What is Box Plot?
A box plot (box-and-whisker plot) is a compact chart that shows the distribution of a numerical dataset using five summary values: minimum, first quartile, median, third quartile and maximum, with outliers highlighted. It’s used to compare spread and central tendency across groups at a glance.
A box plot visualises how a set of numbers is distributed. The central box spans from the first quartile (Q1) to the third quartile (Q3); a line inside the box marks the median (Q2). ‘Whiskers’ extend from the box to show the typical range of the data (commonly to the furthest point within 1.5 × interquartile range), and data points beyond the whiskers are plotted individually as outliers. From a box plot you can quickly see the dataset’s center, spread, skew, and any unusually high or low values. Box plots can be drawn for multiple groups side‑by‑side to compare distributions.
Usage example
A local council compares satisfaction scores from different neighbourhoods: each neighbourhood’s scores are shown as a box plot so the engagement officer can quickly see which areas have lower medians, wider variation, or many outliers.
Practical application
Box plots matter because they turn many numbers into a simple visual summary. For people running multilingual surveys, box plots let you: - Compare response distributions across language groups (e.g., satisfaction ratings in English vs. Somali). - Spot differences in variability that might indicate translation or comprehension issues. - Identify extreme responses that merit manual review. They’re especially useful when you want insight into patterns and differences without inspecting every individual response.
FAQ
What does the length of the box tell me?
The box length equals the interquartile range (IQR = Q3 − Q1) and shows the middle 50% of responses. A longer box means greater variability among typical responses; a very short box means most answers are similar.
What are whiskers and outliers?
Whiskers usually extend to the most extreme data points within 1.5 × IQR of the quartiles. Points beyond that threshold are shown as individual outliers, drawing attention to unusually high or low values that may be real extremes or data errors.
Does a box plot show the mean?
Not by default — box plots emphasise medians and quartiles. Some implementations add a separate marker for the mean, but the key summary is the median and the spread of the middle 50%.
Can I use box plots with small sample sizes?
You can, but interpret them cautiously. With very few data points the quartile estimates are unstable and outlier rules may be misleading. For small samples, complement box plots with raw data points or other charts.