On its face it seems too good to be true: take a large dataset generated by someone else, search it for something interesting, and write up the results for publication without all the expensive and time-consuming data collection, low response rates, low statistical power, or complicated IRB applications associated with doing it yourself. Yet these are the potential advantages of doing research with large, public databases that were enumerated by Dr. Man Hung, Associate Dean for Research in the Roseman College of Dental Medicine, in a presentation made to the Roseman College of Pharmacy faculty last month. In fact, Dr. Hung suggested that research using public databases can be a good way for faculty to increase their publication rates and prepare more compelling grant applications.
However, anyone who has contemplated engaging in database research can tell you that it comes with its own set of challenges. Publically available datasets can be large and intimidating to download, process, and analyze. The research requires, at a minimum, a good understanding of statistical software, but specialized, or even custom, computer programs may also be needed. Sometimes there is too much data for the average desktop computer to handle. Furthermore, the vendor’s documentation of what data was collected, and how it was collected, can be massive, complicated, and sometimes incomplete.
Nevertheless, Dr. Hung pointed out that the same research methods are required whether you are working with a large, medium-sized, or small dataset. The only difference is scale. This suggests that approaching a smaller database with a more modest research question may produce a learning curve you can manage. Alternatively, you may want to identify an experienced database researcher and offer to assist them in their work as a way to help you learn the ropes.
Of the countless public data sources available, Dr. Hung provided links to the following:
- https://libraryguides.missouri.edu/c.php?g=213300&p=1407295
- https://socialwork.nyu.edu/content/dam/sssw/faculty-staff/ofr/pdf/UsefulSecondaryDatabases.pdf
- https://fhssrsc.byu.edu/ossm/Pages/home.aspx
- https://international.ipums.org/international/
- https://www.icpsr.umich.edu/icpsrweb/ICPSR/
- https://www.data.gov/
Consider checking out these and other public data sources. What kinds of research questions might they help you address?
If you would like to contribute to The Faculty Development Blog, please contact Tyler Rose at trose@roseman.edu.
Author
Tyler Rose, PhD
Associate Professor of Pharmaceutical Sciences
Roseman University of Health Sciences College of Pharmacy