DataTerminology.comNEW
Also known as: Box-and-Whisker Plot
Statistical chart showing a variable’s median, quartiles, range, and outliers using a box with whiskers.
DESCRIPTION
A box plot summarizes distribution using the five-number summary: minimum, Q1, median, Q3, and maximum. The box spans the interquartile range, and whiskers extend to non-outlier extremes. Points beyond whiskers are flagged as outliers using rules like 1.5×IQR. Notches can show median confidence. Box plots facilitate comparison across categories. They are compact and robust to outliers, but hide multimodality. Violin plots augment box plots with kernel density for shape visualization.
ALTERNATIVE DEFINITIONS
NIST/ITL
A box plot is a graphical summary of a data set that displays the median, quartiles, and extremes.
Focuses on five-number summary and extremes.
Encyclopaedia Britannica
Box-and-whisker plot, a method for displaying the distribution of data based on a five-number summary: minimum, first quartile, median, third quartile, and maximum.
Enumerates the five-number summary explicitly.
Tableau
A box plot displays the distribution of values within a dataset using quartiles and whiskers to show variability and potential outliers.
Highlights variability and outlier identification in BI tooling.
RELATED TERMS
Median Quartile Interquartile Range Outliers Five-Number Summary Descriptive Statistics Notched Box Plot Whiskers
COMPETING TERMS
KNOWLEDGE AREAS
Data Visualization Data Science Mathematics
TARGET AUDIENCE
BI Specialist Data Analyst Data Scientist Analytics Engineer
EXTERNAL SOURCES
- Wikipedia - Box plot
- NIST/ITL - Definition and usage in NIST handbook
- Matplotlib - Python plotting function reference
- ggplot2 - R boxplot geometry documentation
TOP QUESTIONS
When should Box Plot be used?
Use box plots to compare distributions across categories, quickly spotting medians, spread, and outliers without assuming a specific distribution.
Category: Requirements
What is a common misunderstanding about Box Plot?
Many think whiskers always show min and max, but default rules often set whiskers to 1.5×IQR beyond quartiles.
Category: Misunderstanding
How does Box Plot compare to Violin Plot?
Box plots summarize with quantiles, while violin plots add density shape; violin plots reveal multimodality hidden by box plots.
Category: Opinion
What risks exist using Box Plots?
Overplotting too many categories can hinder readability; hidden multimodality may mislead without complementary charts.
Category: Risk
What is a competing term for Box Plot?
Violin plot is a common alternative, showing both summary and density.
Category: Alternatives
How to interpret outliers in a Box Plot?
Points beyond whiskers indicate potential outliers; investigate causes and domain relevance rather than removing blindly.
Category: Example
Can Box Plots show mean values?
Yes, but the default emphasizes medians; some tools allow overlaying means for additional context.
Category: Opinion
Should Box Plots be used with small samples?
They’re informative but quantile estimates become unstable; consider jittered points or violin plots alongside.
Category: Requirements
Where to start learning Box Plots?
Review NIST’s definition and practice with Matplotlib or ggplot2 documentation using sample datasets.
Category: Overview