SpecialCensusProgram_SSB_092222

SUPPORTING STATEMENT B

U.S. Department of Commerce

U.S. Census Bureau

SPECIAL CENSUS PROGRAM

OMB Control No. 0607-0368

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 government 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. Indicate expected response rates for the collection as a whole. If the collection had been conducted previously, include the actual response rate achieved during the last collection.

Universe and Respondent Selection

Sampling methods are not employed in the Special Census Program. Each Special Census consists of a 100-percent enumeration within the geographic area designated by the governmental unit (GU). The GU can elect to have their entire jurisdiction enumerated (Full Special Census) or specific locations within their jurisdiction enumerated (Partial Special Census). Every living quarters within the selected Special Census area of the local government is enumerated. This includes housing units (HUs), group quarters (GQs), and transitory locations (TLs).

In order to achieve a 100-percent enumeration of a GU’s designated area, the Census Bureau will allow self-response using an internet self-response instrument and perform additional listing and enumeration activities using in-field data collection. Special Census mailings and reminder postcards will be sent to each HU in the Special Census area to provide information on how to respond to the Special Census through the internet self-response instrument. HU respondents will respond by using a Census Bureau-provided identification number which they receive by mail. For HUs that do not receive mailed materials or did not self-respond using the internet self-response instrument, the Census Bureau will conduct field follow up. Field work will include the listing of all HUs and enumeration of HUs that did not self-respond, GQs, and units at TLs. Following the self-response period, field representatives (FRs) will be sent to the field to facilitate data collection for HUs that did not self-respond. FRs will undertake multiple attempts and vary the timing of their visits in order to ensure an enumeration of the HU. During this in-field data collection period, residents of GQs and TLs in the designated area will also be enumerated.

2. Describe the procedures for the collection of information 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, and

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

Procedures for Collecting Information

The purpose of the Special Census is to obtain a complete and accurate population and housing count for the community as of the agreed-upon reference day, referred to as “Special Census Day.” The local government identifies area boundaries and annexations and then confirms the “Special Census area” via a map. The Census Bureau then divides the “Special Census area” into Assignment Areas (AA) for data collection purposes. AAs are small geographic areas, usually a block or group of blocks, established by the Census Bureau as a basic unit for data collection by a single FR or other field staff. The “Special Census area” is the only area where the 100-percent enumeration will occur.

Using the Census Bureau’s Master Address File (MAF), Special Census mailings and reminder postcards will be sent to each HU in the Special Census area to provide information on how to respond to the Special Census through the internet self-response instrument. The invitation letter, SC-L1(E/S), is sent to all known HUs in the Special Census area and invites them to respond via the internet self-response instrument. For HUs that do not receive mailed materials or did not self-respond using the internet self-response instrument, the Census Bureau will conduct field follow up. The invitation letter contains information about the Special Census, a unique Special Census ID for each HU, and the URL where the HU can respond online to the Special Census. The invitation letter also includes an insert with answers to frequently asked questions. Follow up mailings, including the reminder letter (SC-L2(E/S)), reminder postcard (SC-P3(E/S)), and final reminder postcard (SC-P4(E/S)), are sent to all known HUs in the Special Census area to remind them to self-respond through the Special Census internet self-response instrument.

Following the self-response period of approximately 4-6 weeks, FRs will be sent to the field using the Special Census Questionnaire (SC-Q), the AA maps, and the Address Register to facilitate data collection for HUs that did not self-respond. The Address Register is a book that lists all the known addresses in an AA, which are also extracted from the Census Bureau’s MAF. The Address Register contains the cover page, block list, address listing page (SC-920), add page (SC-921), notes page, Dependent QA Check Record (SC-435), and the maps for the AA. Special Census FRs will update the addresses contained in the Address Register, if needed, at the time of enumeration.

The FR uses the AA maps to locate the area they need to enumerate. The FR uses the Address Register to record, verify, or update addresses and related information for all living quarters in an assignment area. The FR will also conduct an interview at every HU in the assignment area that has not self-responded using a paper data collection instrument, SC-Q. There is a SC-Q with a pre-filled address label affixed for each address in the Address Register that did not self-respond. The enumeration consists of personal visits to each HU to conduct a in-person interview with the occupants to complete the SC-Q. The FR will use the Add Page (SC-921) to add addresses that are observed to exist on the ground, that are not contained on the address listing page. The FR will enumerate persons at the new HU using a blank SC-Q that does not have a pre-filled address label.

Several quality assurance measures will be implemented for each Special Census to ensure that high-quality data are gathered using the most efficient and cost-effective procedures. These include edits incorporated into the online questionnaire and the ability to validate potentially erroneous responses in the field. Independent quality assurance checks, such as initial FR observation and review of completed questionnaires, will be conducted by field supervisors and office staff. Quality control field supervisors will conduct the Dependent Quality Check (DQC) to verify that production FRs performed all listing and mapping tasks completely and accurately. Reinterview of a sample of field questionnaires will also be implemented by a quality control FR to ensure the quality of the data collected in the field.

During the Quality Control operations for HU listing and enumeration, FRs will use the Dependent QA Check Record (SC-435) to complete an address check of a random sample of addresses in every AA. FRs will use the Special Census Reinterview Questionnaire (SC-RQ) to complete reinterview visits at a random sample of HUs in every assignment area. The quality control (QC) FRs will be different from the production FRs. DQC is used to check that production FRs find all units, verify and update all information on the address registers, and perform all mapping tasks completely and accurately. The QC field supervisors only amends listing addresses for coverage updates (e.g., adds and deletes).  

