A mail-out/mail-back survey of about 22,000 retail businesses with paid employees, supplemented by administrative data to account for nonemployer businesses. The employer sample is drawn from the Business Register, which contains all Employer Identification Numbers (EINs) and listed establishment locations. Firms are first statified by major kind of business and estimated sales. All firms with sales above applicable size cutoffs are selected into the survey and report for all their retail industry EINs. In a second stage, unselected EINs are statified by major kind of business and sales, and randomly selected from each strata. The sample is updated quarterly to reflect employer business "births" and "deaths"; adding new employer businesses identified in the Business and Professional Classification Survey and deleting firms and EINs when it is determined they are no longer active. There is about a 9 month delay before new firms can be represented in the sample. To account for births during this interim period, data are imputed for all EINs that go out of business but are still active on the IRS mailing list.
The Annual Survey of Manufactures includes approximately 55,000 establishments selected from the census universe of 350,000 manufacturing establishments. Some 25,000 large establishments are selected with certainty, and some 30,000 other establishments are selected with probability proportional to a composite measure of establishment size. The survey is updated from two sources; Internal Revenue Service administrative records are used to include new single-unit manufacturers and the Company Organization Survey identifies new establishments of multi-unit forms.
The Census Bureau provides aggregate statistics to the NSF who has primary responsibility for releasing the data.