Boxplot
A boxplot, or box and whisker diagram, is a way to show the spread and centers of a data set. Measures of spread include the interquartile range and the mean of the data set. Measures of center include the mean (sometimes called the average) and median (the middle of a data set). When you look at a boxplot, it’s much easier to see how your data is centered or spread out, rather than looking at a list of data.
Box and whiskers graph, or boxplot.
 |
| Box Plot |
The boxplot shows the five number summary: the minimum, first quartile (a line that separates the first and second quarters of the data set), median, third quartile (a line that separates the third and fourth quarters of the data set), and the maximum of your data set. The central rectangle in the diagram starts at the first quartile and ends at the third quartile of your data. This area is known as the interquartile range or IQR (you can think of it as the “middle half” of the data) and gives you an idea of where the bulk of your data is — it’s a way to show the likely range of variation. A segment or line inside the rectangle shows the median for your data (the median can also be thought of as a typical value for the data set) and the “whiskers” at either end of the box show where the minimum and maximum values are.
Data sets can sometimes contain outliers that are suspected to be anomalies (perhaps because of data collection errors or just plain old flukes). If outliers are present, the whisker on the appropriate side is drawn to 1.5*IQR rather than the data minimum or the data maximum. Small circles or unfilled dots are drawn on the chart to indicate where suspected outliers lie. Filled circles are used for known outliers.
