Aggregating Numeric Data

The Table/Aggregate data menu item opens the following dialog to allow one or more numeric variables to be summarized–aggregated–for each value of a categorical variable. Several different types of aggregates can be computed. The aggregates for each categorical variable value are displayed in a table and can be saved to a file.

The dialog for aggregating numeric variables by values of a categorical variable

This dialog prompts for:

  • Whether to use all data in the data table or just the subset that has been selected (e.g., by clicking on the table or map).

  • What type of aggregate to calculate. Possible aggregates are:

    • The count.

    • The minimum.

    • The maximum.

    • The median.

    • The arithmetic mean.

    • The geometric mean. This will not be calculated if there are any negative values for a category.

    • The harmonic mean. This will not be calculated if there are any negative values for a category.

    • The sum.

  • One or more numeric variables to be summarized. These are selected from the list at the left by clicking on a variable name to select it, and control-clicking or shift-clicking to select additional variables.

  • A single categorical variable that will be used to group the numeric variables into subsets for which the aggregate will be calculated.

After one or more numeric variables have been selected, and the grouping variable selected, a table of aggregated data will be displayed on the right. This table can be saved to a file with the Ctrl-S hotkey.

The “Source Data” button will display a table of all of the selected variables and values without any aggregation.

Histograms of count and arithmetic mean aggregates can be viewed using the general plot types Count by category and Mean by category, respectively.