The County Business Patterns data published by the US Census Bureau track employment by county and industry from 1946 to the present. Two features of the data limit their usefulness to researchers: (1) employment for the majority of county-industry cells is suppressed to protect confidentiality, and (2) industry classifications change over time. We address both issues. First, we develop a linear programming method that exploits the large set of adding-up constraints implicit in the hierarchical arrangement of the data to impute missing employment. Second, we provide concordances to map all data to a consistent set of industry codes. Finally, we construct a user-friendly, 1975 to 2018 county-level panel that classifies industries according to a consistent set of 2012 NAICS codes in all years.
We may periodically update the imputed data. If your enter an email address below we will notify you of such changes.
Full County×Industry Panel 1975-2018:
Panel with Native Industry Codes
Panel with Harmonized 2012 NAICS Industry Codes
Important: NB: Census changed the way the CBP data are reported starting in 2017. For these years, Census now perturbs cells with small employment counts, making these data fundamentally different from earlier periods. We do not impute data in those years since there are no missing cells in the data. We nevertheless appended 2017 and 2018 to the panel for completeness. Note that the 2017 and 2018 data are reported on a NAICS2017 basis.
Raw and Imputed CBP Files:
1980 1981 1982 1983 1984 1985 1986 1987 1988 1989
1990 1991 1992 1993 1994 1995 1996 1997 1998 1999
2000 2001 2002 2003 2004 2005 2006 2007 2008 2009
2010 2011 2012 2013 2014 2015 2016
Cleaning and Imputation Codes:
Find all codes needed to replicate the imputation on our public Github Repo.
If you use the data or code posted on this website please cite:
Fabian Eckert, Teresa C. Fort, Peter K. Schott, and Natalie J. Yang. "Imputing Missing Values in the US Census Bureau's County Business Patterns." NBER Working Paper #26632, 2021