Measures of Central Tendency for SSC CGL — Mean, Median, Mode, and Beyond

Concept

Central tendency is the idea that any data set has a natural "center" — a single representative value that summarizes the entire distribution. You've been using this idea since school: if you score 70, 80, and 90 on three tests, your average is 80, and that one number tells the story without listing all three scores.

Think of it like this: imagine ten people standing on a number line, each person standing at their salary value. Central tendency asks, "Where is the gravitational center of this group?" Different measures answer this question differently:

• Mean (माध्य) asks: where would the center of mass be if every person had equal weight?
• Median asks: who stands exactly in the middle when everyone lines up in order?
• Mode asks: which position has the most people crowded around it?

Each measure has a different job. The mean uses every value but gets pulled hard by outliers. The median ignores extreme values but gives a stable center. The mode tells you what is most common — useful for categorical data or finding peaks in a distribution.

For SSC CGL, you'll encounter three mean types beyond simple arithmetic mean:

• Arithmetic Mean (AM): simple average, sum divided by count
• Geometric Mean (GM): the nth root of the product of n values — used for growth rates
• Harmonic Mean (HM): n divided by the sum of reciprocals — used for average speeds

Here's a key inequality that examiners love to test: for any positive dataset, HM ≤ GM ≤ AM. The three are equal only when all values are identical.

The analogy that sticks: mean is like a see-saw balance point. One heavy person (outlier) on one end shifts the balance dramatically. Median is like the person standing in the exact middle of a queue — the queue can stretch wildly on both ends, and the middle person's position barely changes.

Deep Dive

Arithmetic Mean

For n values x₁, x₂, ..., xₙ:

$\bar{x} = \frac{x_1 + x_2 + \cdots + x_n}{n} = \frac{\sum x_i}{n}$

The sum-substitution principle is the single most tested idea in SSC CGL mean problems. Once you know the mean and count, you know the sum — and that sum is the real working number.

• If mean = M and count = n, then sum = M × n
• If one value is replaced: new sum = old sum − removed value + added value
• New mean = new sum ÷ n

Weighted Arithmetic Mean:

When different values carry different importance (weights w₁, w₂, ..., wₙ):

$\bar{x}_w = \frac{w_1 x_1 + w_2 x_2 + \cdots + w_n x_n}{w_1 + w_2 + \cdots + w_n} = \frac{\sum w_i x_i}{\sum w_i}$

This appears in problems involving combined groups, mixed populations, or explicitly stated weights.

Combined Mean for two groups:

$\bar{x}_{combined} = \frac{n_1 \bar{x}_1 + n_2 \bar{x}_2}{n_1 + n_2}$

This is just weighted mean where the weights are the group sizes.

Median

Arrange all values in ascending (or descending) order. Then:

• If n is odd: Median = value at position $\frac{n+1}\{2\}$
• If n is even: Median = average of values at positions $\frac{n}\{2\}$ and $\frac{n}\{2\} + 1$

For ungrouped data, this is purely mechanical. Don't overthink it. Sort, count, pick.

For grouped data (frequency distribution), the median class is the one where the cumulative frequency first crosses n/2, and you use the interpolation formula — but SSC CGL rarely goes that deep for this topic at beginner level.

Mode

The mode is the value (or values) that appear most frequently. A data set can have:

• One mode (unimodal)
• Two modes (bimodal)
• No mode (all values appear equally often)

For ungrouped data: just count frequencies. No formula needed.

The Empirical Relationship

Look — this single formula is responsible for a dedicated question type in SSC CGL:

$\text{Mode} = 3 \times \text{Median} - 2 \times \text{Mean}$

This approximation holds for moderately skewed (not heavily skewed) distributions. Rearrange it freely depending on what you're asked to find:

• Given Mode and Mean, find Median: Median = (Mode + 2 × Mean) / 3
• Given Median and Mean, find Mode: Mode = 3 × Median − 2 × Mean
• Given Mode and Median, find Mean: Mean = (3 × Median − Mode) / 2

Memorize all three rearrangements. Examiners rotate which variable they ask for.

Geometric Mean and Harmonic Mean

Geometric Mean of n values:

$GM = \sqrt[n]{x_1 \cdot x_2 \cdots x_n}$

For two numbers a and b: GM = √(ab)

Harmonic Mean of n values:

$HM = \frac{n}{\frac{1}{x_1} + \frac{1}{x_2} + \cdots + \frac{1}{x_n}}$

For two numbers a and b: HM = 2ab/(a+b)

The classic application: if you travel from A to B at speed u and return at speed v, the average speed for the whole journey is the harmonic mean — not the arithmetic mean.

