Definition
A box plot shows a distribution with five numbers: the box spans from the lower to the upper quartile (the middle 50 % of values), the line inside is the median and the "whiskers" show the range of usual values; points beyond them are outliers. At a glance you compare location, spread, skewness and extremes of several groups side by side.
Data & visualisation
It is the most economical way to compare groups before a test: do the boxes overlap? do the medians differ? do the groups have similar spread? Unlike a bar chart of means with error bars it does not hide skewness and outliers.
Variants: mean ± standard error boxes (common in engineering), notched boxes with an interval for the median, or a violin plot adding the distribution shape. State what the box and whiskers mean — conventions differ.
In Statistica
Box plots are created in Graphs → 2D Graphs → Box Plots (by groups, for several variables, with median/quartiles or mean/SD/SE options) or directly from the results dialogs of the t-test, ANOVA and nonparametric tests. Graphs are fully interactive — points can be labelled, recoloured and traced back to the data.
Related terms
- HistogramA histogram shows the distribution of a continuous variable: values are divided into intervals (bins) and the height of…
- OutliersAn outlier is an observation that differs conspicuously from the rest — a measurement or entry error, a different population, or a genuine rare event.
- Mean, median and modeThe mean, median and mode are measures of central tendency — a single number summarizing where the data lie.
- Nonparametric testsNonparametric tests do not assume a normal distribution — they work with the ranks of values rather than the values themselves.
Knowledgebase guides
FAQ
- How long are the whiskers?
- Most often up to 1.5 times the interquartile range from the box; values beyond are drawn as outliers. Statistica also offers min–max or percentile whiskers.
- When a box plot instead of a histogram?
- When comparing several groups — side-by-side histograms are harder to read. For the shape of a single distribution a histogram is better.
Try it on your own data
Statistica free for 30 days
Full version, no credit card. Or get a pricing estimate in a minute.