Data Set

A data set is data that is in a data analysis program (e.g., Q, R, SPSS, or Displayr), which can be queried by variable.

In some programs the data sets are databases. In some programs, the data sets are data files. In some programs, the data sets exist in memory. Many programs support multiple types of data sets. From the perspective of the user, this distinction is usually inconsequential.

Often analysis requires multiple data sets. For example, one data set may represent the characteristics of individual transactions, and a separate data set may represent the characteristics of people that made those transactions (where one person may have made multiple transactions – these are called hierarchical data sets). Some software packages can only work with a single data set at a time, whereas others can integrate more than one into the analysis.