What Is Data and What Are Datasets?
data: factual information (such as measurements or statistics) used as a basis for reasoning, discussion, or calculation
At the most basic level, a dataset is a collection of data, usually a table of rows and columns of different variables. Sometimes the term "dataset" can refer to not only raw data, but to metadata about that data and other items necessary to understand or use that data.
Finding Data and Datasets
Before you begin searching around data repositories for raw data or datasets, you should spend some time thinking about what kind of data you need or are looking for, and who is most likely to have gathered that data. Is it likely to have been gathered by a government agency? Federal, state or local? What about academic researchers?
Once you've thought of the type of data you want to find, or discovered a citation to a specific dataset, it's time to start looking. Google can be very helpful in locating discipline-specific data repositories or open data sources. Is the data from a proprietary database? Does the library already subscribe to it, or is it something we can look into subscribing to? Can you request a copy from the researcher, or ask a researcher where she obtained the data?
When in doubt, ask any of the friendly STEM librarians!