GQs will be enumerated by FRs using the SC-Q-GE Questionnaire. During the enumeration visit at GQs, the FR will give the Group Quarters Facility Manager Letter (SC-LFM-GE(E/S)) to the GQ manager to provide information about the Special Census and procedures for enumerating GQs. FRs will use the Group Quarters Enumeration Control Sheet (SC-116) to list clients/residents of the GQ. An Individual Census Questionnaire for GQ (SC-Q-GE) will be completed for each client/resident of the GQ and will be placed inside a privacy envelope (SC-E-GE(E/S)).

TLs will be enumerated by FRs using the SC-Q-TL Questionnaire. During the enumeration visit at TLs, the FR will give the Transitory Locations Facility Manager Letter (SC-LFM-TL(E/S)) to the TL manager to provide information about the Special Census and procedures for enumerating at TLs. Office staff in the Special Census Office will use the TL Enumeration Control Record (SC-117) to collect contact information and schedule interviews for TLs, to determine the type of TL, and to estimate the number of interviews to be conducted at the TL. A Transitory Locations Questionnaire (SC-Q-TL) will be completed for each person staying in a transitory unit.

The listing of GQs and TLs undergo the same DQC process as HUs. However, the enumeration of GQs and TLs undergoes its own QC processes. For GQs, the Special Census office staff conduct reinterview for all GQs before checking in the GQ forms. Reinterview is conducted using the SC-116 Group Quarters Quality Control Record. During reinterview, the clerk asks if anyone visited the GQ as well as what the population count was. If necessary, the field manager will investigate and resolve any discrepancies.

TLs do not undergo reinterview and instead, quality assurance activities are conducted at the TL during the production enumeration visit. The field supervisor checks the enumeration materials and questionnaires for completeness using a QC checklist.

When there are more than six people living or staying at a HU or transitory unit, FRs will use continuation questionnaires (SC-CQ and SC-CQ-TL) to collect information for the remaining people. Each questionnaire also has a companion Spanish version, for interviewing Spanish-speaking respondents.

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

Prior to a Special Census being conducted, the Special Census Program recommends that local governments educate their residents about the upcoming enumeration by way of public service announcements, mailings, community service boards, and web site postings to ensure that residents are at ease when FRs knock on their doors and to encourage response. These activities, however, are at the discretion of the local government. 

Special Census mailings and reminder postcards will be sent to every HU with a known mailing address in the Special Census area to provide information on how to respond to the Special Census through the internet self-response instrument.

During field data collection, the Special Census SC-CN(E/S) Confidentiality Notice is distributed to the respondent at each unit visited. The SC-CN(E/S) informs respondents of the legal authority by which all U.S. Census Bureau employees are bound, for life, to protect the confidentiality of information contained in questionnaires. While participation is voluntary, historically, refusals are rarely encountered. The FR will visit the HUs several times to attempt to collect a response. If there is no answer after several visits, a proxy respondent will be used, usually a next-door neighbor.

When questionnaire data are missing or inconsistent, the Census Bureau uses a statistical method called imputation to assign values. Imputation relies on the statistical principle of homogeneity and the tendency of households within a small geographic area to be similar in most characteristics. Imputations for missing data characteristics in the Special Census processing involve a modification of the 2020 Census post-processing procedures for data editing. It uses nearest neighbor hot deck matrices to do the imputation.

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.

For the 2020 Special Census internet self-response instrument, the questionnaire and content are essentially the same as the instrument that was used for the 2020 Census. This instrument was tested extensively before the start of the 2020 Census.

For in-field data collection, the questionnaires, procedures, and methods used in the Special Census Program are essentially those that were used in the 2020 Census Update Enumerate operation. The 2020 Census questionnaires underwent extensive pretesting (cognitive testing and expert review) prior to implementation in 2020. All 2020 Census procedures and methods were the subject of an extensive and intensive evaluation and assessment program. Thus, the Special Census Program has been able to incorporate into this decade’s questionnaires, methods and procedures, the lessons learned as a result of all of the Census Bureau’s tests of 2020 procedures and methods leading up to the 2020 Census as well as the results of the 2020 Census research and evaluation program. 

In addition to the testing described above, the systems and procedures supporting the 2020 Special Census program are subject to a testing framework similar to that used in the 2020 Census. The framework includes user acceptance testing, integration testing, output testing, and operational readiness testing efforts that are reviewed as part of three significant phase gates: Test Readiness Review, Production Readiness Review, and Operational Readiness Review.

5. Provide the name and telephone number of individuals consulted on 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.

The Special Census Program uses largely the same design as the 2020 Census. In developing the design of the 2020 Census, the Census Bureau consulted with a variety of stakeholders, including, but not limited to, academics, national researchers, community and organizational leaders, the Congress (particularly through its authorizing and appropriations committees), and the Census Bureau’s advisory committees, in particular, the National Advisory Committee and the Census Scientific Advisory Committee. In addition, external consultants from the National Academy of Sciences provided regular feedback that contributed to research objectives and the ultimate design plans. Between December 2012 and February 2019, the Census Bureau held quarterly Program Management Reviews to provide updates on the status of operations and programs. These were attended by members of oversight organizations and the National Academy of Sciences. The programs were also streamed live on the internet to allow maximum exposure and awareness of plans by all stakeholders for the 2020 Census.

Findings and recommendations from over a dozen audits each, covering a variety of operations and program management activities, by the Government Accountability Office and the Department of Commerce’s Office of Inspector General were also factored into planning for the 2020 Census.

For information regarding the statistical aspects and/or data collection for the Special Census Program, contact Christine Borman, Chief, Nonresponse Operations Branch, Decennial Census Management Division, 301-763-4315, and [email protected].

Attachments to the Supporting Statement: Please see Attachment A for the Special Census Materials List

Page | 3