A boxplot is a graphical summary of the distribution of a sample that shows its shape, central tendency, and variability.

Parts of a boxplot

  • A: outlier (*): observation that is beyond the upper or lower whisker
  • B: upper whisker: represents the upper 25% of the distribution (excluding outliers)
  • C: interquartile range box: middle 50% of the data
  • D: lower whisker represents the lower 25% of the distribution (excluding outliers)

Boxplots can help you understand your distribution. For example, the previous boxplot could represent hold times for customer support calls. The outlier at the upper end and longer upper whisker indicate positive skewness, which is logical because at the lower end of the distribution, no hold times can be less than zero.

Boxplots are also useful for comparing several distributions. For example, a quality engineer compares the diameter of plastic pipes produced over three weeks. The following boxplot represents the results.

The medians for the three weeks are similar. However, the boxplots show a tendency for some higher pipe diameters over time.

By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy