The target population of the AIES covers all domestic, private sector, non-farm employer businesses in the U.S. (50 states and the District of Columbia) as defined by the 2017 North American Industry Classification System (NAICS).  Exclusions are foreign operations of U.S. businesses and most government operations (including the U.S. Postal Service), agricultural production companies, and private households. AIES excludes data for businesses located in the United States territories. 

The AIES will include coverage of the following NAICS sectors of the U.S. economy:

• 11 - Agriculture, Forestry, Fishing and Hunting 
  • 111 - Crop Production ¹
  • 112 - Animal Production and Aquaculture ¹
  • 113 - Forestry and Logging ²
  • 114 - Fishing, Hunting and Trapping ²
  • 115 - Support Activities for Agriculture and Forestry ²
• 21 - Mining, Quarrying, and Oil and Gas Extraction ²
• 22 - Utilities
• 23 - Construction ²
• 31-33 - Manufacturing
• 42 - Wholesale Trade
• 44-45 - Retail Trade
• 48-49 – Transportation and Warehousing
  • 482 - Rail Transportation ²
  • 491 - Postal Service ¹
• 51 - Information
• 52 - Finance and Insurance
  • 525 - Funds, Trusts, and Other Financial Vehicles ¹
• 53 - Real Estate and Rental and Leasing
• 54 - Professional, Scientific, and Technical
  •  54112 - Offices of Notaries¹
• 55 - Management of Companies and Enterprises ²
• 56 - Administrative and Support, and Waste Management and Remediation
• 61 – Educational Services
  • 6111 - Elementary and Secondary Schools ²
  • 6112 - Junior Colleges ²
  • 6113 - Colleges, Universities, and Professional Schools ²
• 62 - Health Care and Social Assistance
• 71 - Arts, Entertainment, and Recreation
• 72 - Accommodations and Food Services
• • 8131 - Religious Organizations ²
  • 81393 - Labor Unions and Similar Labor Organizations ²
  • 81394 - Political Organizations ²
  • 814 - Private Households ¹
• 81 - Other Services (except Public Administration)

¹ Indicates NAICS is out-of-scope.  However, there are instances where companies with multiple locations have business activities in both in-scope and out-of-scope NAICS.  In these cases, NAICS that are considered out-of-scope will be asked to provide key data items limited to revenue, annual payroll, 1^st quarter payroll, and employment for company-owned establishments.

² Indicates NAICS is only in-scope for the collection of limited items which include company-level data (business characteristics and business classification formerly collected in the Report of Organization), capital expenditure and robotics data (formerly collected in the ACES), and key data items limited to revenue, annual payroll, 1^st quarter payroll, and employment.

The Annual Integrated Economic Survey (AIES) sampling frame is constructed from single-establishment employer companies and multiple-establishment employer companies extracted from the Census Bureau’s Business Register. The Business Register is a multi-relational database that contains a record for each known establishment located in the United States or one of its territories and has paid employees. An establishment is a single physical location where business transactions take place and for which payroll and employment records are kept.

To create the sampling frame, we first extract the records from the Business Register (as of December 2023) for all employer establishments located in the 50 states and the District of Columbia that are classified in the NAICS sectors in-scope to AIES. For these establishments we extract sales, payroll, and employment, along with name and address information from the Business Register. Other information from the Business Register along with data from the 2022 Economic Census is also added to the sampling frame for sample analysis purposes.

The sampling unit for the AIES is the company. To create the company sampling unit, for multiple-establishment companies, we aggregate the extracted establishment data to the company level by tabulating the establishment data for all establishments associated with the company. For single-establishment companies, no aggregation is necessary to put the establishment on a company basis.

The measure-of-size (MOS) variable used for the AIES sample design is based on administrative annual payroll, which is available for most establishments on the AIES sampling frame and is generally positively correlated with the AIES key data items.

Approximately 385,000 companies will be included in the sample.  Of the sampled companies, approximately 48,500 are identified as self-representing (included with probability = 1) based on the diversity of their operations.

For sectors 11, 21, 23, and 55, companies are sampled at the sector level. The remaining companies on the frame are stratified into broad strata defined by the 3-digit NAICS subsector. A zero MOS stratum is also defined for each sector level, containing companies active in the previous Economic Census but not active on the most recent vintage of the Business Register. For select sectors, the broad strata are further defined using:

• type of operation (only in wholesale sector 42) or
• tax-exempt status (only in professional, scientific, and technical services sector 54; educational services sector 61; health care and social assistance sector 62; arts, entertainment, and recreation sector 71; and other services sector 81).

Companies are further sub-stratified within broad stratum by nesting geographic groups as follows:

• One multi-geography stratum for each unique broad stratum, containing all multi-unit companies that operate in two or more geographic categories within that broad stratum.
• Twenty-seven single-geography strata: one stratum for each unique broad stratum, cross-classified by geographic categories.

The geographic categories for stratification are specified in the table below. Each direct-use state defines a unique geographic stratum. Each “Balance of Region” stratum contains companies that operate in one or more of the states included in the collapsed geographic group.

Sample size allocation

Allocation is performed independently by sector. The AIES requires a minimum stratum sample size of 5 and targets a maximum sampling fraction of 0.30. The maximum sampling fraction allowed is 0.50. Consequently, each geographic stratum with less than 15 companies is automatically designated as a certainty stratum with inclusion probability equal to 1.

In each zero MOS stratum, all companies are sampled with equal probability. A small sample is selected with a sampling rate of approximately 0.005. If 5 or fewer companies are in the zero MOS stratum, then all units will be sampled with probability equal to 1.

