2018EndtoEndCensusTest_SupportingStatement_Part B_v2

Department of Commerce

United States Census Bureau

OMB Information Collection Request

2018 End-to-End Census Test – Peak Operations

OMB Control Number XXXX-XXXX

Part B – Collection of Information Employing Statistical Methods

1. Universe and Respondent Selection

The U.S. Census Bureau will conduct the 2018 End-to-End Census Test to test data collection methods for the 2020 Census. Participating in the 2018 End-to-End Census Test will be mandatory for those units in the selected areas. The Census Bureau will concurrently contact approximately 277,000 housing units and 500 group quarters units in Providence County, RI. The Peak Operations portion of the 2018 End-to-End Census Test is comprised of four major phases: Self-Response (including the option to respond without providing a preassigned census identification code called a User ID), Update Leave (UL), Nonresponse Followup (NRFU), and Group Quarters (GQ).

All addresses within the portion of the test designated as the Self-Response geographic area will be included in the initial mailouts to encourage self-response. No known group quarters will be selected for the self-response mailout. The Census Bureau estimates a self-response rate of 42 percent in the test.

The 2018 End-to-End Census Test also includes a UL operation involving a subset of approximately 2,000 housing units and a NRFU operation involving approximately 163,000 housing units (based on the projected self-response rate). Finally, the GQ operation will include approximately 500 group quarters units.

2. Procedures for Collecting Information

Census Day for the 2018 End-to-End Census Test will be April 1, 2018. The test will employ four response modes for housing units: internet self-response on a secure website, paper questionnaire, Computer Assisted Telephone Interviewing (CATI) using Census Questionnaire Assistance, and Computer Assisted Personal Interviewing (CAPI) during field enumeration. The CATI modes will be available in English, Spanish, Chinese, Vietnamese, Korean, Russian, Arabic, and Tagalog, with the internet, paper and CAPI modes available in English and Spanish. For GQs, five response modes are available: electronic transfer of response data (eResponse); in-person interview; drop off and pickup of paper questionnaires, which are completed by self-enumeration; facility self-enumeration; and paper response data listing, also known as paper administrative records. The GQ modes will be available in English and Spanish.

As in previous censuses and tests, the Census Bureau will accept responses from respondents who do not have the unique User ID assigned by the Census Bureau for their living quarters. These responses, designated as Non-ID responses, will be checked against the Census Bureau’s address list. In addition, Census Bureau staff will review each address not matched during automated processing as part of a manual Non-ID Processing operation. This may require contacting respondents in some instances to obtain further address information to help obtain a match to the frame or to request assistance to accurately locate their living quarters in the absence of a match.

Self-Response

All addresses in the selected test site will be contacted to participate in the test.

Starting on or about March 16, 2018, addresses in the portion of the test designated as the Self-Response geographic area will receive mail materials encouraging the household to respond to the 2018 End-to-End Census Test. Most housing units will receive the Internet First contact strategy, in which the initial mailings will encourage online responses, and the Census Questionnaire Assistance number will be provided and callers will be able to provide their census responses in a telephone interview. The mailings for the Internet First panel will be staggered over multiple cohorts to modulate the response load on the receiving systems. Housing units in areas that are less likely to respond online will receive the Internet Choice contact strategy, in which the first mailing will include a paper questionnaire.

Later mailings for both contact strategy panels will be similar. In the second mailing, a reminder letter will be sent four days after the initial mailing. Then, a second reminder (mail postcard) will be sent to nonrespondents 10 days later. Approximately three weeks after the initial notification, the Census Bureau will send a third reminder with a paper questionnaire to all nonrespondents, asking them to complete the questionnaire and return it in the business reply envelope provided. They will also be informed they can still choose to respond online or by telephone. A final “It’s Not Too Late” postcard reminder will be sent to housing units that do not respond by paper, telephone, or through the internet.

