Box & Whisker and Box-Percentile Plots

The box & whisker graphs display rank statistics. They can have the form of a box or notched box that spans the distance between the two quartiles surrounding the median. Aabel provides different options for displaying the whiskers and/or outliers.

The options for plotting the whisker and outliers include:

Whiskers extended to extreme data points Q1 - 1.5 * IQR, Q3 + 1.5 * IQR Q1 - 1.5 * IQR, Q3 + 1.5 * IQR (and outliers)

10th percentile, 90th percentile 10th percentile, 90th percentile (and outliers) 5th percentile, 95th percentile 5th percentile, 95th percentile (and outliers)

A box-percentile plot gives the same graphical information as a box plot, but also uses width to encode information about the shape of the distributions.

A two-way box & whisker or box-percentile plot allows comparing rank statistics of response data (scores, measurements) obtained from pq levels of two experimental factors (i.e.,k=pq samples/groups).

Using a Worksheet Layout With Two-Grouping Variables

• Here, levels of two grouping variables split the response values from a single numeric column.
• You can choose which components of the split should represent the legend entries and which should represent the X-axis labels; in the example below, the legend entries represent levels of the 2^nd grouping variable, the X-axis labels represent levels of the 1^st grouping variable.
A Two-Way Box & Whisker Graph Comparing Rank Statistics of Response Data From pq=8 Groups

Using a Worksheet Layout With One-Grouping Variable

• Here, levels of a grouping variable split the response values from multiple numeric columns.
• You can choose which components of the split should represent the legend entries and which should represent the X-axis labels; in the example below, the legend entries represent levels of the grouping variable, the X-axis labels represent the response variables.

The one-way plots are designed for a worksheet layout in which scores from different samples/groups are stored in separate numeric columns.