Mains GS I: Modern history and culture of India, current events, statistics · Unit 37 of 38
Statistical Analysis, Graphs and Diagrams
Mean, median, mode, weighted and combined averages, range and standard deviation, percentages and growth, ratios, index numbers, and reading and drawing bar, pie, line and tabular data, with BPSC-style worked examples.
- BPSC Mains GS Paper I: statistical analysis, graphs and diagrams
- BPSC Prelims: general mental ability (arithmetic and data)
- JPSC: data interpretation basics
Why this unit matters
- BPSC Mains GS Paper I has a section on statistical analysis, graphs and diagrams. These questions carry high marks and are fully scoring if you practise them.
- BPSC Prelims and JPSC ask quick arithmetic and data questions.
Measures of central tendency
- Arithmetic mean: x̄ = (Σx) ⁄ n.
- Weighted mean: x̄ = (Σwx) ⁄ (Σw).
- Combined mean: x̄ = (n₁x̄₁ + n₂x̄₂) ⁄ (n₁ + n₂).
- For a frequency table: x̄ = (Σfx) ⁄ (Σf), using class mid-points for grouped data.
- Median: the middle value after sorting.
- For an odd n, it is the ((n + 1) ⁄ 2)th value.
- For an even n, it is the average of the (n ⁄ 2)th and (n ⁄ 2 + 1)th values.
- Grouped data: Median = L + ((n ⁄ 2 − cf) ⁄ f) × h, where L is the lower limit of the median class, cf the cumulative frequency before it, f its frequency and h the class width.
- Mode: the most frequent value.
- Grouped data: Mode = L + ((f₁ − f₀) ⁄ (2f₁ − f₀ − f₂)) × h.
- Empirical relation: Mode ≈ 3 Median − 2 Mean.
- Which to use:
- The mean is affected by extreme values (incomes, for example).
- The median is better for skewed data.
- The mode suits categories (the most common crop, for example).
Measures of dispersion
- Range = largest value − smallest value.
- Mean deviation = Σ|x − x̄| ⁄ n.
- Variance: σ² = Σ(x − x̄)² ⁄ n.
- Standard deviation: σ = √(variance).
- Coefficient of variation (CV) = (σ ⁄ x̄) × 100. Use it to compare consistency: the lower the CV, the more consistent the series.
- Quartiles: Q₁ and Q₃. The interquartile range is Q₃ − Q₁.
Percentages, ratios and growth
- Percentage change = ((new − old) ⁄ old) × 100.
- Successive changes of a% and b%: net = a + b + (ab ⁄ 100). Use a minus sign for a fall.
- Percentage points vs per cent: a rise in unemployment from 4% to 5% is 1 percentage point, but 25 per cent.
- Growth:
- Decadal growth = ((P₂ − P₁) ⁄ P₁) × 100.
- CAGR = (ⁿ√(final ⁄ initial) − 1) × 100, where n is the number of years. For example, doubling in 10 years means a CAGR of about 7.2%.
- Rule of 70: doubling time ≈ 70 ⁄ (growth rate in %).
- Ratio and proportion: a : b = ka : kb. To split ₹x in the ratio a : b, the first share is x × a ⁄ (a + b).
- Index numbers: Index = (current value ⁄ base value) × 100.
- Laspeyres uses base-year weights; Paasche uses current-year weights.
- India's CPI and WPI are index numbers.
Diagrams and graphs
| Type | Use | Drawing tips |
|---|---|---|
| Simple bar diagram | Compare one variable across categories (districts, years) | Equal widths and gaps; start the axis at 0; label values |
| Multiple (grouped) bar | Compare two or three variables (male and female literacy by district) | A key or legend; distinct shading |
| Sub-divided (stacked) bar | Parts of a whole across categories | Same order of parts in every bar |
| Percentage bar | Composition in per cent | Every bar is 100 |
| Pie chart | Parts of one whole | Angle = (value ⁄ total) × 360°; at most 6–7 slices |
| Line graph | Trend over time | Time on the x-axis; mark the points; use a false origin (a "break") only when needed |
| Histogram | Continuous class intervals | Bars touch; area ∝ frequency |
| Frequency polygon or ogive | Shape of a distribution; cumulative frequency | The ogive gives the median and quartiles |
| Pictogram, cartogram | Simple presentation; data on a map | Show the scale |
- Every diagram needs a title, labelled axes with units, a scale, a legend and the source (for example "Source: Census 2011"). Neatness carries marks in BPSC Mains.
Worked BPSC-style example
Question. The literacy rates (%) of four districts of Bihar are: Patna 70.7, Rohtas 73.4, Purnia 51.1 and Kishanganj 55.5 (Census 2011). Find the mean and the range, and name a suitable diagram.
Answer.
- Mean = (70.7 + 73.4 + 51.1 + 55.5) ⁄ 4 = 250.7 ⁄ 4 ≈ 62.7%.
- Range = 73.4 − 51.1 = 22.3 percentage points.
- Diagram: a simple bar diagram with districts on the x-axis and literacy (%) on the y-axis (scale 1 cm = 10%). Draw a horizontal line for the state average (61.8%) for contrast.
Data interpretation strategy
- Read the title, units and notes first. Is the figure in lakh or crore, per cent or absolute?
- Approximate wherever the options are far apart.
- Avoid common traps: confusing the base year, mixing up percentage and percentage points, or reading a stacked bar's segment as a total.
Exam tip: Practise one table, one bar chart and one pie chart each day for a month. In BPSC Mains, carry a scale, pencil and eraser, and draw diagrams in pencil with neat labels.
Mains practice
Write each answer in the word limit your exam sets. Use the notes above for the structure: introduction, body with facts and examples, a short way forward.
- The table gives the population (lakh) of four districts in 2001 and 2011. Calculate the decadal growth rate of each and draw a suitable bar diagram. (BPSC Mains GS I style)
- Explain the difference between a histogram and a bar diagram with examples. When is a pie chart unsuitable?