Mathematics · Statistics

How Spread Out?

Range Quartiles & IQR Box plots Standard deviation The bell curve

Two basketball players both average 10 points a game. One scores 10 every night. The other scores 0 one night and 20 the next. The average cannot tell them apart. Spread can. Drag data points around, watch the numbers respond, and learn the measures statisticians use to describe consistency.

Learning Targets

  • Compute and interpret the range, quartiles, and interquartile range (IQR).
  • Read a box plot and spot outliers with the 1.5 × IQR rule.
  • Explain standard deviation as a typical distance from the mean, and see how it responds to changing the data.
  • Use the 68–95–99.7 rule and a z-score to place a value on a bell curve.

Prerequisites: Mean, Median & Mode. Next: Galton Board & Pachinko Lab, where a bell curve emerges from falling balls.

Lab 1 · Drag the Data

Each dot is one value on a number line from 0 to 20. Drag any dot left or right. The orange line is the mean, the blue band reaches one standard deviation either side, and the box plot underneath is built from the quartiles. Dots beyond the outlier fences turn red.

Mean10
Median10
Range0
Q1 · Q30 · 0
IQR0
Std deviation (σ)0

How each measure is found

  • Range = largest − smallest. Simple, but one wild value ruins it.
  • Q1, median, Q3 cut the sorted data into four equal-sized groups. IQR = Q3 − Q1, the spread of the middle half.
  • Standard deviation: find each value's distance from the mean, square them, average the squares, then take the square root. It is the “typical” distance from the mean. (Here we treat these dots as the whole population.)

Try: drag one dot far away. Which changes more, the IQR or the standard deviation? Which one would you trust with an outlier in the data?

Lab 2 · Same Mean, Different Story

Team A and Team B both average 10 points. Team A is steady. Use the slider to change how spread out Team B is, and see how the story changes even though the mean never does.

Team A: mean · σ10 · 1.5
Team B: mean · σ10 · 4.0

Discuss: which team would you pick to score at least 8 in a must-win game? Which would you pick if you needed 18 and were willing to gamble?

Lab 3 · The Bell Curve & the 68–95–99.7 Rule

Many measurements pile up in a bell shape: heights, test scores, measurement errors, the balls in a pachinko board. For a bell curve, about 68% of values fall within 1 σ of the mean, 95% within 2 σ, and 99.7% within 3 σ. Change the mean and σ and see where the bands land.

68% of values60 – 80
95% of values50 – 90
99.7% of values40 – 100

z-scores: how many σ from the mean?

A z-score lets you compare things measured on different scales. A 85 on a test with μ = 70 and σ = 10 has z = 1.5. Whether that beats a 28 on a test with μ = 20 and σ = 4 (z = 2) is a question about how far from typical, not about raw points. That is the practice question below.

Practice

Answers within 0.05 count.

1. Data: 3, 5, 8, 10, 15. What is the range?

2. Data: 1, 2, 3, 4, 5, 6, 7. The median is 4. Q1 is the median of 1, 2, 3 and Q3 is the median of 5, 6, 7. What is the IQR?

3. Data: 2, 4, 6, 8 (mean 5). What is the standard deviation, to two decimal places?

4. Scores have μ = 70 and σ = 10. What is the top of the middle 68%?

5. About what percent of a bell-curve data set lies within 2 standard deviations of the mean?

6. z-score of 85 when μ = 70 and σ = 10?

7. Test B has μ = 20 and σ = 4. What is the z-score of a 28? (The bigger z is the more impressive result.)

8. Q1 = 8 and Q3 = 12. Values above what number count as outliers? (Upper fence = Q3 + 1.5 × IQR.)

Exit Ticket

  • Two data sets have the same mean and median. How could one still be much more spread out than the other?
  • A single extreme value is added. Which changes more: the IQR or the standard deviation, and why?
  • Describe a real situation where consistency (small σ) matters more than the average.