- Arithmetic mean for individual observations is Σx/n; for frequency data it is Σfx/Σf.
- Grouped arithmetic mean uses class marks and is generally an estimate.
- Assumed-mean and step-deviation methods simplify the same mean calculation.
- Weighted mean is Σwx/Σw; combined means must account for group sizes.
- Median is the middle ordered value; grouped median uses cumulative frequency and interpolation.
- Mode is the most frequent value and may be non-unique.
- The mean is sensitive to outliers, while the median is comparatively robust.
- Grouped-mode interpolation and the empirical mean, median, mode relation require assumptions.
- Averages should be interpreted with dispersion, units and sample size.
Use these notes alongside your current textbook. Check important formulas, worked answers and syllabus coverage with your teacher or official learning material.
Measures of Central Tendency , Class 11 Economics
Original supplementary guide for Statistics for Economics. All datasets are constructed teaching examples.
Learning objectives
Calculate arithmetic mean, median and mode for individual, discrete and grouped frequency data; use direct, assumed-mean and step-deviation methods; compute weighted mean; interpret quartiles and positional averages; compare advantages and limitations; and recognise when grouped-data answers are estimates.
1. Meaning of central tendency
A measure of central tendency summarises a dataset using a representative central value. Common averages include arithmetic mean, median and mode. They answer different questions: the mean balances values, the median locates the middle of an ordered distribution, and the mode identifies the most frequent value. No single average describes variability or all characteristics of a distribution.
2. Arithmetic mean: individual observations
For n observations x₁, x₂, …, xₙ, arithmetic mean x̄ = Σx/n. It uses every observation and has the same units as the data. Example: values 4, 6, 8 give x̄ = (4 + 6 + 8)/3 = 6.
Direct method: add the observations and divide by n. Assumed-mean method: choose A and define d = x − A; then x̄ = A + Σd/n. Step-deviation method: if d' = (x − A)/h for a convenient common scale h, then x̄ = A + h(Σd'/n). These are algebraically equivalent when used consistently.
3. Arithmetic mean: discrete frequency series
For values x with frequencies f, N = Σf and x̄ = Σfx/N. Constructed example:
| x | f | fx |
|---|---|---|
| 10 | 2 | 20 |
| 20 | 3 | 60 |
| 30 | 5 | 150 |
| Total | 10 | 230 |
Mean = 230/10 = 23. The assumed-mean form is x̄ = A + Σfd/N; step-deviation form is x̄ = A + hΣfu/N, where u = (x − A)/h.
4. Arithmetic mean: continuous grouped series
For grouped intervals, use class marks m = (lower boundary + upper boundary)/2 as representative values. The estimated mean is Σfm/N. Example:
| Class interval | f | Class mark m | fm |
|---|---|---|---|
| 0, 10 | 4 | 5 | 20 |
| 10, 20 | 6 | 15 | 90 |
| 20, 30 | 10 | 25 | 250 |
| Total | 20 | , | 360 |
Estimated mean = 360/20 = 18. This is generally approximate because exact values within each class are unknown.
5. Assumed mean and step deviation: worked example
For the grouped table above choose A = 15, class width h = 10, and u = (m − 15)/10. The u values are −1, 0, 1; therefore Σfu = 4(−1) + 6(0) + 10(1) = 6. Thus x̄ = 15 + 10(6/20) = 18. Using deviations d = m − 15 gives Σfd = 60, so x̄ = 15 + 60/20 = 18 again. Do not divide by the number of classes instead of total frequency.
6. Weighted arithmetic mean
When observations have different importance, use x̄w = Σwx/Σw with suitable nonnegative weights and Σw > 0. For course components with scores 80, 70, 90 and weights 20%, 30%, 50%, weighted mean = 0.2(80) + 0.3(70) + 0.5(90) = 82. Weights must refer to comparable measures; a simple average of subgroup means can be misleading when subgroup sizes differ.
7. Combined mean
For groups with sizes n₁, n₂ and means x̄₁, x̄₂, combined mean = (n₁x̄₁ + n₂x̄₂)/(n₁ + n₂). Example: 10 students average 60 marks and 20 students average 75 marks; combined mean = (10 × 60 + 20 × 75)/30 = 70, not the unweighted average 67.5.
