2021 PRA Supporting Statement B

Supporting Statement
U.S. Department of Commerce
National Telecommunications and Information Administration
NTIA Internet Use Survey
OMB Control No. 0660-0021

B. Collections of Information Employing Statistical Methods

1. Describe (including a numerical estimate) the potential respondent universe and any sampling or other respondent selection method to be used. Data on the number of entities (e.g. establishments, State and local governmental units, households, or persons) in the universe covered by the collection and in the corresponding sample are to be provided in tabular form for the universe as a whole and for each of the strata in the proposed sample. If the collection has been conducted previously, include the actual response rate achieved during the last collection.

The CPS is an address-based sample derived from the Census Master Address File (MAF) covering the 50 states and the District of Columbia. The potential respondent universe for the CPS is one household respondent for each of the 128 million households. From this universe, we randomly select a sample of approximately 70,000 households each month. Of these, approximately 59,000 households will be eligible for interview, since approximately 11,000 households are found to be vacant, converted to a business, destroyed, or other reasons. The expected yield of completed interviews is 50,000 households per month.

Table B.1: Universe, Sample Count, and Expected Response Rate

Type of Entity	Total Universe	Sample Size	Expected Response Rate	Actual Response Rate (Annual Average)
Households	128,000,000	59,000	84.0 %	80.0 %

All households within CPS are eligible for the NTIA Internet Use Survey, which is administered as a CPS supplement.

2. Describe the procedures for the collection, including:

• Statistical methodology for stratification and sample selection

• Estimation procedure

• Degree of accuracy needed for the purpose described in the justification

• Unusual problems requiring specialized sampling procedures

• Any use of periodic (less frequent than annual) data collection cycles to reduce burden.

The Census Bureau will request survey participation from approximately 59,000 households each month via one of two modes: computer-automated personal interviewing or computer-automated telephone interviewing. The first contact for each household is attempted in-person, and successive monthly contacts are allowed by telephone. Attachment B-1 gives an overview of the CPS sample design and estimation methodology. The CPS produces demographic data, labor force data, and data from various periodic supplemental inquiries. We designed the CPS sample to produce estimates of employment and unemployment characteristics with sufficient reliability to meet the Bureau of Labor Statistics' requirements for monthly data and estimates of month-to-month, quarter-to-quarter, and year-to-year changes. The coefficient of variation on estimates of unemployment is 1.9 percent monthly at the national level. It is 8.0 percent annually at the state level. This degree of accuracy is sufficient to meet the needs mandated.

In accordance with our standard practice, the CPS sample has been redesigned based on information collected in the 2010 Decennial Census. (See Attachment B-1).

One of the primary goals for the CPS is to provide estimates of month-to-month change in the employment and unemployment statistics. The current rotation pattern for the CPS (4-8-4) was chosen because it provides such estimates reliably with a much smaller sample size than an annual rotation would.

3. Describe methods used to maximize response rates and to deal with nonresponse. The accuracy and reliability of the information collected must be shown to be adequate for intended uses. For collections based on sampling, a special justification must be provided if they will not yield "reliable" data that can be generalized to the universe studied.

Attention is placed on the following design elements to help increase cooperation by prospective respondents.

• Questions were developed with logical, clear wording and simple grammar.

• Questions were grouped according to subject areas.

• Respondent contact strategies and letters have been carefully designed to maximize respondent attention and interest.

• Monthly interviewer instruction and training on survey concepts and respondent cooperation strategies.

• Close monitoring of real-time data to react quickly to low response rates.

Refer to section 3 of Attachment B-1 for a discussion of the CPS nonresponse.

4. Describe any tests of procedures or methods to be undertaken. Testing is encouraged as an effective means of refining collections of information to minimize burden and improve utility. Tests must be approved if they call for answers to identical questions from 10 or more respondents. A proposed test or set of tests may be submitted for approval separately or in combination with the main collection of information.

An extensive program of testing was conducted on CPS methods, procedures, and content from 1978 through 1993 using the Methods Development Survey (MDS), and its predecessor, the Methods Test Panel (MTP).

The results of the testing have become the CPS Labor Force instrument, which uses an automated Computer Assisted Telephone Interviewing/Computer Assisted Personal Interviewing environment. For information on the results, see the February 1994 Employment and Earnings article titled, “Revisions to the Current Population Survey Effective January 1994.”

In addition, since 1994 the roster and demographic collection questions have been thoroughly vetted and reviewed on a regular basis. Any changes to the Roster Collection or Demographic Characteristic questions are reviewed at the corporate level within the U.S. Census Bureau. Following standard testing procedures, any changes are cognitively tested, then tested in the field by the survey designated to first use them, and then reviewed and incorporated in any other survey using the same mode, with a need for the same collection. The current questions covered under this clearance request were included in the most recent Decennial Census Content test, American Community Survey (ACS) content test, and ACS production.

Procedurally, each month before production, each data processing system is tested for any errors. On a test platform, we mimic interviewing to collect test data. As part of the initial load of data and instruments, we test case assignments in the field as well. In the winter of 2013, as part of the sample redesign that began in April 2014, all systems were thoroughly tested in three rounds.

The proposed NTIA Internet Use Survey questionnaire underwent two rounds of cognitive testing, the results of which were used to improve wording of the questionnaire to increase data accuracy and reduce response burden. While the Census Bureau is working to complete its formal cognitive testing report, slides discussing the findings from each round of testing are available in Attachments B-2 - 2022 CPS CIUS Cognitive Test: Round 1 Preliminary Findings and B-3 – 2022 CPS CIUS Cognitive Test: Round 2 Preliminary Findings.

5. Provide the name and telephone number of individuals consulted on the statistical aspects of the design, and the name of the agency unit, contractor(s), grantee(s), or other person(s) who will actually collect and/or analyze the information for the agency.

Contacts regarding the statistical data collection and analysis operations:

Statistical Design:

Tim Trudell

Lead Scientist, Current Population Survey

U.S. Census Bureau Demographic Statistical Methods Division

(301) 763-0465

Data Collection Survey Design:

Kyra M Linse

Acting Survey Director, Current Population and Time Use Surveys,

Associate Directorate Demographics Programs

(301) 763-9280

3