Comparing Data Sets
Go beyond averages — compare two data sets using measures of centre AND spread to draw meaningful, evidence-based conclusions.
Printable Worksheets
Print or save as PDF — or build a custom worksheet from any module's questions.
Before you read on — two classes both have a mean score of 65% on a test. Class A's scores range from 40% to 90%. Class B's scores range from 58% to 72%. Which class performed more consistently? Write your thinking.
To compare two data sets fairly, you must compare measures of centre (mean or median) AND measures of spread (range). A smaller range means more consistent data. Same mean does not mean same performance.
Team A and Team B both average 72 points. But Team A has range 24 (60 to 84) while Team B has range 8 (68 to 76). Team B is far more consistent even though the means are identical. Centre tells you the typical value; spread tells you how reliable that typical value is.
Know
- The definitions of centre (mean, median) and spread (range)
- How to read a back-to-back stem-and-leaf plot
- That consistency is measured by spread, not centre
Understand
- Why comparing only means is not sufficient
- How a smaller range indicates more consistent data
- Why sample size affects how you interpret comparisons
Can Do
- Calculate and compare mean, median and range for two data sets
- Draw and read a back-to-back stem-and-leaf plot
- Write a conclusion comparing two data sets in context
Wrong: "Both groups have the same mean, so their data is the same." Same mean says nothing about spread — the data could be completely different.
Right: Compare mean and range. Two sets can have identical means but very different spreads, telling very different stories.
Wrong: "Group A is better than Group B." Better in what way? Higher mean? Smaller range? Always specify what you mean.
Right: "Group A has a higher mean score, but Group B is more consistent with a smaller range." Name the measure and the direction.
When comparing two data sets, calculate the mean (sum ÷ count) and the median (middle value when ordered) for each set. The group with the higher mean or median typically performs better on average.
Group A scores: 12, 15, 18, 20, 25. Mean = (12+15+18+20+25)÷5 = 90÷5 = 18. Median = 18 (middle value).
Group B scores: 10, 16, 18, 22, 24. Mean = 90÷5 = 18. Median = 18. Same centre — but the spread will be different!
The range is the simplest measure of spread. Range = maximum − minimum. A smaller range means the data is clustered closer together — the group is more consistent. A large range means the values are spread out — the group is more variable.
Group A: 12, 15, 18, 20, 25. Range = 25 − 12 = 13.
Group B: 10, 16, 18, 22, 24. Range = 24 − 10 = 14.
If Group A were 5, 15, 18, 20, 30 → range = 25 — much less consistent despite the same mean. A single outlier can blow out the range.
A back-to-back stem-and-leaf plot places two data sets side by side, sharing a common stem in the middle. The left group's leaves read outward to the left (right to left from the stem). This makes visual comparison of centre and spread very easy.
Team A scores: 61, 68, 72, 75, 78, 84. Team B scores: 69, 71, 73, 74, 76, 77. The stems are 6, 7, 8. Reading Team B's leaves, they cluster in the 70s row. Team A's values are spread across three rows, showing greater variability.
Watch Me Solve It · 3 examples
-
1Calculate the mean for each classClass A: (55+60+65+70+75) ÷ 5 = 325 ÷ 5 = 65
Class B: (40+60+65+70+90) ÷ 5 = 325 ÷ 5 = 65Both classes have the same mean. Centre alone doesn't tell the full story. -
2Calculate the range for each classClass A: 75 − 55 = 20
Class B: 90 − 40 = 50Class A's range is much smaller: 20 vs 50. The spread is very different! -
3Write a comparison in contextBoth classes have the same mean score of 65. However, Class A is more consistent with a range of 20, while Class B is less consistent with a range of 50.Always state the measure, the direction, and what it means in context.
-
1Identify the stems (tens digits)Stems: 2 (for 20s), 3 (for 30s)Both groups have values in the 20s and 30s, so the stems are 2 and 3.
-
2Fill in the leaves for each groupGroup X | Stem | Group Y
7 3 | 2 | 1 4
8 5 1 | 3 | 3 6 9Group X leaves go left (read outward from stem). Group Y leaves go right. -
3Add a keyKey: Group X: 3|2 means 23. Group Y: 2|1 means 21.A key is essential so readers can interpret the leaves correctly.
-
1Compare the centres (mean times)Runner A mean = 58 s (faster on average). Runner B mean = 61 s.Lower time is better for a runner. Runner A is faster on average.
-
2Compare the spread (range)Runner A range = 4 s. Runner B range = 1 s.Runner B is far more consistent — their time barely changes each run.
-
3Write a conclusion with contextRunner A is faster on average (mean 58 s vs 61 s). Runner B is more consistent (range 1 s vs 4 s). For a relay where you need reliability, Runner B is the safer choice.Context determines which measure matters most. Always relate back to the real-world question.
Centre
- Mean = sum ÷ count
- Median = middle value when ordered
- Higher mean = higher typical performance
Spread
- Range = max − min
- Smaller range = more consistent
- Larger range = more variable
Back-to-Back Stem Plot
- Shared stem in the middle
- Left group reads outward (right to left)
- Always include a key
Conclusion Formula
- Group ___ has a higher mean, so it performs better on average.
