B. Collection of Information Employing Statistical Methods
1. Universe and Respondent Selection
AHS-N
The 2009 AHS-N sample will consist of about 60,966 sample units. The sample is comprised of three components.
52,800 returning sample units selected primarily from the 1980 census sample files by variables, such as owner-occupied housing units, renter occupied housing units, vacant units for rent, and mobile homes.
2,200 new construction units selected from permits issued since the most recent decennial census. Starting with the 2005 AHS-N, the updates are from new construction units selected from permits issued since Census 2000. New construction selection is based on the same criteria detailed for the core sample. The Census Bureau designed the sample to provide 0.4, 0.7, 3.0, and 3.0 percent standard error on estimates of the above variables, respectively.
5,966 large metro area supplemental sample units. As mentioned earlier, the National Sample was supplemented with large metro area cases every four years through the 2003 AHS-N. For this data collection, the Census Bureau selected units from 5 of the 6 areas that comprise the supplementary sample (New York, Northern New Jersey, Philadelphia, Detroit, and Chicago) leaving out Los Angeles. The Census Bureau selected a new supplementary sample after the 2003 AHS-N survey so all work will be incoming units new to sample. As indicated, the Census Bureau will produce a separate set of data reports for each of the five areas but not micro-data PUFs.
AHS-MS
The 2009 AHS-MS sample will consist of approximately 2,500 sample addresses. The Census Bureau selected the sample from the 1990 decennial census addresses. The Census Bureau will update the sample to include new construction units built since the last survey year. As mentioned earlier, the Census Bureau continues taking steps to insure the sample remains representative of the current housing market. This includes (1) adding about 25 special living units, and (2) replacing about 30 returning manufactured/ mobile homes with units selected from the Census 2000. Special living units are complexes with five or more units where services are offered to the self-sufficient residents.
Based On The 1990 Census Of Population And Housing
MS AREA |
TOTAL HOUSING UNITS IN MS AREA* |
ESTIMATED HOUSING UNITS IN SAMPLE |
APPROXIMATE RESPONSE RATE LAST ENUMERATION (PERCENT) |
Seattle, WA
|
857,000 |
2,500 |
88 |
2. Procedures for Collecting Information
The sample for the Seattle metropolitan area represents the households included in the area as it was defined in 2003.
3. Methods to Maximize Response
The Census Bureau expects the response rate to be between 87 and 90 percent on the AHS-N and the AHS-MS. If an occupant is reluctant to participate, the FR informs the regional office staff, who sends a follow-up letter explaining the survey in greater detail and urging the occupant's cooperation. A Census Bureau FR or supervisory FR will contact the occupant again.
4. Testing Procedures
The Census Bureau conducted a test of the interview forms and procedures in September 1983 and again in 1994 and 1995. Based on the results of the tests, the HUD made modifications and changes in preparation for the 1984 through 2006 AHS-MS and the 1985 through 2007 AHS-N.
In preparation for the change to computer-assisted personal interviewing beginning with the 1997 survey, the HUD and the Census Bureau staff reviewed the current survey questions and decided to test different versions of questions for rooms, heating equipment, and housing quality items to improve the quality of this information. We made changes to all these areas as a result of this research.
The HUD and the Census Bureau conducted a major review of the survey questions in the summer of 2004 to review the data user suggestions received and identify areas where updates should be made to stay current with new housing conditions. The Center for Survey Methods Research (CSMR) at the Census Bureau tested different versions of questions for neighborhood quality, income, utility costs, and renter subsidies to improve the quality of this information. We made changes to all of these areas as a result of their research. In October 2005, we tested these changes in a live hot house test held in Pittsburgh, Pennsylvania.
5. Contacts for Statistical Aspects and Data Collection
The HUD consulted the following individuals on the statistical data collection and analysis operation:
Dennis Schwanz
Demographic Statistical Methods Division
U.S. Census Bureau
301-763-1984
Statistical Design
Tamara Cole
Housing and Household Economic Statistics Division
U.S. Census Bureau
301-763-4665
Analysis
La Terri Bynum
Demographic Surveys Division
U.S. Census Bureau
301-763-3858
Collection
Attachment
| File Type | application/msword |
| File Modified | 0000-00-00 |
| File Created | 0000-00-00 |