The remaining within-sector strata allocations are obtained in two steps. First, proportional allocation is used to allocate the sector sample size to the unique broad stratum based on the proportion of companies in the sector that fall in the broad stratum. Then, a power allocation is used to allocate the broad stratum sample size to each geographic substratum.

Once sample size allocation is complete, the inclusion probabilities for each company are calculated based on each companies’ contribution to national industry (typically 6-digit NAICS) level estimates and geographic x 3-digit NAICS estimates. For small companies with similar MOS and inclusion probabilities, a data-driven weight trimming algorithm is used to determine the threshold for the minimum inclusion probability in a given substratum.

Sample Selection

AIES uses an unequal probability stratified sequential sampling design, also known as Chromy’s method. This stratified sequential sampling is a without-replacement probability proportional to estimated size sampling method that allows for a within-strata sort; thereby, implicitly offering an additional level of sub-stratification. To perform the sort, each company on the frame is assigned a single stratification industry corresponding to the company’s lowest unique level of NAICS classification. Within each AIES sampling stratum, companies are sorted by stratification industry, state, and MOS. The estimated size is a company’s inclusion probability.

Matrix Sampling for the Manufacturing Sector

With the AIES, there will be an ongoing focus on finding the right balance between satisfying user demands for expansive (and detailed) data without overburdening the sampled companies during collection.  A matrix sampling design is a commonly used survey methodology technique designed to reduce respondent burden while allowing unbiased estimation (with a measurable "cost" of increased sampling variance). In a matrix (or split panel) sample, sets of questions are randomly assigned to different sampled units, so that each question has a known inclusion probability. The AIES will pilot this approach in the manufacturing sector in its first year of data collection. Companies in the AIES sample with establishments conducting business in the manufacturing sector will be asked to provide information on a suite of items for each establishment. To reduce burden on noncertainty companies in the AIES sample, mostly single-location companies, the AIES will introduce a matrix sampling design.  

For the matrix design, AIES self-representing companies (included in AIES with probability = 1) with establishments in the manufacturing sector will be asked to provide data for all items at each establishment. For the remaining companies in the AIES sample with manufacturing activity, the previously defined strata are maintained for the matrix sample design. Manufacturing sector strata with fewer than 15 noncertainty (selected with probability < 1) companies selected for AIES collection are defined as self-representing strata for the matrix design. Strata with more than 15 noncertainty companies selected in the AIES sample are split into two panels by conducting a simple random sample with a 1 in 2 sampling rate. The companies selected for the first panel will be asked the full set of manufacturing questions at each establishment, while the second panel will only be asked to provide data on four items: annual payroll, total receipts, first quarter payroll, and March 12 employment.

There are approximately 43,500 companies in the AIES sample with activity in the manufacturing sector. Of these, 33,000 companies will receive the full set of manufacturing items for each establishment, and the remaining 10,500 companies will only be asked for information on the previously listed four items at each establishment.

The inaugural sample will be redesigned after two years.  Subsequent sample redesigns will take place every 3 years.

Information will be provided as it becomes available.

Data items requested

The AIES collects the following information from most employer businesses in sample:

• Business characteristics, including employment, operating status, organizational change, ownership information, and co-op status
• Business classification, including business activity, type of operation, and tax status
• Revenue, including sales, shipments, and receipts, revenue by class of customer, source of revenue, taxes, contributions, gifts, and grants, products, and e-commerce activity
• Operating expenses, including purchased services, payroll, benefits, rental payments, utilities, interest, resales, equipment, materials and supplies, research and development, and other detailed operating expenses
• Assets, including capital expenditures, inventories, and depreciable assets
• Robotic equipment

Additional information regarding the AIES content planned for collection can be found in the AIES Content Summary.  

Key data items

Revenue and payroll are required to be counted as a response.

Type of request

Response is required by law.  The AIES OMB control number is 0607-1024. The AIES collection is authorized by Title 13 U.S.C. Sections 131 and 193.  Response to the AIES is mandatory per Sections 224 and 225 of Title 13 U.S.C.

Frequency and mode of contact

The AIES will be collected annually.

Firms will receive a mailing with instructions to provide responses online via a spreadsheet.  Due date and follow-up mailings and emails are also conducted during the collection period.  Phone calls will also be utilized to follow-up with firms that fail to respond, and data may also be obtained in this manner.

Data collection unit

All single-establishment firms and multi-establishment firms will be asked to report data at the company, industry and establishment unit.

Information will be provided as it becomes available.

Information will be provided as it becomes available.

Information will be provided as it becomes available.

Published estimates from the AIES will be benchmarked to the Economic Census.

Cell suppression is a disclosure avoidance technique that protects the confidentiality of individual survey units by withholding cell values from release and replacing the cell value with a symbol, usually a “D”.  If the suppressed cell value were known, it would allow one to estimate an individual survey unit’s response too closely.

The cells that must be protected are called primary suppressions.

To make sure the cell values of the primary suppressions cannot be closely estimated by using other published cell values, additional cells may also be suppressed. These additional suppressed cells are called complementary suppressions.

The process of suppression does not usually change the higher-level totals. Values for cells that are not suppressed remain unchanged. Before the Census Bureau releases data, computer programs and analysts ensure primary and complementary suppressions have been correctly applied.

The Census Bureau has reviewed this data product to ensure appropriate access, use, and disclosure avoidance protection of the confidential source data (Project No. #######, Disclosure Review Board (DRB) approval number: CBDRB-FY##-###)

Information will be provided as it becomes available.