Supporting Statement B

Status: Original and derived artifacts are available for this document.

Download: docx | pdf | html

Supporting Statement for Paperwork Reduction Act Submissions
Survey of Market Absorption
of New Multifamily Units (SOMA)
OMB Control # 2528-0013

B. Collections of Information Employing Statistical Methods

    1. Describe (including a numerical estimate) the potential respondent universe and any sampling or other respondent selection methods 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.


The buildings selected for SOMA are those included in the Census Bureau's Survey of Construction (SOC). For SOC, the United States is first divided into primary sampling units (PSUs) which are sampled based on population. Next, a sample of permit-issuing places is selected within each sample PSU. Finally, all buildings with five or more units within sampled places as well as a subsample of buildings with one to four units are selected for the SOC sample.

The respondent universe consists of builders, building managers, rental agents, sales agents, and landlords of newly completed real estate developments or buildings containing five or more units.

A more detailed description of the SOC methodology can be found here: https://www.census.gov/construction/soc/methodology.html.

The expected response rate for the collection is 80% or higher. The response rate for 2021-2023 SOMA completions were as follows: 

Completion Quarter
Sample Size
Weighted Response Rate (%)
2023 annual
4,500
92.9
Q1 2023
1,100
95.3
Q2 2023
1,200
92.5
Q3 2023
1,100
91.0
Q4 2024
1,200
93.0
2022 annual
3,800
97.0
Q1 2022
850
95.3
Q2 2022
900
97.9
Q3 2022
950
97.6
Q4 2022
1,000
96.8
2021 annual
4,000
96.6
Q1 2021
1,000
94.3
Q2 2021
1,100
96.2
Q3 2021
1,000
97.5
Q4 2021
950
98.5

A more detailed description of the SOMA sample design, weighting, and accuracy of the estimates can be found here: https://www.census.gov/programs-surveys/soma/technical-documentation/source-accuracy.html

    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.

Buildings for SOMA come from those included in the Census Bureau’s Survey of Construction (SOC). Because SOMA uses the SOC sample, we begin by describing the sample design of SOC.
 
In the first stage of the SOC’s sample design, the United States is divided into primary sampling units (PSUs) that are stratified based on population and building permit activity. PSUs with large populations or high permit activity are classified as self-representing. Otherwise, PSUs are classified as non-self-representing. In the last SOC, there were 48 self-representing PSUs and 772 non-self-representing PSUs. Non-self-representing PSUs were stratified into 121 strata by Census Division, permit activity, metropolitan status, and population. Next, one PSU is randomly selected from each stratum (for a total of 169 PSUs).

In the second stage of the SOC’s sample design, a sample of geographic locations is chosen within each of the 169 selected PSUs. Areas that don’t require building permits are selected separately from the permit-issuing places. Approximately 80 block groups of non-permit areas were selected from the sample PSUs. Permit-issuing places are stratified by permit activity. Approximately 900 permit-issuing places were selected.

In the third stage of the sample design, permits are selected monthly. Within sampled places, permits for buildings with five or more units are selected with certainty and permits for buildings with one to four units are subsampled. In the non-permit areas, field representatives 
canvass the areas and all housing unit construction starts are included in the sample with certainty. For further details on the SOC sample design and weighting see: https://www.census.gov/construction/soc/methodology.html. For further details on New Residential Construction definitions see: https://www.census.gov/construction/nrc/definitions.html.

When SOC indicates the construction of a building is complete, the building is selected for the SOMA to collect absorption data. Construction of a multifamily building is classified as complete when at least 50 percent of the units are available for occupancy. Each month the SOMA selects its sample from the SOC records reporting five or more units. If more than 1,200 buildings are completed in a month, a subsample of buildings is selected. In this case, the Census uses systematic random sampling from an ordered list to reduce the sample. The list is ordered by Regional Office, PSU, Place, Measure of Size (Number of Units * SOC Weight), and SOC Schedule Number (which is a control number). Buildings with measures of size (Number of Units * SOC Weight) are self-representing and included with certainty. The subsampling rate is dependent on the total number of buildings completed, but the total number of buildings in each month’s sample can’t exceed 1,200. Historically, the SOMA hasn’t used subsampling since 2005. For more details, refer to the SOMA Source & Accuracy Statement: https://www.census.gov/programs-surveys/soma/technical-documentation/source-accuracy.html.

Information about units absorbed 3, 6, 9, and 12 months after building completion is collected each quarter.

Unbiased quarterly estimates are formed by multiplying the counts for each building by its base weight (the inverse of its probability of selection) and then summing over all buildings. The final estimate is then obtained by multiplying the unbiased estimate by a ratio estimate factor.

    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.

Based on the recent weighted response rates of SOMA, the U.S. Census Bureau expects the weighted response rate to be at least 80 percent. If a respondent is reluctant to participate, the Field Representative (FR) informs the regional office staff who sends a follow-up letter explaining the survey in detail and urging the occupant’s cooperation. The FR or their supervisor then contact the respondent again.


    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.

In 2014, the Census SOMA CAPI instrument was developed and thoroughly tested. Included in the testing were instrument testing, an initial systems test, and a final systems test or verification test. Instrument testing examines different navigation pathways through the instrument, ensuring the questions and response categories appear as intended and that skip patterns are correct. Census Headquarters staff conducted extensive instrument tests. A few local Census Field Representatives (FRs) were invited to Census Headquarters to test the instrument to obtain actual end-users’ opinions. FRs’ feedback was positive and they welcomed the change to an automated instrument. Beyond the functioning of questions, question fills, and skip patterns, the initial and final systems tests systems within the CAPI instrument and examine how the CAPI instrument interacts with other IT systems. Issues were recorded and fixed during the initial systems test and retested during the verification test. We performed systems testing prior to the April 2015 and April 2016 instrument releases. Only minor changes have been made to the instrument since testing concluded.

    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 individuals to contact are:

Shawna Cox
Survey Director, SOMA
Bureau of the Census
Phone: (301) 763-4665

Sydney England
Assistant Survey Director
Bureau of the Census
Phone: (301) 763-2185

KeTrena Phipps
Lead Scientist, SOMA
Demographic Statistical Methods Division
Bureau of the Census
Phone: (301) 763- 5931

List of Attachments

SOMA Items Booklet
USC 1701Z citation
H31L SOMA Letter
SOMA Instrument Screenshots