- Practice
- About 18 min
- 5 practice questions
Dispersion and standard deviation
Explain dispersion and the difference between absolute and relative measures, and calculate the standard deviation and variance of raw data by the actual mean and assumed mean methods.
If something looks wrong, please tell us.
By the end of this lesson you can
- Explain why an average needs a measure of dispersion beside it.
- Define standard deviation and variance and know the symbols σ and s.
- Calculate standard deviation by deviations from the actual mean and from an assumed mean.
Two classes can have the same average mark and still be very different: in one, everybody scores near the average; in the other, some score very high and some very low. An average locates the centre but says nothing about how the values are spread around it. That spread is called dispersion.
Absolute and relative measures
- Absolute measures state the variation in the units of the data (rupees, kilograms, marks). Standard deviation is one of them.
- Relative measures are pure numbers, free from units, so they can compare the variation of sets measured in different units.
Standard deviation
Karl Pearson introduced the standard deviation in 1893. It is the positive square root of the arithmetic mean of the squared deviations of the observations from their arithmetic mean, which is why it is also called the root-mean-square deviation. Its square is the variance. The population standard deviation is written σ (sigma) and a sample's is written s. The textbook adds that for small samples (fewer than 30 items) the sum of squared deviations is divided by n − 1 instead of n; the worked examples below divide by n, as the book's examples do.
Actual mean method: σ = √[Σ(X − X̄)² ÷ n]. Assumed mean method: σ = √[Σd² ÷ n − (Σd ÷ n)²], where d = X − A. Variance = σ².
Steps: actual mean method
- Find the mean X̄
- Find each deviation x = X − X̄
- Square the deviations and add: Σx²
- Divide by n: this is the variance
- Take the square root: this is σ
Worked example 1: actual mean method
Made-up data: units sold by a shop on six days: 14, 10, 18, 12, 20 and 16. Step 1: ΣX = 90, so X̄ = 90 ÷ 6 = 15.
| X | x = X − 15 | x² |
|---|---|---|
| 14 | −1 | 1 |
| 10 | −5 | 25 |
| 18 | 3 | 9 |
| 12 | −3 | 9 |
| 20 | 5 | 25 |
| 16 | 1 | 1 |
| ΣX = 90 | Σx = 0 | Σx² = 70 |
Step 2: the deviations add to 0, which checks the mean. Step 3: variance = 70 ÷ 6 ≈ 11.67. Step 4: σ = √11.67 ≈ 3.42 units. Answer: σ ≈ 3.42; on average, daily sales lie about 3.4 units from the mean of 15.
Worked example 2: assumed mean method
Made-up data: weekly income (₹ hundred) of eight households: 32, 45, 38, 51, 40, 47, 29 and 42. Take A = 40.
| X | d = X − 40 | d² |
|---|---|---|
| 32 | −8 | 64 |
| 45 | 5 | 25 |
| 38 | −2 | 4 |
| 51 | 11 | 121 |
| 40 | 0 | 0 |
| 47 | 7 | 49 |
| 29 | −11 | 121 |
| 42 | 2 | 4 |
| n = 8 | Σd = 4 | Σd² = 388 |
Step 1: Σd ÷ n = 4 ÷ 8 = 0.5, so the mean is 40 + 0.5 = 40.5. Step 2: Σd² ÷ n = 388 ÷ 8 = 48.5. Step 3: variance = 48.5 − (0.5)² = 48.5 − 0.25 = 48.25. Step 4: σ = √48.25 ≈ 6.95. Check: ΣX = 324 and 324 ÷ 8 = 40.5, which matches the mean found in step 1. Answer: σ ≈ 6.95 (₹ hundred).
Worked example 3: comparing two sets
Made-up data: Set P = 48, 50, 52 and Set Q = 30, 50, 70. Both have mean 50. For P, deviations are −2, 0, 2; Σx² = 4 + 0 + 4 = 8; σ = √(8 ÷ 3) ≈ 1.63. For Q, deviations are −20, 0, 20; Σx² = 400 + 0 + 400 = 800; σ = √(800 ÷ 3) ≈ 16.33. Same mean, but Q is ten times as spread out, which the mean alone could not show.
Key takeaways: dispersion is the spread of values around the centre. Standard deviation, introduced by Karl Pearson in 1893, is an absolute measure: the root-mean-square deviation from the mean. Variance is its square. Use σ = √[Σx² ÷ n] with the actual mean, or σ = √[Σd² ÷ n − (Σd ÷ n)²] with an assumed mean.
Check your understanding
-
1. Standard deviation is also called:
- mean deviation
- quartile deviation
- root-mean-square deviation
- relative deviation
Show answer
Answer: C. It is the square root of the mean of the squared deviations from the mean, hence root-mean-square deviation.
-
2. The concept of standard deviation was introduced by:
- Karl Pearson
- Francis Galton
- R. A. Fisher
- Ragnar Frisch
Show answer
Answer: A. The textbook states that Karl Pearson introduced standard deviation in 1893.
-
3. Made-up data: find the standard deviation of 2, 4, 6, 8 and 10.
- 8
- 2
- 4
- about 2.83
Show answer
Answer: D. Mean = 30 ÷ 5 = 6. Deviations −4, −2, 0, 2, 4; squares 16, 4, 0, 4, 16; sum 40. Variance = 40 ÷ 5 = 8; σ = √8 ≈ 2.83. 8 is the variance, not σ.
-
4. If the standard deviation of a series is 5, its variance is:
- √5
- 25
- 10
- 2.5
Show answer
Answer: B. Variance is the square of the standard deviation: 5² = 25.
-
5. Made-up data: for 5 values, using an assumed mean, Σd = 5 and Σd² = 45. The standard deviation is:
- 3
- 9
- about 2.83
- about 3.16
Show answer
Answer: C. σ = √[Σd² ÷ n − (Σd ÷ n)²] = √[45 ÷ 5 − (5 ÷ 5)²] = √(9 − 1) = √8 ≈ 2.83. Forgetting to subtract (Σd ÷ n)² gives √9 = 3.
Sign in to keep track of the lessons you finish.