Chapter 13 · Statistics and data displays

Create and Interpret Dot Plots

Learn to turn a list of data into a dot plot with one mark for each observation, then read the stacks to count and compare the data.

13 min read

You know that a statistical question has answers that vary. Those answers form a distribution, which is the way the data values are spread out. A dot plot is one way to draw the distribution of numerical data. Some books call it a line plot.

A dot plot is a number line with marks above it. The numbers along the line are the scale, and each number on the scale is a position. The scale goes up by the same amount each time. That amount is the step size.

Each mark stands for one observation, which is one recorded data value. A mark sits above the position that equals its value. The marks above one position form a stack. People often draw the marks as dots, and that gives the plot its name.

Here is a small set of data. Eight students each said how many pets they have:

0,0,1,1,1,2,4,40, 0, 1, 1, 1, 2, 4, 4

The unit is pets, and each mark is one student's answer. Look at the dot plot below. Its scale goes from 00 to 44 pets in steps of 11.

  • The two answers of 00 are the two marks above 00.
  • The three answers of 11 are the three marks above 11.
  • The one answer of 22 is the one mark above 22.
  • Nobody answered 33, so the position for 33 stays on the line with no marks. That is an empty stack.
  • The two answers of 44 are the two marks above 44.

Now count the marks: (2+3)+(1+0+2)=5+3=8(2 + 3) + (1 + 0 + 2) = 5 + 3 = 8. That matches the 88 students.

Line plotLine plot. Value axis: each step is 1, up to 3. Measure axis: each step is 1 pet, up to 4 pets. 0 pets, 2. 1 pet, 3. 2 pets, 1. 3 pets, 0. 4 pets, 2.0××1×××2×34××pets
Line plot
Each mark is one student. From 00 to 44 pets, the stacks hold 22, 33, 11, 00 and 22 marks.

Key concept

One mark for each observation

A dot plot shows every observation by itself. Each mark is one observation, and it sits above its exact value on the number line. Each value has its own position, so the plot never groups nearby values together.

The number of marks in a stack is the count of observations with that value. In this lesson, the scale starts at 00 and goes up in equal steps. The plot shows every position on the scale, even when its stack is empty.

Because each mark is one observation, the number of observations is the sum of the counts of all the stacks. Counting the positions that have marks answers a different question: how many different values appear.

number of observations=sum of the counts of all the stacks\text{number of observations} = \text{sum of the counts of all the stacks}

To create a dot plot, you turn a list of data into stacks of marks. In this lesson, you build every plot the same way.

  1. Find the greatest value in the data. The scale starts at 00 and must reach that value.
  2. Choose a step size that lets every data value land exactly on a position. Whole-number data can use steps of 11. Data that are all multiples of 55 can use steps of 55.
  3. Draw the number line. Show every position from 00 to the end of the scale, and label the line with its unit.
  4. Count how many times each value appears. Put that many marks above the value. When the count is 00, leave the stack empty but keep the position.
  5. Check your plot. The counts of all the stacks must add up to the number of data values, because each mark is one observation.

Why keep an empty position? A number line needs equal spacing. If you drop a value that nobody had, the values on each side look closer than they really are. The empty stack also tells a true fact: no observation has that value.

Worked example

Example 1: Create a dot plot from a list

Twelve students each recorded how many books they read over the summer: 3,5,2,4,3,7,2,3,5,3,2,43, 5, 2, 4, 3, 7, 2, 3, 5, 3, 2, 4. Create a dot plot of the data. The unit is books, and each mark stands for one student.

  1. Find the greatest value, because the scale must reach it. The greatest value is 7 books. Every value is a whole number, so steps of 1 land exactly on every value.

  2. Draw the number line from 0 to 7 in steps of 1, and label it books. With the position for 0, that makes 8 positions. The scale starts at 0, so 0 and 1 are on the line even though no student gave those answers.

    0,1,2,3,4,5,6,70, 1, 2, 3, 4, 5, 6, 7
  3. Count how many times each value appears, because each stack must show that count. Cross off each value as you count it, so you use every value exactly once. The value 2 appears three times, 3 appears four times, 4 appears twice, 5 appears twice and 7 appears once. The values 0, 1 and 6 do not appear, so their counts are 0.

    counts from 0 to 7 books: 0,0,3,4,2,2,0,1\text{counts from } 0 \text{ to } 7 \text{ books: } 0, 0, 3, 4, 2, 2, 0, 1
  4. Draw one mark for each observation, above its exact value. Stack three marks above 2, four marks above 3, two marks above 4, two marks above 5 and one mark above 7. Leave the stacks above 0, 1 and 6 empty, but keep those positions on the line.

  5. Check the plot. Each mark is one observation, so the counts of all 8 stacks must add up to the 12 values in the list.

    (0+0+3+4)+(2+2+0+1)=7+5=12(0 + 0 + 3 + 4) + (2 + 2 + 0 + 1) = 7 + 5 = 12

Answer

The dot plot has a scale from 00 to 77 books in steps of 11. From 00 to 77 books, its stacks hold 00, 00, 33, 44, 22, 22, 00 and 11 marks. That is 1212 marks for the 1212 students.

