Supporting Statement A 2020 PIPFU

Department of Commerce

United States Census Bureau

OMB Information Collection Request

2020 Census Post-Enumeration Survey Person Interview and Person Followup Operations

OMB Control Number 0607-XXXX

A. Justification

1. Necessity of the Information Collection

The U.S. Census Bureau requests authorization from the Office of Management and Budget (OMB) to conduct the Post-Enumeration Survey (PES) Person Interview (PI) and Person Followup (PFU) operations as part of the 2020 Census. The 2020 PES PI and PFU operations will be conducted in the U.S. (excluding remote Alaska) and in Puerto Rico (PR) in selected PES sampled areas. Group quarters are out of scope. As in the past, including the 2010 Census Coverage Measurement (CCM) program, the PES operations and activities will be conducted separate from and independent of the 2020 Census operations.

The 2020 PES will use the dual-system estimation procedure, which uses two independent enumerations of the population. The independence between the PES and census operations is a fundamental necessity for dual-system estimation. The PES will comprise two independent enumerations of housing units and the household population within the same sample areas. These two enumerations are called the enumeration sample (E sample) and the population sample (P sample). The primary sampling unit is the Basic Collection Unit (BCU), which is the smallest unit of collection geography for 2020 Census operations. The E sample contains the list of housing units (HUs) and people enumerated in the 2020 Census within a sample of BCUs. The P sample contains HUs and people in the same sample BCUs, but obtained independently from the census. The independent roster of HUs is obtained during the PES IL operation. The P sample HUs will be matched to census HUs in the sample BCUs and surrounding BCUs. The results of the HU matching operations will be used to determine which PES and census addresses will be eligible to go to the PES Person Interview (PI) operation. The PI operation will contain approximately 190,000 HUs. The Person Interview Reinterview operation will be a sample of those cases with an estimated 28,500 HUs. During the PES PI, all sample HUs are interviewed to obtain complete rosters of the people living in the sample HUs. After people collected from the PES PI operation are matched to people collected by the census, some HUs with discrepancies or incomplete information between the PES PI and census will be sent for another interview called the PES Person Followup operation. The PFU operation will contain approximately 65,000 HUs. The PFU Reinterview operation will be a sample of those cases with an estimated 9,750 HUs.

The PES PI computer-assisted instrument will collect the following information for people in housing units:

1. Roster of people living at the housing unit at the time of the PES PI Interview operation.

2. Census Day (April 1, 2020) address information from people who moved into the sample address since Census Day.

3. Other addresses where a person may have been counted on Census Day.

4. Information to determine where a person should have been counted on Census Day (according to census residence criteria). For example, interviewers will probe for people who might have been left off the household roster, ask additional questions about people who moved from another address on Census Day to the sample address, and collect additional information for people with multiple addresses.

5. Demographic information for each person in the household on Interview Day or Census Day, including name, date of birth, age, sex, Hispanic origin, race, and relationship to Householder.

6. Name and above information for any person who has moved out of the sample address since Census Day (if known).

The PES PI instrument will also collect tenure of the household and address status for unoccupied housing units.

The paper PFU questionnaire will be used to collect address and dates-of-stay information for people selected for follow-up to verify their residence on Census Day and on the day of the PES PI for that household. PFU will also contain questions to resolve match and enumeration status codes for the P and E samples.

We also will conduct separate quality control operations for the PI and PFU operations. The first quality control operation is the Person Interview Reinterview, which contains about 15 percent of the PI workload. The second quality control operation is the Person Followup Reinterview, which contains about 15 percent of the PFU workload. These operations are implemented to ensure that the work performed is of acceptable quality.

Title 13, United States Code, Section 141 authorizes the Secretary of Commerce to conduct a decennial census of the population, and Section 193 authorizes the Secretary to conduct surveys to gather supplementary information related to the census to inform the initiation, taking, or completion of the census.

2. Needs and Uses

The PES will produce estimates of net coverage and components of coverage (correct enumerations, erroneous enumerations, imputations, and omissions) for HUs and people in HUs. These estimates will measure the coverage of the 2020 Census and may be used to improve future censuses. This is similar to methodologies of the 2010 CCM program. Prior to that, Coverage Measurement programs were designed only to measure net coverage.

The Person Interview will collect the housing unit status and an independent roster of people who lived at the sample address on Interview Day and where they lived on Census Day. These people will be used for person matching. During PES PFU, interviewers collect additional information for people unresolved after matching operations. The PES PFU operation attempts to collect additional information that might allow a resolution of match or nonmatched codes for people in the PES PI and the census list and also to resolve potential duplicates. Both operations will also collect additional addresses where the person stayed during 2020 to determine their residence on Census Day and Interview Day.

