HVS 08 Supporting Statement Part B

2

SUPPORTING STATEMENT

U.S. Department of Commerce

U.S. Census Bureau

Housing Vacancy Survey

OMB Control No. 0607-0179

B. Collection of Information Employing Statistical Methods

1. Universe and Respondent Selection

We conduct the HVS in conjunction with the CPS for which the universe is

128,000,000 housing units. We select a sample of approximately 72,000 housing units from this universe each month. We interview a unit for the HVS if it is vacant and intended for year-round occupancy, as determined during the CPS interview. Approximately 6,936 units in the CPS sample meet these criteria each month; these units represent about 13 million year-round vacant units (in 2007) across the United States each month. Based on past experience, we expect a response rate of approximately 96.7 percent.

2. Procedures for Collecting Information

Attachment G gives an overview of the CPS sample design and weighting methodology. The HVS weighting procedure is similar to that used by the CPS. The basic weight is the reciprocal of the probability of selection of the unit in the CPS sample. First- and second-stage adjustments similar to those described in

Attachment G for the CPS are made to the HVS basic weight. The first-stage adjustment is made to bring the sample estimates into agreement with distributions for vacant units at the state levels as measured in the 2000 decennial census. The second-stage adjustment inflates the weight to account for undercoverage in the CPS sample.

Historically, the coefficient of variation for vacant rental units was approximately

1.5 and 4 percent annually at the national and regional levels respectively. We deem this degree of accuracy sufficient for data analysis and publication purposes.

3. Methods to Maximize Response

We maintain response rates and data accuracy for the CPS at high levels through interviewer instruction and training and close monitoring of data output. (Refer to paragraph 5 of Attachment G for a discussion of the CPS nonresponse.) Allocation for item nonresponse is done within the HVS eligible households (item nonresponse rarely exceeds 3.3 percent).

4. Tests of Procedures or Methods

Tests of procedures and methods are not required since we have conducted the HVS for 49 years.

5. Contacts for Statistical Aspects and Data Collection

The following individuals were consulted on the statistical data collection and analysis operations:

Statistical Design

Patrick Flanagan

Demographic Statistical Methods Division

U.S. Census Bureau

(301) 763-4290

Analysis

Howard Savage

Housing and Household Economic

Statistics Division

U.S. Census Bureau

(301) 763-5665

Collection

Gregory Weyland

Demographic Surveys Division

U.S. Census Bureau

(301) 763-3806

List of Attachments

A - Tenure Question on the CPS Instrument

B - HVS Items on the CPS Instrument

C - Census Bureau Reports on Residential Vacancies and Home Ownership

D - CPS-263, Respondent Letter

E - Fact Sheet for the Housing Vacancy Survey

F - Confidentiality Brochure

G - Overview of CPS Sample Design and Methodology