Part B

B. Collection of Information Employing Statistical Methods

1. Universe, Respondent Selection, and Response Rates

Data are collected monthly from a sample of manufactured homes shipped to dealers. About 4.0 percent of the roughly 6,800 homes manufactured each month are randomly selected for the survey. A list of all manufactured homes is provided by manufacturers to the Institute of Building Technology and Safety (IBTS). The list identifies the home and shows the name, city, and state of the dealership that ordered it. Under contract, the Census Bureau obtains copies of these lists from IBTS on a monthly basis. The Form C-MH-9A imprinted with a letter signed by the Director of the Census Bureau, (see Attachment 2) explaining the survey and identifying the home, is mailed to the manufactured home dealer shown as the receiver of the sampled home.

The dealer is asked to have the answers to the questions available when the interviewer telephones for the information. The current response rate is approximately 85 percent.

2. Statistical Methodology - Estimation Procedures

Each sampled home is weighted by its probability of selection. The average relative standard error of monthly 2008 estimates of placements is 6 percent for the United States and approximately 16 percent at the regional level.

3. Methods to Maximize Response

Telephone follow-ups are used to reduce nonresponse.

4. Testing of Procedures

There are no tests of procedures or methods currently planned.

5. Contacts

The Manufacturing and Construction Division staff plans and coordinates the survey. This includes the design of the reporting form, sample design and selection, collection, tabulation, analysis, and publication.

The contact person for questions relating to the statistical aspects of the survey is Ms. Amy Newman-Smith. She can be reached on 301-763-6595. The contact person for questions relating to the collection and analysis of the data is Mr. Michael Davis. He can be reached on 301-763-4590.