The PES Person Interview will be conducted using a computer-assisted data collection instrument on a laptop. The PFU data collection form will be created through DocuPrint technology. The questions included for each Followup case and each Followup person within that case will vary depending upon the reason the case is sent to Followup. There will be two PFU questionnaires, D-1301 and D-1301 (PR). The D-1301 is the stateside version of the form. It will be used in PES sample areas in the 50 states (excluding remote Alaska) and the District of Columbia. It will contain English wording on one side and Spanish wording on the back of each page. The D-1301 (PR) is the Puerto Rico version of the form and will be used only for the PES sample areas in Puerto Rico. This form will contain only Spanish wording.

Completed PI and PFU interviews are subject to reinterview wherein reinterviewers return to the field to verify that the household was contacted during the PI or PFU operations, respectively. If the case fails the reinterview, then the reinterviewer conducts a complete interview for the case.

Similar to PI, the PI Reinterview operation will be conducted using a computer-assisted data collection instrument on a laptop. There are also two PFU RI Forms, D-1301.2 (Attachment C) and D-1301.2 (SP). The D-1301.2 is the English version of the form. It contains the identifiable information of the PFU case to be reinterviewed. The reinterviewer will use this form to verify that the household was contacted. The D-1301.2 (SP) is the Spanish version of the form and will be used for both stateside and the PES sample areas in Puerto Rico.

Information quality is an integral part of the review of data by the Census Bureau (fully described in the Census Bureau’s Information Quality Guidelines located at http://www.census.gov/quality/). Information quality also is integral to the information collections conducted by the Census Bureau and is incorporated into the clearance process required by the Paperwork Reduction Act.

3. Use of Information Technology

The automation efforts for the 2020 PES are focused on the PES PI and PI Reinterview. Those interviews will be conducted using laptop computers. The PFU interview and PFU Reinterview, however, will use paper questionnaires. The PI and PFU interviews are conducted through personal visits while the reinterview operations are conducted through personal visits or telephone.

4. Efforts to Identify Duplication

This effort does not duplicate information collected by any other agency. By design, the data collection is duplicated between the census and the PES. The results are used to measure the coverage of the census, which is the purpose of the PES.

5. Minimizing Burden

The proposed information collection consists of collecting demographic and address information about people rostered in the PES Person Interview, PES Person Followup, PES PI Reinterview, and PES PFU Reinterview operations. Interviews will be conducted at the smallest number of housing units required to adequately estimate net coverage and the components of census coverage. Respondents will be asked the minimum number of questions to identify Census Day and Interview Day residence of the sample address and other potential addresses where they may have been counted in the census.

6. Consequences of Less Frequent Collection

The Census Bureau will conduct the PES PI and PES PFU activities only once in the 2020 Census. If these activities are not conducted, it would adversely affect our ability to measure the coverage of the population in the 2020 Census.

7. Special Circumstances

No special circumstances exist.

8. Consultations Outside the Agency

The Census Bureau has historically conducted research to evaluate results for the decennial census. We benefit from consultation with a variety of data users, including, but not limited to academics, national researchers, and community leaders. These individuals and members of the National Academy of Science and the Census Advisory Committees are well-known scholars and respected spokespeople for various communities and organizations. Both now and in the past, we have responded to advice obtained through this ongoing consultation process.

The Census Bureau published a notice in the Federal Register on June 5, 2019 (Vol. 84, Pg. 26066), inviting public comments on our plans to submit this information collection. We received comments from four writers. The first writer’s comment was not related to the collection. The second commenter, from the Partnership for America’s Children, urged the Census Bureau to devote more attention to the issue of the undercount of children, specifically for the population age 0 to 4, and to find a remedy for this problem. Census Bureau staff working on the PES have consulted with others, both inside and outside the Census Bureau, to address this concern. The Census Bureau continues to welcome internal and external research into how to improve dual-system estimates of young children. To improve the data collection of young children, the PES Person Interview instrument now includes probes specifically for the presence of babies in the household.

The third commenter, from the Georgetown Center on Poverty and Inequality and the Beeck Center, had the following recommendations:

1. Increase the sample size to account for the potential for reduced cooperation, both by householders and proxy respondents, with interviewers.

The planned workload for the 2020 PES Person Interview will be comparable to the workload for the 2010 Census Coverage Measurement (CCM) Person Interview. The Census Bureau expects similar standard errors on coverage estimates to those reported for the 2010 CCM. Historically, the post-enumeration survey has had high response rates. The 2010 Census Coverage Measurement Person Interview had a unit noninterview rate of 3.1 percent. Although past response rates are not predictive of future response rates, the PES Person Interview contact strategy (including over five in-person contact attempts and proxy responses) is extensive, helping to mitigate the drivers of nonresponse.