$\text{Average Speed} = \frac{2uv}{u+v}$

Trying to use AM here is one of the most common errors in speed-distance problems.

Relationship between AM, GM, HM for two positive numbers a and b:

$AM = \frac{a+b}{2}, \quad GM = \sqrt{ab}, \quad HM = \frac{2ab}{a+b}$

$GM^2 = AM \times HM$

This identity (GM² = AM × HM) occasionally appears directly in SSC CGL questions.

Memory Tricks & Shortcuts

Fast-Solving Framework

When you see a central tendency question in the exam hall, run this decision tree:

Step 1 — Identify the measure asked. Mean, Median, Mode, or an empirical formula question?

Step 2 — For Mean questions:

• Is it a straightforward average? → Sum ÷ Count.
• Is something excluded or replaced? → Use Sum-First + Delta Trick.
• Are weights given? → Weighted mean formula.
• Are two groups being combined? → Combined mean formula.

Step 3 — For Median questions:

• Sort the data first — never skip this step.
• Count n. Odd → single middle value at (n+1)/2. Even → average the two middle values.

Step 4 — For Mode questions:

• Ungrouped data? Count frequencies, pick the highest.
• Empirical formula involved? Write all three rearrangements, substitute.

Step 5 — Speed check sanity. Your answer should be within the range of the data (for mean and median). If your mean comes out higher than all values in the set, you made an arithmetic error — don't submit.

Total time budget: mean problems 30-45 seconds, median problems 20-30 seconds, empirical formula problems 30-40 seconds.

Solved PYQs

Why this question: Tests the sum-substitution principle — the most fundamental mean technique.

Solving path: Sum = 5 × 18 = 90. New sum (4 numbers) = 4 × 16 = 64. Excluded = 90 − 64 = 26. No algebra needed, just two multiplications and one subtraction. Time: under 15 seconds.

Why this question: Pure median mechanics — tests whether you remember to sort before picking the middle value.

Solving path: Sort: 3, 5, 7, 9, 11, 13, 15. Count = 7 (odd). Middle position = (7+1)/2 = 4th. 4th value = 9. The trap is picking 10 (the arithmetic mean) or 7 — examiners put both as options.

Why this question: Tests the replacement-delta shortcut — a single replacement changes only the sum, not the count.

Solving path: Original sum = 10 × 15 = 150. Delta = 30 − 20 = +10. New sum = 160. New mean = 160 ÷ 10 = 16. Option 15.5 is a distractor for people who average the delta incorrectly.

Why this question: The empirical formula applied forward — given mean and median, find mode.

Solving path: Mode = 3 × Median − 2 × Mean = 3 × 45 − 2 × 50 = 135 − 100 = 35. The distractor 40 comes from people who swap the formula to 2 × Median − 3 × Mean or some scrambled version. Pre-writing the formula prevents this.

Why this question: Tests the empirical formula in reverse — given mode and mean, find median.

Solving path: Mode = 3 × Median − 2 × Mean → 12 = 3 × Median − 20 → 3 × Median = 32 → Median = 32/3 ≈ 10.67. Note the non-integer answer — SSC CGL does give these. Don't round to 11; compute carefully.

Common Mistakes

• Not sorting before finding median. If you pick the middle value of the unsorted sequence, you will almost certainly get it wrong. This mistake is shockingly common under time pressure. Sort first, every time, without exception.

• Using AM for average speed problems. If a body travels equal distances at two different speeds, the average speed is the HM, not the AM. The AM answer is always present as a distractor. Trigger phrase to watch: "same distance, different speeds."

• Confusing Mean = 0 with Sum = 0. If the mean of a data set is zero, the sum is zero — the individual values are not all zero. This sometimes appears in algebraic mean problems where you need to find an unknown value.

• Weighted mean with the wrong denominator. The denominator is the sum of weights, not the count of items. For weights 3, 2, 1, the denominator is 6 — not 3. This single error shifts your answer completely.

• Misapplying the empirical formula when the distribution is heavily skewed. The formula Mode = 3 Median − 2 Mean is an approximation. If an exam question explicitly states "using the empirical relationship," use it. If they don't, and the data looks extreme, be cautious — but SSC CGL always signals when they want this formula.

• Treating bimodal data as having the higher-frequency value win. If two values appear the same number of times and that frequency is the maximum, the data set is bimodal — it has two modes. Some questions test this edge case. Don't automatically pick the larger or smaller of the two.

Related Topics

• measures of dispersion
• frequency distribution
• data interpretation
• ratio and proportion
• weighted averages
• grouped data statistics

Practice on SarkariRise