- Foundation
- About 18 min
- 5 practice questions
Why we need averages; arithmetic mean of individual observations
Understand why data are summarised by one representative value, name the three common averages, and calculate the arithmetic mean of ungrouped data by the direct, assumed mean and step deviation methods.
If something looks wrong, please tell us.
By the end of this lesson you can
- Explain what a measure of central tendency does and name the three common averages.
- Calculate the arithmetic mean of ungrouped data by the direct method.
- Use the assumed mean and step deviation methods to simplify the calculation.
We meet averages every day: average marks in a test, average rainfall, average income in a locality. Suppose you want to judge whether a made-up farmer's 2 acres in a village of 60 small farmers is large or small. You might ask whether it is above the ordinary average (the arithmetic mean), above what half the farmers own (the median), or above what most farmers own (the mode). Each question needs the whole set of land holdings to be summarised by one number.
A measure of central tendency summarises a set of data by a single typical or representative value that can stand for the entire data.
The three most commonly used averages are the arithmetic mean, the median and the mode. Two others, the geometric mean and the harmonic mean, suit special situations but are not studied in this chapter.
Common measures of central tendency
-
Arithmetic mean
Sum of values ÷ number of values
- Based on all observations
-
Median
Middle value of ordered data
- A positional average
-
Mode
Most frequently occurring value
- The most typical value
Arithmetic mean: definition
The arithmetic mean is the sum of the values of all observations divided by the number of observations. It is written X̄ (read 'X bar'). If there are N observations X1, X2, ..., XN, then X̄ = (X1 + X2 + ... + XN) ÷ N, written briefly as X̄ = ΣX ÷ N, where Σ (sigma) means 'sum of'.
Worked example 1: direct method
Illustrative: daily earnings (₹) of six made-up vegetable vendors are 420, 380, 450, 510, 470 and 410. Step 1, sum: 420 + 380 = 800; + 450 = 1,250; + 510 = 1,760; + 470 = 2,230; + 410 = 2,640. Step 2, divide by N = 6: 2,640 ÷ 6 = ₹440. Check: 440 × 6 = 2,640. On average a vendor earns ₹440 a day.
Assumed mean method
When observations are many or large, the direct method is tiresome. Choose any convenient value A as the assumed mean (any value, in the data or not; a centrally placed one makes the work easiest). Take deviations d = X − A, add them, and correct A by the average deviation.
Assumed mean method: X̄ = A + Σd ÷ N, where d = X − A. Step deviation method: X̄ = A + (Σd' ÷ N) × c, where d' = (X − A) ÷ c and c is a common factor.
Worked example 2: assumed mean method
Illustrative weekly incomes (₹) of eight made-up families: 1,200; 950; 4,800; 1,500; 700; 2,300; 1,050; 1,900. Take A = 1,500.
| Family | Income X (₹) | d = X − 1,500 | d' = d ÷ 50 |
|---|---|---|---|
| P | 1,200 | −300 | −6 |
| Q | 950 | −550 | −11 |
| R | 4,800 | 3,300 | 66 |
| S | 1,500 | 0 | 0 |
| T | 700 | −800 | −16 |
| U | 2,300 | 800 | 16 |
| V | 1,050 | −450 | −9 |
| W | 1,900 | 400 | 8 |
| Total | 14,400 | 2,400 | 48 |
Assumed mean method: Σd = −300 − 550 + 3,300 + 0 − 800 + 800 − 450 + 400 = 2,400. X̄ = 1,500 + 2,400 ÷ 8 = 1,500 + 300 = ₹1,800. Check by the direct method: ΣX = 14,400; 14,400 ÷ 8 = ₹1,800. Both agree.
Worked example 3: step deviation method
All the deviations above are multiples of 50, so divide them by the common factor c = 50 to get d' (last column). Σd' = −6 − 11 + 66 + 0 − 16 + 16 − 9 + 8 = 48. X̄ = 1,500 + (48 ÷ 8) × 50 = 1,500 + 6 × 50 = 1,500 + 300 = ₹1,800. The smaller numbers make mistakes less likely, and the answer is the same.
Steps in the step deviation method
- Choose A A convenient, central value
- Deviations d = X − A
- Divide by c d' = d ÷ c, using a common factor
- Sum and average Σd' ÷ N
- Correct A X̄ = A + (Σd' ÷ N) × c
Notice that family R's income (₹4,800) is far above the rest and pulls the mean up: six of the eight families earn less than the mean of ₹1,800. You will see later that the mean is affected by extreme values.
Key takeaways: averages summarise data by one representative value; the common ones are the mean, median and mode. The arithmetic mean is ΣX ÷ N. With an assumed mean A, X̄ = A + Σd ÷ N; with a common factor c, X̄ = A + (Σd' ÷ N) × c. All three methods give the same answer.
Check your understanding
-
1. Illustrative: marks of five students are 42, 55, 38, 61 and 49. Their arithmetic mean is:
- 49
- 48
- 245
- 50
Show answer
Answer: A. Sum = 42 + 55 + 38 + 61 + 49 = 245. Mean = 245 ÷ 5 = 49.
-
2. Illustrative: with an assumed mean A = 60, the deviations of 10 observations add up to −30. The arithmetic mean is:
- 57
- 63
- 30
- 60
Show answer
Answer: A. X̄ = A + Σd ÷ N = 60 + (−30 ÷ 10) = 60 − 3 = 57.
-
3. In the assumed mean method, the assumed mean:
- must be the largest observation
- must be one of the observations
- must be the true mean
- can be any value, though a central one simplifies the work
Show answer
Answer: D. The chapter notes that any value, whether in the data or not, can be taken as the assumed mean; a centrally located value keeps deviations small.
-
4. Illustrative: using A = 200 and c = 20, the step deviations of 8 observations sum to 12. The mean is:
- 212
- 230
- 201.5
- 240
Show answer
Answer: B. X̄ = A + (Σd' ÷ N) × c = 200 + (12 ÷ 8) × 20 = 200 + 1.5 × 20 = 200 + 30 = 230.
-
5. Assertion (A): The direct, assumed mean and step deviation methods give the same arithmetic mean. Reason (R): The assumed mean and step deviation methods only simplify the arithmetic; the correction term restores the true mean.
- Both A and R are true, and R is the correct explanation of A
- Both A and R are true, but R is not the correct explanation of A
- A is true, but R is false
- A is false, but R is true
Show answer
Answer: A. Both are true, and R explains A: subtracting A (and dividing by c) is undone by adding back A and multiplying by c, so the result equals ΣX ÷ N.
Sign in to keep track of the lessons you finish.