Data for Research

The government data landscape has been shaken recently by the new presidential administration. As a result, many government websites containing public government datasets have periodically gone offline and some have returned with banners indicating that they've been edited. To keep up to date with the various executive orders affecting government websites and data you can check them out on the Federal Register. Below is a list of resources to help locate data or websites that may be down or have recently changed:

To select the correct data, you first need a solid research question.  Not all questions can be answered by all data sets. If you are still working on developing your research question it may be helpful to review this page of our Evidence-Based Medicine guide or to meet with a librarian to discuss your question in more depth.

Once you have clarified your research question, it is highly recommended that you search the literature on your topic.  This will give you an idea of what similar work has been done, and what data was used in those papers.  Searching the literature for studies similar to yours is another area where meeting with a librarian can be helpful.

Researchers may prefer to use pre-existing datasets or databases to analyze and use for their research projects. 

The Excel book below contains lists of both publicly available datasets, available-through-request datasets, and repositories. Please read the notes carefully before browsing the lists. If there is a dataset or repository you feel should be added, or if a link no long works, please contact the Research Services Librarian, Jordan, at jcorreia2@nymc.edu.

Those affiliated with NYMC may request use of the National Inpatient Sample dataset.

Google also has a search engine for finding datasets that may be useful for finding a topic appropriate dataset. 

When collecting your own research data, it is important to take the time beforehand to plan out your data collection workflows, naming conventions, and data variables carefully. The video below by NYU Health Sciences Library's Karen Hanson, Kevin Read, and Aliza Surkis covers some common data collection pitfalls and things to think through when designing a data collection instrument.