8E- stem and leaf plot

A stem-and-leaf plot is an easy and visual way to sort and display numbers. It looks a lot like a sideways bar graph, but it has one big superpower: it keeps every single original number in place, so no data is ever lost. Each number is broken into two parts: a stem and a leaf.

Core Components
  • Stem: Represents the front digit or digits (such as the tens or hundreds place). Stems are listed in a vertical column from smallest to largest, going down.

  • Leaf: Represents the very last digit of the number (the units or ones place). Each leaf must always be a single digit from 00 to 99. Leaves are written in rows to the right of their stem in order from least to greatest, spaced out evenly.

  • Key (Legend): Tells you how to read the plot like a map key. Without a key, you cannot know what the values mean.

    • Whole number key: 3∣4=343 \mid 4 = 34

    • Decimal key: 3∣4=3.43 \mid 4 = 3.4

Shapes of the Distribution

If you tilt your head to the left, the rows of leaves look just like bars on a graph. This reveals the overall shape of your data:

  • Symmetrical Distribution:

    • The data is balanced evenly on both sides.

    • The longest rows of leaves are right in the middle, and they taper off equally toward both the top and the bottom (forming a neat hill or bell shape).

  • Positively Skewed (Skewed Right):

    • Most of the data is clustered at the smaller values (near the top stems).

    • The distribution has a long "tail" stretching down toward the larger values (toward the bottom stems).

    • Remember: Skewness always points toward the stretched-out tail.

  • Negatively Skewed (Skewed Left):

    • Most of the data is clustered at the larger values (near the bottom stems).

    • The distribution has a long "tail" stretching up toward the smaller values (toward the top stems).

Steps to Draw a Stem-and-Leaf Plot
  1. Sort the data

    • Arrange all your numbers in order from least to greatest.

  2. Split into stems and leaves

    • The last digit of every number becomes the leaf.

    • All digits in front of the last digit become the stem.

  3. Set up the stem column

    • Write the stems in sequential order down the left side of a vertical dividing line.

    • Include stems that have no leaves if they fall between your smallest and largest values to show gaps in the data.

  4. Fill in the leaves

    • Write each leaf to the right of its stem in order from least to greatest.

    • Space the digits evenly so the lengths of the rows accurately show the shape of the data.

  5. Add a key

    • Always write a key at the bottom showing what one stem and leaf combination means.

Worked Example

Scores from a class test with 1010 students: 5858, 6262, 6767, 7171, 7171, 7575, 8383, 8888, 9090, 9494

5 | 8
6 | 2 7
7 | 1 1 5
8 | 3 8
9 | 0 4

Key: 6∣2=62 marks6 \mid 2 = 62\text{ marks}

  • Shape: This data set is roughly symmetrical because the longest row is in the middle at stem 77, with the leaves tapering off evenly toward stems 55 and 99.

Finding Summary Statistics
  • Mode: The most frequent value. Find leaves that repeat on the same stem. Here, the digit 11 appears twice on stem 77, so the mode is 7171.

  • Median: The middle value. Because the numbers are already in order, count inward from the first leaf (5858) and the last leaf (9494) to find the middle.

  • Range: The difference between the highest and lowest values (94−58=3694 - 58 = 36).

Variations
  • Back-to-Back Stem-and-Leaf Plot: Compares two groups (like boys vs. girls or test 11 vs. test 22) using a single stem column down the center, with leaves branching out to the left and right.

  • Split Stem-and-Leaf Plot: Splits each stem into two rows (leaves 00 to 44 on the first row, and leaves 55 to 99 on the second) when too many numbers bunch up on only a few stems.

Advantages and Limitations
  • Advantages:

    • Retains all exact values without losing any details.

    • Clearly displays shape, skewness, mode, and outliers.

    • Makes finding the median and range simple.

  • Limitations:

    • Becomes crowded and difficult to read when working with very large data sets.