OMB Supporting Stmt Part B 1.21.22

U.S. Department of Commerce

U.S. Census Bureau

OMB Information Collection Request

Annual Business Survey

OMB Control Number 0607-1004

Supporting Statement Part B. – Collections of Information Employing Statistical Methods

1. Universe and Respondent Selection

The 2022 Annual Business Survey (ABS) employer universe for this submission is constructed using a combination of 2019 and 2020 Internal Revenue Service (IRS) tax return data. The universe of approximately 5.4 million employer businesses will be those reporting activity on any one of the following IRS tax forms: 1040 (Schedule C), “Profit or Loss from Business” (Sole Proprietorship); 1065, “U.S. Return of Partnership Income”; 941, “Employer’s Quarterly Federal Tax Return”; 944, “Employer’s Annual Federal Tax Return”; or any one of the 1120 corporate tax forms. The ABS samples employer businesses, therefore current plans will only request responses from businesses filing the 941, 944, 1065, or 1120 tax forms.

Additionally, nonprofit organizations will be sampled to collect data on their research activities. Of note, nonprofit organizations will only see questions relating to research activities and will not be asked any questions relating to owner demographics. The universe of approximately 50,000 nonprofit organizations will come from a combination of the Census Bureau’s Business Register (BR) and the IRS Exempt Organization Business Master File (EO/BMF), excluding those operating in the Public Administration and Education industries. Also excluded are industries that are not expected to have research activities, such as Religious Organizations. Nonprofit organizations that fall below a payroll size cut-off will be excluded from the mailed sample.

The total universe size will be approximately 5.7 million including both employer businesses and nonprofit organizations . The total estimated sample size for the 2022 ABS is 308,000. Approximately 300,000 will be employer businesses. This sample size is necessary to provide summary-level estimates for women-, minority-, and veteran-owned businesses and to produce reliable estimates at the 2-digit NAICS, U.S., state, and metropolitan statistical area (MSA) levels. The remaining 8,000 of the total cases will be nonprofit organizations that will yield national and state level estimates on research activities for U.S. nonprofit organizations.

For sampled employer businesses, the ABS uses administrative data to estimate the probability that a firm is minority- or women-owned. Each firm is then placed in one of nine frames for sampling. The sampling frames are: American Indian or Alaskan Native, Asian, Black or African American, Hispanic, Native Hawaiian and Other Pacific Islander, Non-Hispanic White Men, Other, Publicly Owned, and Women. The employer business sample is stratified by state, frame, and industry and systematically sampled within each stratum. A standard type of estimation for stratified systematic sampling is used. (Refer to Sampling Techniques by W.G. Cochran.) The nonprofit organizations sample is randomly stratified by state and type of nonprofit category. The types of nonprofit category are health and medical, science and technology, and other. Organizations previously identified as having large R&D expenses from either the 2016 Nonprofit Research Activities (NPRA) survey or the 2021 ABS will be taken with certainty.

The target relative standard error for the total number of women-, minority-, and veteran-owned businesses will be less than 10 percent.

2. Procedures for Collecting Information

The ABS primary collection method is via an electronic or web based instrument. Respondents selected for the survey receive an initial letter informing them of their requirement to complete the survey as well as instructions on accessing the survey. The 2022 ABS initial mailing is scheduled for July 2022. Responses will be due approximately 30 days from initial mailing and respondents will receive a due date reminder approximately one week before responses are due. The Census Bureau plans to conduct two follow-up mailings and an optional third follow-up that may include a paper questionnaire if deemed necessary based on check-in rates. Closeout of mail operations is scheduled for January 2023 but may be extended to allow ample time to receive returned forms if necessary. Response data will be processed as they are received. Upon the close of the collection period, data processing will continue, and records will be edited, reviewed, tabulated, and disseminated.

3. Methods to Maximize Response

This information collection will maximize response through the following means:

• Mailing materials that emphasize the mandatory and confidential nature of census reports, as provided by Title 13, United States Code;

• Designing effective electronic reporting instruments and instructions;

• Offering a toll-free telephone number for companies that have questions or need assistance in completing the electronic survey;

• Conducting systematic mail follow-ups to nonrespondents;

• Conducting telephone outreach to select nonprofit organizations prior to the initial mail and during follow-up activities to encourage their response;

• Reducing mailings of similar content to similar businesses by combining several surveys into the ABS;

• Conducting nonresponse bias analysis if unit response rate falls below 80 percent.

