian workers by occupations within areas (nation, state, metropolitan, and nonmetropolitan), by job characteristics and work levels.

The sample size for the NCS is not large enough to produce direct estimates by area, occupation, and job characteristic for all of the areas for which the OES publishes estimates by area and occupation. The NCS sample consists of 6 private industry panels with approximately 3,300 establishments sampled per panel, and 1,600 sampled state and local government units.  The OES full six-panel sample consists of nearly 1.2 million establishments.

What areas are used to model the relationship between wages and the job characteristics?

Twenty-four areas are used in the NCS sample design. They consist of the 15 largest metropolitan areas, based on employment size, plus the balance of the nine census divisions.

The 15 metropolitan areas are: Atlanta-Sandy Springs-Gainesville, GA-AL CSA; Boston-Worcester-Manchester, MA-NH CSA; Chicago-Naperville-Michigan City, IL-IN-WI CSA; Dallas-Fort Worth, TX CSA; Detroit-Warren-Flint, MI CSA; Houston-Baytown-Huntsville, TX CSA; Los Angeles-Long Beach-Riverside, CA CSA; Miami-Fort Lauderdale-Pompano Beach, FL MSA; Minneapolis-St. Paul-St. Cloud, MN-WI CSA; New York-Newark-Bridgeport, NY-NJ-CT-PA CSA; Philadelphia-Camden-Vineland, PA-NJ-DE-MD CSA; Phoenix-Mesa-Scottsdale, AZ MSA; San Jose-San Francisco-Oakland, CA CSA; Seattle-Tacoma-Olympia, WA CSA; and Washington-Baltimore-Northern Virginia, DC-MD-VA-WV CSA.

The 9 census divisions area: New England, Middle Atlantic, South Atlantic, East South Central, West South Central, West South Central, East North Central, West North Central, Mountain, and Pacific.

Therefore, in the calculation of the modeled estimates, the relationships between wage rates and the job characteristics from the larger sample area are assumed to hold in all of the smaller areas that the larger area contains.

For a listing of areas covered by the latest OES estimates, see

How are modeled wage estimates calculated?

The method for calculating modeled wage estimates by job characteristics follows essentially the procedures and formula that the OES program uses to calculate its estimates, with an additional step to incorporate job characteristics and work levels from the NCS program.

For example, the wage rates of workers are typically reported as grouped data across 12 consecutive, non-overlapping wage intervals by the OES program. Data from the NCS program are then used to calculate average wage rates for these intervals and thereby produce modeled wage estimates that are published as average hourly wages. The extra step needed to produce the modeled wage estimates for the job characteristics is to allocate the OES employment data by wage interval on the basis of proportions for the job characteristics from the NCS data. These proportions are calculated for the 24 NCS sample areas, where the modeling assumptions are incorporated.

Are modeled wage estimates published at the same level of detail as OES?

No, modeled wage estimates reflect detail only where there is sufficient sample to meet publication criteria.  There are three components to the publication criteria: (1) there must be sufficient OES data to support a published estimate for the occupation in the area, (2) there must be sufficient NCS data for the area, occupation, job characteristic, and work level to support the published estimate, and (3) the NCS–OES wage estimate for the area, occupation, job characteristic, and work level must fit broadly within expectations based on the patterns of compensation data.

What types of workers are included and how are they defined?

Modeled wage estimates are calculated for civilian workers, using the NCS definition: the combination of private industry and state and local government workers.  Civilian workers exclude federal government, self-employed, agriculture sector, and private household workers.

How are workers classified into occupations?

The 2010 Standard Occupational Classification (SOC) system is used to classify workers into occupational groups, see for more information on the classification system.

What geographic areas are published?

Modeled wage estimates are published at the national, state, metropolitan, and nonmetropolitan area levels. The estimates are not produced for Guam, Puerto Rico, and the Virgin Islands.

What industries are published?

While establishments are classified in industry categories based on the North American Industry Classification System (NAICS) for sampling purposes, estimates are not published by industry. The OES publishes some occupational estimates by industry, see for more information.

What are job characteristics?

Job characteristics refer to the attributes of workers within an occupation and include worker bargaining status (union and nonunion), part- and full-time work status, and incentive- and time-based pay.

Union and nonunion status is based on the conditions for union coverage as defined by the NCS. Part- and full-time work status is not determined by a set number of hours, but is based instead on the establishment's definition of those terms. Incentive- and time-based pay is determined depending on whether any part of the pay was based directly on the actual production of the worker, rather than solely on the number of hours worked. For more information on these concepts, see the BLS Handbook of Methods, Chapter 8, National Compensation Measures (PDF).

What are work levels and how are they determined?

Work levels provide insight into the range of duties and responsibilities for an occupation and are determined by assessing four factors: knowledge, job controls and complexity, contacts (nature and purpose), and the physical environment. During data collection, points are assigned for each of the four factors and then totaled to determine the work levels of the occupation. There are up to 15 work levels, and work levels vary by occupational groups. Some jobs cannot be leveled. For more information on work levels, see NCS: Guide for Evaluating Your Firm's Jobs and Pay (PDF).

Are average annual wages available?

No, only average hourly wages are available from the modeled wage estimates.

Are modeled wage estimates available for occupations where the OES only publishes average annual wages?

Wages for some occupations that do not generally work year-round, full-time, are reported by OES either as hourly wages or annual salaries depending on how they are typically paid.  For instances where OES only publishes average annual wages (e.g., legislators, teachers, pilots, flight attendants) the average hourly wages are not available from modeled wage estimates.

When are new estimates available?

Modeled wage estimates are published on an annual basis, typically in May, with a reference period of the prior year.

Are these estimates a time series?

No. Just like the OES estimates, modeled wage estimates are point in time estimates.

Are measures of reliability available for these estimates?

Measures of reliability are not currently available. Standard errors are being developed for future publication.

Where do I find articles that further explain modeled wage estimates?

The articles linked below provide valuable information regarding the approach to pairing OES and NCS data to produce modeled wage estimates and the efforts to validate the estimates. 

Wage estimates by job characteristic: NCS and OES program data
Revisiting the dilemma of review for modeled wage estimates by job characteristic

What data are available through the OES and NCS programs?

The Occupational Employment Statistics (OES) program produces employment and wage estimates annually for over 800 occupations. These estimates are available for the nation as a whole, for individual States, and for metropolitan and nonmetropolitan areas; national occupational estimates for specific industries are also available.

The National Compensation Survey (NCS) program produces the Employment Cost Index (ECI) that measures changes in labor costs. Average hourly costs for employee compensation is presented in the Employer Costs for Employee Compensation (ECEC) series. The NCS also provides benefits incidence data on the percentage of workers with access to and participating in employer provided benefit plans.


Last Modified Date: May 25, 2017