Box Plots

Wednesday, January 16, 2013

Box Plots are an important tool for visualizing the center, spread, and shape of a distribution of data.

In Stats Pad select Box Plot from the graphs tab of the menu.

Enter titles if desired.

For this example we are grouping by column, which means each column will be treated as a separate sample and get its own box on the plot.

Select the raw data (not including labels) and tap the data button.

Using labels is optional. To use labels ensure there is one label for each sample of data. Select the labels and tap the labels button.

box plot 1.001

Tapping the “Create” button will generate the box plot.

box plot 2.002

Box plots will have the following components:

A line indicating the median of the data.

A box with the lower end indicating the 25th percentile and the upper end indicating the 75th percentile. The length of this box the “Interquartile range.”

An upper whisker indicating the maximum data point that is still less than the 75th percentile plus 1.5 times the inter-quartile range.

A lower whisker indicating the minimum data point that is still higher than the 25th percentile minus 1.5 times the inter-quartile range.

Asterisks indicating data that falls outside the upper and lower whisker limits. Asterisk data is generally considered “outlier” data and for one reason or another doesn’t fall within the distribution.