How to Cite Data: Numeric Data

The purpose of citations is to enable others to find the same sources you used. Data are like any other source and should be cited in your bibliography and your writing.

Examples of Social Science Numeric Data Citation

Citation example from a Data Librarian (UNC's)

This is my personal preference for a way to cite Census data.  It's particularly important to include the Summary File number for censuses between 1960 and 2000 because some variables show up in multiple files (my personal preference also includes the table number since the point of a citation is to point readers to the specific source of the material).  Likewise, American Community Survey data should cite the product used, 1-, 3- or 5-year.  I've also included information here for citing data accessed through a non-Census database such as Social Explorer.

United States Department of Commerce. Bureau of the Census.  2000 Decennial Census, Summary File 3, Table P1. Total Population.  Social Explorer [distributor], 2013-10-22. 

[Note that Social Explorer also publishes its own tables which should be cited as such rather than simply as Census tables.  Source information {excluding the table number} may be found below every table in Social Explorer.

[Also, I do not believe that one must list a geographic location for every database.  Style guides may disagree, however.]

 

Citation examples from ICPSR

If you're using ICPSR data, you're in luck--ICPSR not only provides citations, its web site offers a download option to export citations directly into bibliographic citation software like RefWorks.

For work based on ICPSR data, consider submitting your publication to the ICPSR Bibliography of Data-Related Literature. It will help other scholars find all the works based on those data. Email bibliography@icpsr.umich.edu to submit citations for inclusion.

Examples:

ABC News, and The Washington Post. ABC News/Washington Post Poll, May 2007 [Computer file]. ICPSR24588-v1. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2009-04-17. doi:10.3886/ICPSR24588

United States Department of Commerce. Bureau of the Census, and United States Department of Labor. Bureau of Labor Statistics. Current Population Survey: Annual Demographic File, 1987 [Computer file]. ICPSR08863-v2. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2009-02-03. doi:10.3886/ICPSR08863 

Johnston, Lloyd D., Jerald G. Bachman, Patrick M. O'Malley, and John E. Schulenberg. Monitoring the Future: A Continuing Study of American Youth (12th-Grade Survey), 2007 [Computer File]. ICPSR22480-v1. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2008-10-29. doi:10.3886/ICPSR22480

Hall, David, Clement Leduka, Michael Bratton, E. Gyimah-Boadi, and Robert Mattes. Afrobarometer Round 3: The Quality of Democracy and Governance in Lesotho, 2005 [Computer file]. ICPSR22203-v1. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2009-05-19. doi:10.3886/ICPSR22203

 

Citation example from the Roper Center Public Opinion Archives

Cable News Network, USA Today. CNN/USA Today/Gallup Poll # 2000-20: 
Microsoft/Parents/'Socially Responsible' [computer file]. 1st Roper Center for Public Opinion Research version. Lincoln, NE: Gallup Organization [producer], 2000. Storrs, CT: The Roper Center, University of Connecticut [distributor], 2001.

More Numeric Data Citation Guides

Here are some additional guides on citing data sets from other institutions and organizations, including links to guides with science examples, as noted.  

Format Suggestion for Data from Advanced Tools

Custom data tabulations from tools like DataFerrett require custom citations.  It is important to list the specific variables utilized as well as the specific data set since multiple options are available within this Census Bureau tool for a single subject.  Likewise since the data sets available through herein are revised from time to time, the date the data were accessed is important.  Note that the Bureau itself is not always the author of the data, e.g., Home Mortgage Disclosure Act is produced by the Federal Financial Institutions Examination Council (FFIEC) and the National Health and Nutrition Examination Survey by the Centers for Disease Control.  Finally, since the tool enables researchers to apply different statistical weights to their queries, that is also important information to cite.  A DataFerrett citation might look something like this:

U.S. Department of Commerce, Bureau of the Census (2013).  American Community Survey 5-Year Estimates - Public Use Microdata Sample, 2008-2012.  Universe: ((SEX in (1,2)) AND (AGEP in (10,11,12,13)) AND (NATIVITY in (2)) AND (HISP in (02)) AND ((ST = 37)); Weight used: PWGTP.  Generated by the author via DataFerrett.  URL: http://dataferrett.census.gov/TheDataWeb/index.html (Files generated April 23, 2014).

Two things to note here:  the codes presented in the Universe field in DataFerrett are shorthand for the Name code of each variable followed by the variable values, e.g., SEX is the Name of the variable for sex and its possible values are 1 (male) and 2 (female).  DataFerrett provides some of this information as a guide to subsetting when one makes a table, but only for those variables for which the researcher did not choose ALL of a variable's values.  If using that "citation" as a shortcut, researchers will need to capture themselves those variable Names (and values) for which they selected all available values.  Second, the date of publication is generally the year following collection, e.g., since the final year of data collection for the 2008-2012 ACS data is 2012, the data were released (read:  published) in 2013.