8. Properties, merits and limitations of arithmetic mean
The sum of deviations from the arithmetic mean equals zero: Σ(x − x̄) = 0, and the mean minimises the sum of squared deviations among real-valued choices of centre. It is convenient for further algebra and uses all values, but is sensitive to outliers. Example: the mean of 2, 3, 4, 5, 100 is 114/5 = 22.8, which does not describe a typical small observation well. Open-ended grouped classes make a class-mark mean difficult without further assumptions.
9. Median: individual series
Arrange observations in ascending order. For odd n, the median is the observation at position (n + 1)/2. For even n, it is the average of observations at positions n/2 and n/2 + 1. Example: ordered 2, 5, 9, 100 gives median = (5 + 9)/2 = 7. The median is less sensitive to extremes than the mean.
10. Median: discrete frequency series
Compute cumulative frequencies and locate the middle ordered observation(s). Example:
| Value x | f | Cumulative f |
|---|---|---|
| 10 | 2 | 2 |
| 20 | 4 | 6 |
| 30 | 3 | 9 |
| 40 | 1 | 10 |
N = 10, so the 5th and 6th observations are both 20; median = 20. For even N, inspect both middle observations rather than automatically taking the first cumulative frequency above N/2.
11. Median: continuous grouped frequency series
Find N/2 and identify the median class using less-than cumulative frequencies. The standard interpolated grouped median is Median = L + [(N/2 − C)/f] × h, where L is the median-class lower boundary, C is cumulative frequency before that class, f its frequency and h its width.
| Class | f | Less-than cumulative f |
|---|---|---|
| 0, 10 | 5 | 5 |
| 10, 20 | 9 | 14 |
| 20, 30 | 6 | 20 |
N = 20; N/2 = 10 lies in 10, 20. Median ≈ 10 + [(10 − 5)/9] × 10 = 15.56. Interpolation assumes a suitable within-class distribution; it does not recover the exact ungrouped median.
12. Quartiles and other positional measures
Quartiles divide ordered data into four parts. Q₁ is the lower quartile (approximately the 25th percentile), Q₂ is the median and Q₃ is the upper quartile (approximately the 75th percentile). For grouped data, an interpolated quartile uses Qk = L + [(kN/4 − C)/f] × h for k = 1 or 3, with the relevant quartile class. Exact positional conventions for small ungrouped samples can differ between textbooks and software; follow the prescribed method.
13. Mode: individual and discrete series
Mode is the most frequently occurring value. In 2, 3, 3, 4, 5, the mode is 3. In a discrete series, identify the value with the highest frequency. Data may be bimodal or multimodal when two or more values tie for highest frequency; if every value occurs equally often, there is no unique mode. Mode can be useful for categorical data such as most common transport choice.
14. Mode: grouped continuous series
For equal-width grouped classes with a clear modal class, the interpolated mode is Mode = L + [(f₁ − f₀)/(2f₁ − f₀ − f₂)] × h, where f₁ is modal-class frequency, f₀ the preceding class frequency, f₂ the succeeding class frequency, L the modal-class lower boundary and h the class width.
| Class | Frequency |
|---|---|
| 0, 10 | 5 |
| 10, 20 | 12 |
| 20, 30 | 7 |
Modal class 10, 20; mode ≈ 10 + [(12 − 5)/(24 − 5 − 7)] × 10 = 10 + 70/12 = 15.83. This formula requires suitable grouped-data assumptions; unequal class widths need care, and an ill-defined modal class can invalidate simple interpolation.
15. Empirical relation among mean, median and mode
For some moderately skewed, unimodal distributions, the rough empirical relationship is Mode ≈ 3 × Median − 2 × Mean. It is a heuristic, not an identity or a universally valid formula. Do not use it when the actual distribution or textbook question does not justify the approximation.
16. Choosing the appropriate average
| Measure | Best use | Important limitation |
|---|---|---|
| Arithmetic mean | Quantitative data, further calculation | Strongly affected by extreme values |
| Median | Skewed data, ordered values, income comparisons | Does not use magnitudes of all observations |
| Mode | Most common category or value | May be non-unique or unstable |
| Weighted mean | Observations with defined relative weights | Depends on justified, correctly scaled weights |
For skewed household incomes, the median often communicates the typical household better than the mean. Report dispersion and sample size alongside an average where possible.
17. Worked examples and calculations
- Simple mean: 4, 6, 8 → (4 + 6 + 8)/3 = 6.
- Even-sample median: 2, 5, 9, 100 → (5 + 9)/2 = 7.
- Odd-sample median: 1, 4, 6, 9, 11 → middle value = 6.
- Mode: 2, 3, 3, 4, 5 → 3.
