Stem-and-Leaf Plot
A text-based chart that preserves every data value while revealing the shape of a distribution — part histogram, part data table.
// 01 — The chart
What it looks like
A stem-and-leaf plot of 30 test scores. The stems are tens digits; leaves are units digits. The highlighted row (70s) shows where the data concentrates.
// 02 — Definition
What is a stem-and-leaf plot?
A stem-and-leaf plot (also called a stemplot) is a simple way to organize numerical data while preserving every individual value. Each number is split into a stem (one or more leading digits) and a leaf (the trailing digit). All leaves sharing the same stem are listed in a row, creating a sideways histogram made of actual digits.
Invented by statistician John Tukey in 1977 as part of his “Exploratory Data Analysis” framework, the stem-and-leaf plot bridges the gap between a frequency distribution table and a histogram. Unlike a histogram, you can read back every original value from the display.
It’s particularly loved in education because it requires nothing more than pencil and paper to construct, yet it reveals distribution shape, central tendency, and outliers at a glance.
Fun fact: Tukey called his approach “detective work” — stem-and-leaf plots were designed as a fast, pencil-friendly tool for exploring data before computers made histograms trivial to generate.
// 03 — Anatomy
Parts of a stem-and-leaf plot
// 04 — Usage
When to use it — and when not to
- You have a small dataset (under ~50 values) and want to see every number
- You want to quickly assess distribution shape without software
- Teaching students about distributions — the hands-on construction builds intuition
- You need to compare two small datasets side by side (back-to-back stemplot)
- Your audience values seeing exact values rather than binned summaries
- Quick exploratory analysis on paper or whiteboard
- Your dataset has more than ~50 data points — it becomes unwieldy
- Data values have many decimal places — leaves get messy
- You need a polished, presentation-ready chart — histograms look cleaner
- Your data spans a very wide range — too many stems with empty rows
- You need to compare more than two groups — use box plots or violins
- Your audience isn’t familiar with the format — a histogram is more intuitive
// 05 — Reading guide
How to read a stem-and-leaf plot
Reading a stemplot is straightforward once you understand the stem|leaf convention.
Identify the key
Look for a legend explaining what the stem and leaf represent. For example, '5|3 = 53' tells you the stem is the tens digit and the leaf is the units digit.
Read individual values
Combine each stem with its leaf to reconstruct original values. Stem 7, leaf 4 = 74. Each leaf is one data point.
Look at row lengths
Longer rows mean more data in that range — just like taller bars in a histogram. The longest row shows where data concentrates.
Spot the shape
Tilt your head left: do the leaf rows form a bell shape, a skewed tail, or multiple peaks? This reveals distribution shape at a glance.
Find outliers and gaps
Stems with no leaves or very few leaves indicate gaps. A single leaf far from the bulk signals a potential outlier.
// 06 — Data format
What your data should look like
A stem-and-leaf plot needs a single column of numeric values — ideally integers or values rounded to one decimal.
| score |
|---|
| 42 |
| 45 |
| 48 |
| 51 |
| 53 |
| 60 |
| 62 |
| 73 |
| 78 |
| 85 |
Code sketch — Python
# Python has no built-in stemplot, but stemgraphic works: import stemgraphic stemgraphic.stem_graphic(df["score"])
// 07 — Construction
How to build one, step by step
Sort your data from smallest to largest.
Decide on a stem unit — typically the leading digit(s). For two-digit numbers, the tens digit is the stem.
Write each unique stem value vertically in ascending order, followed by a divider line.
For each data value, write its leaf (trailing digit) next to the corresponding stem, in order.
Add a key: '5|3 = 53' so readers know how to reconstruct values.
Optionally, add a count column on the left side for each row.
// 08 — Common mistakes
Mistakes to avoid
Forgetting the key
Always include a legend like '3|5 = 35' so readers know how to reconstruct values from stems and leaves.
Unsorted leaves
Leaves within each row must be in ascending order. Unsorted leaves make it impossible to find the median or quartiles quickly.
Wrong stem granularity
If most data falls in one or two stems, split stems (e.g., 3* for 30-34, 3. for 35-39) for better resolution.
Using it for large datasets
Beyond ~50 values, a stemplot gets unwieldy. Switch to a histogram or density plot for larger samples.
// 09 — In the wild
Real-world examples
Education
Teachers use back-to-back stemplots to compare two class sections’ test score distributions on a whiteboard in seconds.
Sports analytics
A coach displays player sprint times as a stemplot to quickly find the median, spot outliers, and compare before/after training.
Quality control
A factory floor operator logs 40 measurements as a quick stemplot to check if product dimensions cluster around the target.
// 10 — At a glance
Quick reference
Category
Distribution
Data type
Continuous / discrete
Best for
n < 50
Tools needed
Pencil & paper
Difficulty
Beginner
Invented
1977 (Tukey)
// 11 — Accessibility
Accessibility notes
Since a stemplot is text-based, it is inherently more accessible than graphical charts
Use a monospaced font so leaves align vertically — this preserves the visual histogram shape
Provide a structured data table as a companion for screen readers
Add a text summary noting the distribution shape, center, and spread
Ensure sufficient font size and contrast — stems and leaves should be clearly distinguishable
// 12 — Variations
Variations
Back-to-back stemplot
Two datasets share the same stems, with leaves extending left and right — ideal for comparing two groups.
Split stems
Each stem is split into two rows (e.g., 3* for 30–34, 3. for 35–39) to increase resolution when data clusters in a few stems.
Truncated leaves
For values with many digits, round or truncate to show only the most significant leaf digit.
Decimal stems
For data between 0 and 10, use the integer part as stem and the first decimal as the leaf (e.g., 2.7 → stem 2, leaf 7).
// 13 — FAQs
Frequently asked questions
What is a stem-and-leaf plot?+
A stem-and-leaf plot (also called a stemplot) is a simple way to organize numerical data while preserving every individual value. Each number is split into a stem (one or more leading digits) and a leaf (the trailing digit). All leaves sharing the same stem are listed in a row, creating a sideways histogram made of actual digits.
When should you use a stem-and-leaf plot?+
Use a stem-and-leaf plot when you have a small dataset (under ~50 values) and want to see every number. It also works well when you want to quickly assess distribution shape without software, and when teaching students about distributions — the hands-on construction builds intuition.
When should you avoid a stem-and-leaf plot?+
Avoid a stem-and-leaf plot when your dataset has more than ~50 data points — it becomes unwieldy. It is also a poor fit when data values have many decimal places — leaves get messy, or when you need a polished, presentation-ready chart — histograms look cleaner.
What data do you need to make a stem-and-leaf plot?+
A stem-and-leaf plot needs a single column of numeric values — ideally integers or values rounded to one decimal.
What size of dataset works best for a stem-and-leaf plot?+
Stem-and-Leaf Plot works best for n < 50. Outside that range the chart either looks empty or becomes too cluttered to read clearly.
Are stem-and-leaf plots accessible to screen readers?+
Yes — a stem-and-leaf plot can be made accessible to screen readers by pairing it with a clear text summary of the key insight, ensuring color choices meet WCAG contrast guidelines, adding descriptive alt text or aria-label to the SVG, and offering the underlying data as an HTML table fallback for assistive technologies.