Abstract:
|
The American Community Survey (ACS) is one of the most important sources of information on the economic well-being of the American people. Given the importance of the survey, the US Census Bureau is interested in finding new ways to maximize the usefulness of the survey and the quality of the data while minimizing respondent burden. This research project continues work to use administrative income data from the Internal Revenue Service to examine the data quality of the ACS by focusing on self-employment and business income. We link detailed tax data from the IRS containing information on income derived from sole proprietorships, partnerships and S-Corporations, in addition to information on wage and salary income. We examine how receipt of these types of income in the IRS data align with reported business income on the ACS, focusing on how this alignment varies by class of worker, industry and occupation. We further examine how this alignment interacts with the ACS's data processing methods, and examine whether there are systematic patterns of misalignment which may be exacerbated by editing and imputation rules.
|