- Discrete mean: x = 10, 20, 30; f = 2, 3, 5 → 230/10 = 23.
- Grouped mean: class marks 5, 15, 25; frequencies 4, 6, 10 → 360/20 = 18.
- Weighted mean: 80, 70, 90 weighted 0.2, 0.3, 0.5 → 82.
- Combined mean: n₁ = 10, mean₁ = 60; n₂ = 20, mean₂ = 75 → 70.
- Grouped median: median class 10, 20, N = 20, C = 5, f = 9 → 15.56 (approx.).
- Grouped mode: modal class 10, 20, f₀ = 5, f₁ = 12, f₂ = 7 → 15.83 (approx.).
18. Practice questions with answers
- Find the mean of 5, 7, 9, 11. 32/4 = 8.
- Find the median of 4, 8, 10. 8.
- Find the median of 3, 5, 7, 9. (5 + 7)/2 = 6.
- Find the mode of 2, 4, 4, 5, 5, 5. 5.
- For x = 1, 2, 3 and f = 2, 3, 5, find mean. (2 + 6 + 15)/10 = 2.3.
- Find class mark of 40, 60. (40 + 60)/2 = 50.
- Find weighted mean of 60 and 90 with weights 1 and 2. (60 + 180)/3 = 80.
- Combine groups of 5 at mean 20 and 15 at mean 40. (100 + 600)/20 = 35.
- For f = 3, 5, 2, find cumulative frequencies. 3, 8, 10.
- Why can the mean misrepresent skewed incomes? A few very large incomes can raise it above the income of a typical household.
- What is the median class if N = 30 and cumulative frequencies are 6, 18, 30? The second class, because N/2 = 15.
- Is Mode = 3 Median − 2 Mean exact? No; it is an approximate empirical relation under restricted conditions.
19. Common errors and revision checklist
Sort raw data before finding the median. For frequency tables divide Σfx by Σf, not the number of distinct values. For grouped data use class boundaries and the preceding cumulative frequency correctly. Check that the modal-class formula uses neighbouring frequencies in the correct order. State when grouped results are estimates. Do not confuse weighted mean with an unweighted mean of group averages. Do not assume mode is unique or the empirical mean, median, mode relation always holds.
20. Formula sheet
| Concept | Formula |
|---|---|
| Individual mean | x̄ = Σx/n |
| Frequency mean | x̄ = Σfx/Σf |
| Assumed-mean method | x̄ = A + Σfd/N |
| Step-deviation method | x̄ = A + hΣfu/N |
| Weighted mean | x̄w = Σwx/Σw |
| Combined mean | (n₁x̄₁ + n₂x̄₂)/(n₁ + n₂) |
| Grouped median | L + [(N/2 − C)/f]h |
| Grouped mode | L + [(f₁ − f₀)/(2f₁ − f₀ − f₂)]h |
| Grouped quartile | Qk = L + [(kN/4 − C)/f]h |
21. Summary and source scope
Arithmetic mean, median and mode each represent a different aspect of a distribution. Choose the measure based on data type, skewness and the question. Grouped-data calculations often use midpoints or interpolation and should be reported as estimates. This is an original supplementary study guide, not a verified reproduction of official NCERT exercise solutions. For exact numbered exercises and current prescribed content consult https://ncert.nic.in/textbook.php and the applicable CBSE 2026, 27 curriculum at https://cbseacademic.nic.in/curriculum_2027.html.
Frequently asked questions
What are the main measures of central tendency?
Arithmetic mean, median and mode; weighted mean and positional measures are also useful in suitable contexts.
How is the arithmetic mean calculated?
For n observations, divide their sum by n; for a frequency distribution, divide Σfx by Σf.
How do you calculate median for even n?
Sort the data and average the observations at positions n/2 and n/2 + 1.
What is the formula for grouped median?
Median = L + [(N/2 − C)/f] × h, using the median-class lower boundary, preceding cumulative frequency, class frequency and width.
How do you calculate grouped mode?
For suitable equal-width classes, use L + [(f1 − f0)/(2f1 − f0 − f2)] × h with the modal class and neighbouring frequencies.
When is median preferable to mean?
Often for skewed data or when extreme observations would distort the mean, such as household income.
Can there be more than one mode?
Yes. A distribution may have two or more values tied for highest frequency.
Are these official NCERT exercise solutions?
No. These are original supplementary notes and practice problems; consult the prescribed NCERT edition for exact numbered exercises.
