FR3059_SSB_20090320_omb

Supporting Statement B

2010 Survey of Consumer Finances

(FR 3059; OMB No. 7100‑0295)

Attachment 2

Overview of Statistical Methods

Statistical Methods

For the business pretest, the survey research organization (contractor) would interview up to 30 households that have ownership of a small business. These interviews would be done in several waves, to allow for optimization of the questions, based on the pretest experience. For the main pretest, the contractor would interview no more than 150 households based on samples they would select. After each of the pretests, the contractor would forward the data collected to the Federal Reserve and would conduct a formal debriefing of interviewers and others involved in the administration of the surveys. In response to issues that emerge, the contractor would revise procedures for the main survey in consultation with the Federal Reserve.

For the main survey, the contractor and the Federal Reserve would draw samples for the survey designed to obtain at most 7,000 completed interviews. The sample selected by the contractor would be an area-probability design, a type of geographically structured random sample that provides good national coverage of widely-distributed behavior. The sample selected by the Federal Reserve would be drawn from statistical records derived from individual tax returns; this sample would be designed to oversample wealthy families. Both samples would be selected in a way that is consistent with procedures used in earlier SCFs. Interviewing for the survey is scheduled to take place between May 2010 and March 2011, with interviews averaging approximately 75 minutes.

The survey questionnaire is designed to collect information consistent with that collected in the earlier SCFs. This instrument would provide a comprehensive view of the finances of U.S. households.

The contractor would select, train, and supervise interviewers during the execution of the survey in areas selected throughout the continental United States. Over the course of the field-period, the contractor would regularly transmit the information collected by interviewers to the Federal Reserve. At the end of the field-period, the contractor would provide the Federal Reserve with the final data along with coded equivalents of verbatim respondent answers.

The re-interview surveys would each be based on samples of no more than 150 participants in the main survey in 2010. These samples would be selected by the contractor to represent proportionately the types of households included in the 2010 survey. The contractor would hire and train interviewers to conduct surveys with these households. The data would be transmitted to the Federal Reserve for analysis to determine the feasibility of a larger such process as a part of the 2013 SCF.