∫ SJ Maths Mathematics Notes
UP PGT Tracker UP TGT Tracker
Statistics

Measurement of central tendency

Measures of central tendency—including the Arithmetic Mean, Median, and Mode—summarize large datasets with a single representative value situated at the center of the distribution. This topic covers their algebraic properties, empirical relations, and weighted formulations.

For: UP PGT Mathematics UP TGT Mathematics DSSSB PGT / TGT KVS / NVS PGT LT Grade
📖 Topic progress
○ Mark as complete

Definition and statement

Empirical Relation of Central Tendency (Karl Pearson's Formula)
For a moderately asymmetrical (skewed) frequency distribution, the exact empirical relationship connecting the mean, median, and mode is given by: $$\text{Mode} = 3(\text{Median}) - 2(\text{Mean})$$

📐 Geometric Interpretation

In a moderately skewed unimodal frequency curve, the median lies between the mean and the mode. The distance from the median to the mode is approximately twice the distance from the mean to the median, reflecting the asymmetric pull of extreme tails.

⚙️ Algebraic & Structural Meaning

Derived from the relative positioning of partition values in skewed distributions, this identity allows the exact determination of an unknown central measure when any two are provided, bypassing the need for raw data reconstruction.

Conditions and hypotheses

Check each condition and what changes when it is omitted:

Hypothesis / Condition Domain / Interval Necessity What Fails If Condition Dropped
Unimodality and Moderate Asymmetry Continuous/Discrete frequency distributions Strictly Mandatory for Karl Pearson's Empirical Formula For extremely J-shaped, U-shaped, or multi-modal distributions, the empirical relation $\text{Mode} = 3\text{Median} - 2\text{Mean}$ fails completely.
Exhaustive and Mutually Exclusive Classes Class intervals in grouped data Strictly Mandatory Overlapping or open-ended class intervals without boundary adjustments lead to indeterminate median and mode calculations.
Finite Variance and Existence of Moments Real number set $\mathbb{R}$ Essential for Arithmetic Mean Infinite or undefined variance (e.g., Cauchy distribution) renders the arithmetic mean undefined or non-existent.

Useful results and shortcuts

Use these identities and results when their conditions apply:

01

Combined Mean of Two Groups

$$ \bar{x}_{12} = \frac{n_1\bar{x}_1 + n_2\bar{x}_2}{n_1 + n_2} $$

Rule: Direct weighting formula to find the combined mean of two or more combined series without re-summing raw observations.

Application: Directly tested in UP PGT/TGT and KVS to find combined average marks of sections.
02

Change of Origin and Scale for Mean

$$ \text{If } y_i = \frac{x_i - a}{h}, \text{ then } \bar{x} = a + h\bar{y} $$

Rule: Coding method: Subtract a provisional mean 'a' and divide by class width 'h' to simplify large numbers before computing the mean.

Application: Saves up to 45 seconds in calculation-heavy UP PGT numerical questions.
03

Median of Discrete Frequency Distribution

$$ \text{Median} = \text{Value corresponding to c.f. just } \ge \frac{N}{2} $$

Rule: Instantly locate median position via cumulative frequency without drawing ogives.

04

Mode of Grouped Data with Equal Class Widths

$$ \text{Mode} = L + \frac{f_1 - f_0}{2f_1 - f_0 - f_2} \times h $$

Rule: Identify modal class by maximum frequency $f_1$, then apply linear interpolation formula.

05

Algebraic Property of Mean Deviations

$$ \sum_{i=1}^n (x_i - A)^2 \text{ is minimum when } A = \text{Mean} $$\n$$ \sum_{i=1}^n |x_i - A| \text{ is minimum when } A = \text{Median} $$

Rule: Sum of absolute deviations is minimized about the median, while sum of squared deviations is minimized about the mean.

06

Geometric Mean of Scale Changes

$$ \text{If } y_i = k x_i, \text{ then } G_y = |k| G_x $$

Rule: Multiplicative scaling affects geometric mean directly by factor $|k|$.

Application: Rapid elimination trick for properties of central tendency.

Common errors and counterexamples

These examples show how a conclusion can fail when a condition is missing:

⚠️ COMMON ERROR #01

Open-End Intervals and Mean Calculation

Common Pitfall: Attempting to calculate the arithmetic mean of a grouped frequency distribution containing open-end classes like 'Below 10' or 'Above 50'.