Update Leave

Between March 19, 2018, and April 13, 2018, census enumerators will canvass the entirety of the Update Leave geographic area to identify every place where people could live or stay and will compare what they see on the ground to the existing census address list to either verify or correct the address and location information. UL uses a dependent address list that is extracted from the Master Address File (MAF), and field staff work from the addresses that exist on the ground to the address list to provide updates. These updates can include corrections to an address, such as spelling or number errors, adding an address to the list, marking an address on the list as nonexistent, or validating an existing address record and all the accompanying data.

In addition, the enumerators will leave an Internet Choice package at all housing units that gives respondents the option to respond online, by phone, or by filling out a paper questionnaire. Any self responses not received will be sent to the NRFU operation for additional attempts.

Nonresponse Followup

Between May 10, 2018, and July 24, 2018, after sufficient time has elapsed for self-response, census enumerators will contact the nonresponding housing units to conduct the NRFU operation. However, to avoid missing students who reside in off-campus housing units and may leave campus before that, Early NRFU will be conducted between April 5, 2018, and May 9, 2018, in blocks near colleges and universities with a high percentage of off-campus housing. The enumerators will determine the Census Day (April 1, 2018) occupancy status of the housing units and will enumerate the members of housing units determined to be occupied. Data will be collected using mobile devices.

At certain points during the NRFU operation, administrative records (AdRec) modeling will be performed on all NRFU cases. The result of this modeling will give each case one of four modeled status outcomes: 1) occupied, 2) vacant, 3) delete, or 4) no determination. Addresses modeled as “occupied”, “vacant” or “delete” will have a final mailing contact attempt. If the outcome of the mailing is inconsistent with the modeled status–that is, a mailing returned by the USPS as “undeliverable as addressed” for an “occupied” address, or a mailing successfully delivered for a “vacant” or “delete” address–then the address will be included in the NRFU workload for handling with normal follow-up procedures. Otherwise, where the outcome of the mailing confirms an “occupied” status, the address will be removed from the NRFU workload after one unsuccessful personal visit attempt, while for a confirmed “vacant” or “delete” status, the address will be immediately removed. Addresses without a modeled status will be handled with normal follow-up proceedures in NRFU. Additionally, to assess the accuracy of AdRec determinations, twenty percent of the cases that undergo AdRec modeling will be sent to the field during NRFU.

Enumerators will be trained on how to encourage reluctant respondents to participate, such as reassuring them of their data privacy and explaining the goals of the test and its importance in developing a quick, easy, and safe 2020 Census. Enumerators will also be trained on how to verify whether an address is vacant, determine if an address has changed, or whether the address refers to something that no longer meets the Census Bureau’s definition of a housing unit.

Notice of Visit forms left by enumerators during unsuccessful contact attempts will include Census Questionnaire Assistance numbers and the web address for the Internet Self-Response site.

Under specific circumstances, data may be collected from proxy respondents, such as a hard refusal by a household member. Addresses believed to be occupied become proxy-eligible after a variable number of unsuccessful contact attempts. Addresses believed to be vacant or not a housing unit will become proxy-eligible for a period of time after each unsuccessful contact attempt.

Between April 4, 2018, and July 31, 2018, a sample of completed NRFU cases will be selected for a quality control reinterview, where a different enumerator will attempt to make contact with and collect data from the original respondent. These collected data will later be compared to the original collected data. This comparison process will help to determine potential falsification by NRFU enumerators and ensure quality in the NRFU operation.

In addition to a production or reinterview case type, an enumerator may have a Non-ID Field Verification case on their caselist. Cases that self-responded without a User ID and could not be matched to the Census Bureau address list will be included in the NRFU workload for field verification. The purpose of this field verification data collection is to verify by observation if the address in question actually exists on the ground. Field Verification does not require an interview with a respondent.

Group Quarters

Between February 5, 2018, and March 9, 2018, staff will contact known group quarters during the GQ Advance Contact operation to collect facility contact and planning data, including the ability of the GQ facility to provide electronic records for the enumeration. The GQ Advance Contact will be an in-office operation. GQ facilities not contacted during the GQ Advance Contact will be contacted and enumerated during the GQ Enumeration operation.