Line plotLine plot. Value axis: each step is 1, up to 4. Measure axis: each step is 1 book, up to 7 books. 0 books, 0. 1 book, 0. 2 books, 3. 3 books, 4. 4 books, 2. 5 books, 2. 6 books, 0. 7 books, 1.012×××3××××4××5××67×books
Line plot
The finished plot from Example 1. The stacks above 00, 11 and 66 books are empty, and the 1212 marks match the 1212 students.

To interpret a dot plot, you read the stacks back into facts about the data. It is creating in reverse.

  • Value: Look at the position under a stack. When the scale starts at 00 and has equal steps, the value of a position is its number of steps from 00 times the step size.
  • Count: The number of marks in a stack is the number of observations with that value. An empty stack means no observation has that value.
  • Total: Each mark is one observation, so the number of observations is the sum of the counts of all the stacks.
  • Groups: To count the observations that fit a description, such as at least 44, add the counts of every stack that fits. At least 44 means 44 or more.

Try it on the books plot above. The stack above 33 is taller than every other stack, so 33 books is the most common answer. That stack has 44 marks, so 44 students read 33 books. At least 44 books means the stacks above 44, 55, 66 and 77. Their counts add to 2+2+0+1=52 + 2 + 0 + 1 = 5, so 55 students read at least 44 books.

Worked example

Example 2: Read values, counts and the total

A quiz has 66 questions worth 55 points each, with no partial credit. Every score is a multiple of 55, from 00 up to 6×5=306 \times 5 = 30 points. The dot plot below shows the scores of one class. Each mark is one student. What is the lowest score? How many students scored exactly 2020 points? How many students took the quiz?

  1. Read the scale first, because it tells you the value under each stack. It starts at 0 and goes up in steps of 5 points, so the positions are 0, 5, 10, 15, 20, 25 and 30. From 0 to 30 points, the stacks hold 0, 1, 0, 3, 6, 5 and 3 marks.

  2. Find the lowest score. Starting from 0, it is under the first stack that has marks, because an empty stack means no student has that score. The stack above 0 is empty, and the stack above 5 has 1 mark.

    lowest score=5 points\text{lowest score} = 5 \text{ points}
  3. Find the position for 20 points. The scale starts at 0 and has equal steps of 5, so the position 4 steps from 0 has the value 4 times 5, which is 20. The stack above it has 6 marks, and each mark is one student.

    4×5=204 \times 5 = 20
  4. Find the total. Each mark is one observation, so add the counts of all 7 stacks. An empty stack adds 0.

    (0+1+0+3)+(6+5+3)=4+14=18(0 + 1 + 0 + 3) + (6 + 5 + 3) = 4 + 14 = 18

Answer

The lowest score is 55 points. Six students scored exactly 2020 points, and 1818 students took the quiz.

Line plotLine plot. Value axis: each step is 1, up to 6. Measure axis: each step is 5 points, up to 30 points. 0 points, 0. 5 points, 1. 10 points, 0. 15 points, 3. 20 points, 6. 25 points, 5. 30 points, 3.05×1015×××20××××××25×××××30×××points
Line plot
Quiz scores in steps of 55 points. From 00 to 3030 points, the stacks hold 00, 11, 00, 33, 66, 55 and 33 marks, which is 1818 marks in all.

Worked example

Example 3: Combine stacks to answer questions

Use the quiz dot plot above. Each mark is one student, and the scale goes from 00 to 3030 points in steps of 55. How many students scored at least 2020 points? How many more students scored 2525 points than scored 1515 points?

  1. At least 20 points means 20 points or more. On this scale, those scores are 20, 25 and 30. Add the counts of those three stacks, because each mark in them is one student who fits.

    6+5+3=11+3=146 + 5 + 3 = 11 + 3 = 14
  2. Check with the rest of the plot. Every student scored either below 20 or at least 20, so the two groups must add up to the total of 18 from Example 2. The stacks for scores below 20 are above 0, 5, 10 and 15.

    (0+1+0+3)+14=4+14=18(0 + 1 + 0 + 3) + 14 = 4 + 14 = 18
  3. Compare two stacks. The stack above 25 has 5 marks, and the stack above 15 has 3 marks. Subtract the counts to find how many more.

    5−3=25 - 3 = 2

Answer

Of the 1818 students, 1414 scored at least 2020 points. Two more students scored 2525 points than scored 1515 points.

Takeaway. A dot plot keeps every observation in view: each mark is one observation above its exact value. In this lesson, you start the scale at 00, show every position in equal steps, and leave a stack empty when no observation has that value. To interpret a plot, read each value from its position and each count from the number of marks in the stack. The number of observations is the sum of the counts of all the stacks, while the number of positions that have marks is only the number of different values.

Next, you will create and interpret histograms, a display that groups data values instead of showing each one by itself.