The expected response for the ABS is estimated to be 68 percent. The expected response rate is based on results from previous ABS collections. For survey years 2018, 2019, and 2020, the average response rate was approximately 68 percent. The Census Bureau will primarily use an electronic reporting instrument to collect the data. Questionnaires may be mailed to select nonrespondents if check-in rates are lower than expected. Nonrespondents may receive a certified mailing for the second and third follow-up mailings. The Census Bureau may also plan to conduct an email follow-up to select nonrespondents reminding them to submit their report in the electronic instrument. Check-in rates are monitored regularly during collection.

Post collection, unit response rates will be evaluated. As a result of the expected response rate, the Census Bureau plans to conduct a nonresponse bias analysis in the fall of 2022. The nonresponse bias analysis will examine unit response rates and total quantity response rates to determine whether there is evidence of nonresponse bias to the key estimates of the survey. The analysis will focus on the differences of response rate by owner characteristics (by sex, ethnicity, race, and veteran status), industry, state-level geography, legal form of organization, and size of firm. To adjust for nonresponse of demographic characteristics, the sex, ethnicity, race, and veteran status are imputed using donor respondents in the same sampling frame with similar characteristics (industry, legal form of organization, geography). Donor imputations are considered reliable because sampling frame assignments are based on administrative data which have had a high level of agreement with the tabulated race and ethnicity for responding firms historically. Sampling variability estimates are adjusted to account for nonresponse. Unit nonresponse for non-demographic items is addressed using a weight adjustment where the sampling weights of responding firms are adjusted to account for the nonresponding firms. Nonresponse weight adjustments are considered reliable when the probability of response is not associated with measured characteristics.

4. Tests of Procedures or Methods

The information collection will use procedures that are based on a considerable body of experience with economic censuses and surveys, such as cognitive testing, expert panels, and evaluation of data results. Previous economic censuses have been the subject of evaluation studies that have examined methodology and conceptual issues. As a result, the procedures used by the ABS are well tested.

The survey questions have been successfully tested through cognitive interviews (see Attachments E and F).

5. Contacts for Statistical Aspects and Data Collection

Persons responsible for directing the sampling, estimation, nonresponse adjustment and disclosure avoidance procedures:

James W. Hunt, Methodology Director

Retail, Wholesale, and Services Programs

Economic Statistical Methods Division

U.S. Census Bureau

Washington, DC 20233

301-763-6599

[email protected]

Roberta Kurec, Chief

Cross Sector Surveys Statistical Methods Branch

Economic Statistical Methods Division

U.S. Census Bureau

Washington, DC 20233

301-763-4690

[email protected]

Persons responsible for directing the survey design, content development, processing, analysis and data publication:

Aneta Erdie, Assistant Division Chief

Governments and Business Owners Programs

Economic Reimbursable Surveys Division

U.S. Census Bureau

Washington, DC 20233

301-763-4841

[email protected]

Patrice N. Hall, Chief

Business Owners Branch

Economic Reimbursable Surveys Division

U.S. Census Bureau

Washington, DC 20233

301-763-7198

[email protected]

John Jankowski, Program Director

National Science Foundation

National Center for Science and Engineering Statistics

2415 Eisenhower Avenue

Alexandria VA, 22314

[email protected]

 

Audrey Kindlon, Survey Statistician

National Science Foundation

National Center for Science and Engineering Statistics

2415 Eisenhower Avenue

Alexandria VA, 22314

[email protected]

Ronda Britt, Survey Statistician

National Science Foundation

National Center for Science and Engineering Statistics

2415 Eisenhower Avenue

Alexandria VA, 22314

[email protected]

Attachments

1. ABS Letters (Initial Mail and Follow-up Letters)

2. ABS Email Contacts

3. 2022 ABS Questionnaire

4. Electronic instrument screens showing the burden statement, collection authority, and purpose and uses statements available to respondents.

5. ABS Nonprofit Organizations Cognitive Testing Results

6. ABS Owner Disability Cognitive Testing Results

7. Nonemployers Plan

8. Legal Authorities for Survey

9. Five-Year ABS Content Plan (draft)

4