- Group ___ has a smaller range, so it is more consistent.
- Always relate to real-world context.
How are you completing this lesson?
Brain Trainer · 4 problems
Four problems to sharpen your data comparison skills. Work each, then reveal the answer.
-
1 Group A: mean = 15, range = 8. Group B: mean = 15, range = 2. Which group is more consistent?
Group B is more consistent. Both groups have the same mean (15), but Group B has a much smaller range (2 vs 8), meaning their values cluster much closer together.Group B: smaller range = more consistent -
2 A back-to-back stem plot has stems 4 and 5. Group X leaves on stem 5: 2, 4, 6. Group Y leaves on stem 5: 0, 1, 9. Which group has the higher median for the 50s values?
Group X values in the 50s: 52, 54, 56. Median = 54. Group Y values in the 50s: 50, 51, 59. Median = 51. Group X has the higher median.Group X median (50s) = 54 > Group Y median (50s) = 51 -
3 Why is comparing only means not enough when comparing two data sets?
Two data sets can have the same mean but completely different spreads. One could be very consistent (all values close together) while the other is highly variable. The mean hides this important difference.Same mean + different range = very different data sets -
4 What does "consistent performance" mean for a sports team?
A team performs consistently when their scores don't vary much from game to game. Statistically, this means a small range — the difference between their best and worst results is small. A consistent team is reliable and predictable.Consistent = small range of scores across games
Quick Check · 5 questions
Show Your Working · 3 questions
Q6. Team Red scores: 45, 52, 60, 63, 70. Team Blue scores: 55, 57, 60, 63, 65. Calculate the mean and range for each team. Which team is more consistent? Explain.
Q7. A back-to-back stem plot shows: Left side (Group X), stem 3: leaves 8, 5, 2 (reading outward). What are the actual data values for Group X on stem 3? List them from smallest to largest.
Q8. Two call centres handle customer complaints. Centre A: mean wait time = 4.2 min, range = 6 min. Centre B: mean wait time = 5.0 min, range = 1 min. A manager says "Centre A is better because it has a lower mean." Do you agree? Give a full explanation using both mean and range.
Quick Check
1. B — Range = 28 − 14 = 14.
2. C — A smaller range means more consistent data.
3. A — Both means = 14. Group A range = 8; Group B range = 16. Group A more consistent.
4. D — Left group leaves read right to left, outward from the stem.
5. B — Ordered: 12, 15, 18, 21, 24. Median = 18.
Show Your Working Model Answers
Q6 (3 marks): Red: mean = (45+52+60+63+70)÷5 = 290÷5 = 58; range = 70−45 = 25 [1]. Blue: mean = (55+57+60+63+65)÷5 = 300÷5 = 60; range = 65−55 = 10 [1]. Team Blue is more consistent because its range (10) is much smaller than Team Red's (25), meaning Blue's scores cluster much closer together [1].
Q7 (2 marks): Leaves 8, 5, 2 on stem 3 represent 38, 35, 32 [1]. Ordered smallest to largest: 32, 35, 38 [1].
Q8 (4 marks): Partially agree [1]. Centre A does have a lower mean (4.2 vs 5.0 min), suggesting faster average service [1]. However, Centre B is far more consistent, with a range of only 1 min vs Centre A's 6 min [1]. From a customer experience perspective, Centre B is more reliable — customers always wait close to 5 min, while Centre A customers might wait anywhere from about 1 to 7 minutes [1].
The Clever Coach
A coach must choose one player for a cricket team. Player A's last 6 scores: 0, 15, 45, 60, 72, 84. Player B's last 6 scores: 30, 35, 38, 42, 45, 50. Calculate mean and range for each. Which player would you choose, and does the purpose of the selection matter (once-off match of the century vs regular season)? Justify your answer fully.
Reveal solution
Player A: mean = (0+15+45+60+72+84)÷6 = 276÷6 = 46, range = 84−0 = 84. Player B: mean = (30+35+38+42+45+50)÷6 = 240÷6 = 40, range = 50−30 = 20. Player A has a higher mean (better on average) but is unpredictable (range 84 — could score 0!). Player B is more consistent. For a once-off high-stakes match, Player A is risky. For reliable regular season performance, Player B is the safer choice.
Centre
Mean = sum ÷ count; Median = middle value ordered
Spread
Range = max − min; smaller = more consistent
Back-to-back plot
Shared stem; left leaves read right to left outward
Compare both
Always state centre AND spread in conclusions
Context matters
Relate your conclusion to the real-world situation
Sample size
Larger samples may show wider range — acknowledge this
Interactive: Data Comparison Explorer
Adjust values in two data sets and watch mean and range update live. See how centre and spread can change independently.
Your Badges
0 of 6Mark lesson as complete
Tick when you've finished Learn, Practice and the Stretch. Earns +85 XP and +25 coins.