Survey of Consumer Finances - Extract File 1989-2019


ABSTRACT

The regular Survey of Consumer Finances (SCF) cross-sectional surveys are conducted every three years to provide detailed information on the finances of U.S. families. No other study for the country collects comparable information. Data from the SCF are widely used, from analysis at the Federal Reserve and other branches of government to scholarly work at the major economic research centers.

The study is sponsored by the Federal Reserve Board in cooperation with the Department of the Treasury. Since 1992, data have been collected by the NORC at the University of Chicago.

To ensure the representativeness of the study, respondents are selected randomly using procedures described in the technical working papers on the Federal Reserve Web site. A strong attempt is made to select families from all economic strata.

The SDA online dataset is the Summary Extract Data -- that is, the extract data set of summary variables used in the Federal Reserve Bulletin. It includes data from the triennial surveys beginning in 1989.

Users should be aware that the dataset appears to have five times the number of cases as it should have. This dataset uses multiple imputation to supply estimates for any missing data point. Since there are five imputed values for each missing value, there are in effect five datasets, which have been combined into the current dataset. Therefore users should not attempt to calculate standard errors or confidence intervals for the point estimates produced by the SDA analysis programs. Although the (weighted) point estimates are accurate, the calculation of the complex standard errors and confidence intervals would require access to additional variables that are not included in the present dataset and would also require calculation algorithms that are not currently available in SDA.

A weight variable (WGT) is provided for the analysis of the data. The sum of the weights for each year is the number of households in the U.S. for that year. However, if you run an analysis that includes all eight years in the dataset, the sum of the weights is eight times the average number of households in those years. Nevertheless, statistics like means and percentages will not be affected by those artificially inflated weighted N's.

NOTE: All values in the Extract SDA dataset are in 2019 dollars.

For more information on the Survey of Consumer Finances, see the SCF documentation on the Web site of the Federal Reserve System.

For answers to some frequently asked questions about the use of the SDA dataset, see the FAQ file.