Data refer to observations gathered according to a research methodology (e.g. experiment, simulation, observational study, etc.). Data can generally be categorized as either quantitative (numerical) or qualitative (non-numerical; e.g. text, images, sound, etc.) Qualitative data can sometimes be coded to create quantitative data.
Statistics refer to summaries and/or interpretations of a set of observations (i.e. data). Statistics are calculated from quantitative, or numeric, data.
The Meteorite Landings data set (provided by The Meteoritical Society; hosted by NASA’s Open Data Portal) documents about 46,000 unique meteorite landings. For each meteorite landing, the data set records things like:
In its raw form, the data set isn’t very useful. Human beings can’t glean much meaning by reading through 46,000 meteorite landing entries – we simply do not learn in that way. However, certain transformations can be applied to the data to make it more meaningful. For example, if we count the number of meteorites that were found on the ground (found), as well as the number of meteorites seen falling (fell), we can better characterize the data.
1,107 meteorites were seen falling; 44,600 meteorites were found on the ground. If we compare each number to the full count of records, we learn that 98% of meteorites were found on the ground and 2% were seen falling. These four numbers are statistics, and are represented by the pie chart.
Dr. Martin Luther King, Jr. Library
One Washington Square | San José, CA 95192-0028 | 408-808-2000