- Foundation
- About 20 min
- 5 practice questions
The median: individual, discrete and continuous series
Define the median as a positional average and calculate it for ungrouped data (odd and even N), a discrete series and a continuous series.
If something looks wrong, please tell us.
By the end of this lesson you can
- Define the median and explain why it is not affected by extreme values.
- Find the median of ungrouped data and of a discrete series using cumulative frequency.
- Apply the median formula to a continuous series.
The mean uses every value, so a few extreme values can distort it. The median avoids this by looking only at position.
The median is the value in the middle position once the data are put in order of size: as many items lie at or below it as lie at or above it, so it splits the distribution into two equal halves.
Because it depends on position, the median is unaffected if, say, the largest value becomes even larger. It is therefore a better summary than the mean when data contain extreme values (outliers). On the other hand, it is not sensitive to all the values; it concentrates on the central items.
Individual (ungrouped) series
Arrange the data in ascending (or descending) order. The position of the median is the (N + 1) ÷ 2 th item; the median is the size (value) of that item. If N is even, the median is the mean of the two middle values.
Worked example 1: odd and even N
Odd N (illustrative): 34, 18, 27, 45, 22, 31, 40, 29, 25. Ordered: 18, 22, 25, 27, 29, 31, 34, 40, 45. N = 9; position = (9 + 1) ÷ 2 = 5th item = 29. Four values lie below 29 and four above.
Even N (illustrative): 12, 15, 9, 20, 18, 11, 16, 14. Ordered: 9, 11, 12, 14, 15, 16, 18, 20. N = 8; position = (8 + 1) ÷ 2 = 4.5th item, between the 4th (14) and 5th (15). Median = (14 + 15) ÷ 2 = 14.5.
Worked example 2: median versus mean with an outlier
| Series (illustrative) | Mean | Median |
|---|---|---|
| 4, 5, 6 | 5 | 5 |
| 4, 5, 60 | 23 | 5 |
| 4, 5, 600 | 203 | 5 |
Means: 15 ÷ 3 = 5; 69 ÷ 3 = 23; 609 ÷ 3 = 203. The median stays at 5 because the middle value never changes. For data such as incomes, where a few very large values occur, the median is often the better average.
Discrete series
Find the cumulative frequencies (cf). Locate the (N + 1) ÷ 2 th item: it lies in the first value whose cf equals or exceeds this position. That value is the median.
Worked example 3: a discrete series
| Daily wage (₹) | Workers (f) | Cumulative frequency (cf) |
|---|---|---|
| 300 | 3 | 3 |
| 350 | 7 | 10 |
| 400 | 12 | 22 |
| 450 | 5 | 27 |
| 500 | 3 | 30 |
N = 30; position = (30 + 1) ÷ 2 = 15.5th item. The cf column reads 3, 10, 22 ...: the 11th to 22nd workers all earn ₹400, so the 15.5th item is ₹400. Median wage = ₹400.
Continuous series
Here we locate the N ÷ 2 th item (not (N + 1) ÷ 2). The class containing it is the median class. Then:
Median = L + ((N ÷ 2 − c.f.) ÷ f) × h, where L = lower limit of the median class, c.f. = cumulative frequency of the class before the median class, f = frequency of the median class, h = width of the median class.
Worked example 4: a continuous series
| Marks | Number of students (f) | Mid-value (m) | fm | d' = (m − 35) ÷ 10 | fd' | Cumulative frequency |
|---|---|---|---|---|---|---|
| 0-10 | 4 | 5 | 20 | −3 | −12 | 4 |
| 10-20 | 8 | 15 | 120 | −2 | −16 | 12 |
| 20-30 | 14 | 25 | 350 | −1 | −14 | 26 |
| 30-40 | 12 | 35 | 420 | 0 | 0 | 38 |
| 40-50 | 7 | 45 | 315 | 1 | 7 | 45 |
| 50-60 | 5 | 55 | 275 | 2 | 10 | 50 |
| Total | 50 | 1,500 | −25 |
Step 1: N ÷ 2 = 50 ÷ 2 = 25. Step 2: cumulative frequencies are 4, 12, 26 ...; 25 first fits within the cf of 26, so the median class is 20-30. Step 3: L = 20, c.f. = 12 (the class before), f = 14, h = 10. Step 4: Median = 20 + ((25 − 12) ÷ 14) × 10 = 20 + (13 ÷ 14) × 10 = 20 + 9.29 = 29.29 marks (to two decimals). Meaning: half the students scored 29.29 or less and half scored 29.29 or more. Check: 29.29 lies inside the median class 20-30, as it must.
Finding the median of a continuous series
- Cumulative frequencies Add frequencies down the table
- N ÷ 2 Position of the median
- Median class First class whose cf reaches N ÷ 2
- Apply formula L + ((N ÷ 2 − c.f.) ÷ f) × h
- Check Answer must lie inside the median class
The median can also be found graphically from the ogives you met in the previous chapter: the 'less than' and 'more than' ogives intersect at the median.
Key takeaways: the median is the middle value of ordered data, a positional average not affected by extreme values. For ungrouped and discrete data, it is the size of the (N + 1) ÷ 2 th item (with cumulative frequency for discrete series). For a continuous series, locate the N ÷ 2 th item and use Median = L + ((N ÷ 2 − c.f.) ÷ f) × h.
Check your understanding
-
1. Illustrative: the median of 7, 3, 9, 5, 11, 1, 13 is:
- 5
- 9
- 6
- 7
Show answer
Answer: D. Ordered: 1, 3, 5, 7, 9, 11, 13. N = 7; position = (7 + 1) ÷ 2 = 4th item = 7.
-
2. Illustrative: the median of 10, 4, 8, 6, 12, 2 is:
- 7
- 6
- 8
- 42
Show answer
Answer: A. Ordered: 2, 4, 6, 8, 10, 12. N = 6; position 3.5, between 6 and 8. Median = (6 + 8) ÷ 2 = 7.
-
3. Illustrative: in a continuous series N = 80, the median class is 40-50 with frequency 16, and the cumulative frequency of the class before it is 30. The median is:
- 45
- 50
- 46.25
- 40
Show answer
Answer: C. N ÷ 2 = 40. Median = 40 + ((40 − 30) ÷ 16) × 10 = 40 + (10 ÷ 16) × 10 = 40 + 6.25 = 46.25, which lies inside the median class 40-50.
-
4. Which statement about the median is correct?
- It is affected most by extreme values
- It is a positional value and is not affected if the largest value increases
- It uses every value in its calculation
- The sum of deviations from the median is always zero
Show answer
Answer: B. The median depends only on position, so increasing the largest value leaves it unchanged. It is the mean whose deviations sum to zero and which is affected by extremes.
-
5. Assertion (A): In a continuous series, the median class is found from the N ÷ 2 th item. Reason (R): In ungrouped data, the median is the size of the (N + 1) ÷ 2 th item.
- 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: B. Both statements are true, as the chapter states, but R describes ungrouped data and does not explain why N ÷ 2 is used for a continuous series. So R is not the explanation of A.
Sign in to keep track of the lessons you finish.