2. Assign Census Bureau interviewers to their local communities wherever possible.

The Census Bureau will conduct the 2020 Post-Enumeration Survey using Census Bureau employees. Recruiting, hiring, and assigning interviewers to their local communities is a good idea. We have done this in the past and plan to do something similar for 2020.

3. Add gender and owner or renter status to the demographic information collected from respondent households.

The gender and tenure status questions are included in the PES Person Interview instrument. PES will collect the same demographic information as the 2020 Census.

The fourth commenter, from The Leadership Conference on Civil and Human Rights, shared similar concerns as the other commenters. In addition to the undercount of small children, this writer is concerned about the net coverage and component estimates of other hard-to-count populations including Hispanics, non-Whites, renters, and men.

The PES will report net coverage and components of coverage for the same demographic characteristics as were reported for the 2010 Census Coverage Measurement, including by Hispanic origin, race groups, tenure, age groups, and sex.

The fourth commenter also urges the Census Bureau to take steps to complete the Person Interview operation within as short a time period as operationally feasible, without sacrificing quality and thoroughness.

The Person Interview operation will take place June 17, 2020, through September 18, 2020. The Person Followup operation will take place February 3, 2021, through March 26, 2021.

9. Paying Respondents

Respondents participating in this survey will not receive any form of compensation for their participation.

10. Assurances of Confidentiality

Confidentiality is provided under Title 13. The interviewer will give each respondent in the 50 states and the District of Columbia a copy of the Introductory Letter, Form D-1409(E/S) for PI and Form D-1709(E/S) and Form D-1609(E/S) for PFU. The PI and PFU Introductory Letters explain that any information given to the Census Bureau will be held confidential under Title 13. It also informs each respondent that participation is mandatory under Title 13.

11. Justification for Sensitive Questions

The Census Bureau perceives no question in the PES PI, PFU, PI Reinterview or PFU Reinterview as being sensitive.

12. Estimate of Hour Burden

The estimated workload is approximately 181,000 housing units for PES PI in selected BCUs in the 50 states and the District of Columbia; and 9,000 housing units for PI in Puerto Rico. From the PI workload, we will select a sample of approximately 27,200 housing units from all BCUs in the 50 states and District of Columbia, and 1,300 HUs from all BCUs in Puerto Rico for the PI Reinterview operation. To calculate the burden hours, we assumed a theoretical 100 percent response rate and an approximate completion time of fifteen minutes per case. The estimated total annual respondent burden for the PI operation is approximately 54,625 hours.

The estimated workload is approximately 62,000 housing units for PES Person Followup in selected BCUs in the 50 states and the District of Columbia; and 3,000 housing units for PFU in Puerto Rico. From the PFU workload, we will select a sample of approximately 9,300 housing units from all BCUs in the 50 states and District of Columbia, and 450 housing units from all BCUs in Puerto Rico for the PFU Reinterview operation. To calculate the burden hours, we assumed a theoretical 100 percent response rate and an approximate completion time of fifteen minutes per case. The estimated total annual respondent burden for the PFU operation is approximately 73,313 hours.

2020 Census
Operation	Estimated Number of Housing Units	Estimated Time per Response (in minutes)	Total Burden Hours
Person Interview (Stateside)	181,000	15	45,250
Person Interview (Puerto Rico)	9,000	15	2,250
Person Interview Reinterview (Stateside)	27,200	15	6,800
Person Interview Reinterview (Puerto Rico)	1,300	15	325
Person Interview Subtotal	218,500		54,625
Person Followup (Stateside)	62,000	15	15,500
Person Followup (Puerto Rico)	3,000	15	750
Person Followup Reinterview (Stateside)	9,300	15	2,325
Person Followup Reinterview (Puerto Rico)	450	15	113
Person Followup Subtotal	74,750		18,688
Totals	293,250		73,313

13. Estimate of Cost Burden

There are no cost to respondents other than their time to participate in this data collection.

14. Cost to the Federal Government

The total cost to the government for this program is estimated to be $61.5 million. The cost for the Person Interview operation and the Person Interview Reinterview operation are approximately $36.7 million. The cost for the Person Followup Operation and Person Followup Reinterview operation are approximately $24.8 million. An interdivisional Census Bureau team developed the data collection methodologies. The Census Bureau’s Decennial Census Management Division allocated the resources for the effective and efficient management of the information.

15. Reason for Change in Burden

This request for clearance pertains to new data collection efforts.

16. Project Schedule

Activity	Schedule
	Start Date	Finish Date
Conduct Person Interview	06/17/20	09/11/20
Conduct Person Interview Reinterview	06/24/20	09/18/20
Conduct Person Followup	02/03/21	03/19/21
Conduct Person Followup Reinterview	02/10/21	03/26/21

17. Request to Not Display Expiration Date

No exemption is requested. Expiration Date will be read to the respondent by the interviewer during the interview.

18. Exceptions to the Certification

There are no exemptions to this certification.