Between March 28, 2018, and June 8, 2018, enumerators will contact group quarters to conduct the GQ Enumeration operation (including service-based locations). The data from group quarters will be collected through the following possible options: receiving an electronic transfer of Administrative Records from the group quarters administrators, in-person interview using the paper questionnaire, self-enumeration through a GQ administrator or point of contact being sworn in and trained to collect the response data, dropping off and picking up of paper questionnaires, and the picking up of paper administrative records, referred to as paper response data collection. Between June 11, 2018, and July 24, 2018, in a second wave, Late GQ Enumeration will be conducted to confirm and enumerate cases identified as possible GQs from the UL operation.

Between April 4, 2018, and July 17, 2018, a sample of completed GQ cases will be selected for a quality control reinterview, referred to as GQ QC. A different enumerator will attempt to make contact with and collect data from the original respondent, which will later be compared with the original received data. The Census Bureau will also test centralized phone contacts of the reinterview cases before sending them to an enumerator in the field.

Re-Collect and Coverage Improvement Components

Between April 4, 2018, and July 31, 2018, Re-Collect is conducted in which respondents from a sample of self-response cases are re-contacted to validate responses. Re-Collect is one aspect of fraud detection and may occur through centralized phone contact or in-field enumeration.

Between March 30, 2018, and August 7, 2018, Coverage Improvement is conducted to resolve potential erroneous enumerations and omissions from the initial self-response and field enumeration data collection. Coverage Improvement cases will be identified and prioritized, with respondents contacted by telephone to attempt resolution.

3. Methods to Maximize Response

Self-Response

One of the primary objectives during the 2018 End-to-End Census Test is to implement the two different contact strategies that are currently planned for the 2020 Census, in order to maximize self-response rates. Each contact strategy is designed to increase the number of households that respond online or return a questionnaire that is delivered by mail. These strategies have been tested and refined based on the results of previous Census Bureau tests, as described elsewhere in this document. Results from this test will provide additional data about maximizing self-response rates.

The first strategy is the Internet First, in which housing units will initially not receive a paper questionnaire, but rather a letter that describes the test and includes instructions about how to respond online. The second strategy is the Internet Choice, in which housing units will initially receive the paper questionnaire along with an explanation on how to respond on the internet, as an option.

Paper questionnaires will be sent to nonrespondents in each of the panels about three weeks after the initial contact notification. The paper questionnaire is an opportunity for those without internet access or a telephone, or with reservations about providing their data online or by phone, to respond. However, households that receive the paper questionnaire still have the option to respond online or on the phone.

Self-Response Panel Design

Panel	Cohort	Mailing 1 Letter	Mailing 2 Letter	Mailing 3* Postcard	Mailing 4* Letter + Questionnaire	Mailing 5* “It’s not too late” Postcard
Internet First	1	March 16	March 20	March 30	April 9	April 19
	2	March 19	March 23	April 2	April 12	April 23
	3	March 22	March 26	April 5	April 16	April 25
Internet Choice	N/A	March 16 Letter + Questionnaire	March 20	March 30	April 9	April 19

*Targeted only to nonrespondents

All dates are in calendar 2018.

4. Tests of Procedures or Methods

In developing these tests, the Census Bureau consulted with a variety of stakeholders, including, but not limited to, academics, national researchers, community and organizational leaders, and the Census Bureau’s Advisory Committees. In addition, external consultants from the National Academy of Sciences shared information about other relevant studies and provided quarterly feedback about the Census Bureau’s research plans and objectives for the 2018 End-to-End Census Test. The objectives for optimizing self-response in the 2018 End-to-End Census Test are largely building on findings and lessons learned from the 2015 National Content Test and other census tests since 2010, with the goal of optimizing the rate at which the public self-responds to the census. The Census Bureau is introducing both a mail contact strategy and an internet response strategy.

The results from this test will be shared widely with decennial census stakeholders.

5. Contacts for Statistical Aspects and Data Collection

For more information, contact Robin A. Pennington 301-763-8132, <robin.a.pennington@census.gov>.

5