Counterexample: \text{Classes: '< 10', '10-20', '20-30', '> 30'}

Why it fails: Arithmetic mean cannot be computed because the mid-point of open-end classes is undefined. However, Median and Mode can still be calculated.

🛡️ Exam Defense: Remember: Mean requires closed intervals for all classes. Median and Mode are immune to open-end classes.
⚠️ COMMON ERROR #02

Zero or Negative Observations in Geometric Mean

Common Pitfall: Applying Geometric Mean to datasets containing zero or negative values.

Counterexample: \text{Dataset: } \{-2, 0, 4}

Why it fails: Geometric mean involves the $n$-th root of the product; negative products yield complex numbers, and zero products annihilate the value.

🛡️ Exam Defense: Geometric Mean is valid strictly for positive real observations ($x_i > 0 \forall i$).

Comparison

Concept / TheoremHypotheses / AssumptionsKey Formula / OutcomeGeometric MeaningExam Identification Clue
Arithmetic MeanAll observations weighted equally; interval/ratio scale$\bar{x} = \frac{1}{n}\sum x_i$Center of gravity or balancing point of the mass pointsKeywords: 'average', 'combined mean', 'sum of deviations is zero'
MedianOrdinal or continuous data; position-basedValue at position $\frac{N+1}{2}$Abscissa dividing total area under the frequency curve into two equal halvesKeywords: 'middle value', 'divided into two equal parts', open-end data
ModeCategorical, discrete, or continuous data$\text{Mode} = L + \frac{f_1-f_0}{2f_1-f_0-f_2}h$Point of maximum ordinate (peak) of the frequency curveKeywords: 'most frequent', 'maximum concentration', 'modal class'
Geometric MeanPositive numbers only ($x_i > 0$)G = $(\prod_{i=1}^n x_i)^{\frac{1}{n}}$Antilog of the mean of logarithmic valuesKeywords: 'growth rate', 'percentage increase', 'compound interest'

Solved examples

Each problem includes a full solution and a shorter method:

CANONICAL PROBLEM 01 Dual-Method Breakdown

In a moderately asymmetrical distribution, the mode and mean are respectively 32.1 and 35.4. Find the median of the distribution.

(A) 34.3(B) 34.2(C) 33.5(D) 35.0
✓ Correct Answer: (A)
📚 Method A: Formal Textbook Derivation
Step 1: Write Karl Pearson's empirical formula: $\text{Mode} = 3(\text{Median}) - 2(\text{Mean})$. Step 2: Substitute given values: $32.1 = 3(\text{Median}) - 2(35.4)$. Step 3: $32.1 = 3(\text{Median}) - 70.8$. Step 4: $3\text{Median} = 102.9 \implies \text{Median} = 34.3$.
⚡ Method B: 25-Second Exam Shortcut
Apply empirical relation mentally: $3M_d = \text{Mode} + 2\bar{x} = 32.1 + 70.8 = 102.9 \implies M_d = 34.3$.
💡 Tip: Direct formula application; takes less than 20 seconds.
CANONICAL PROBLEM 02 Dual-Method Breakdown

The mean weight of 9 students is 25 kg. If one more student is added, the mean weight becomes 26 kg. Find the weight of the added student.

(A) 30 kg(B) 35 kg(C) 34 kg(D) 32 kg
✓ Correct Answer: (B)
📚 Method A: Formal Textbook Derivation
Step 1: Total weight of 9 students = $9 \times 25 = 225$ kg. Step 2: Total weight of 10 students = $10 \times 26 = 260$ kg. Step 3: Weight of 10th student = $260 - 225 = 35$ kg.
⚡ Method B: 25-Second Exam Shortcut
New observation = New Mean + ($n$ \times Increase in Mean) = $26 + 9 \times 1 = 35$ kg.
💡 Tip: Master the shortcut for adding/removing observations to save time.

Practice questions

Choose an answer to check it and see the solution:

Q1
MCQ 1: If the algebraic sum of deviations of 20 observations from $25$ is $100$, then the mean of the observations is:
A 20
B 25
C 30
D 35
Derivation & Analysis:

Given $\sum_{i=1}^{20} (x_i - 25) = 100$. Expanding: $\sum x_i - 20(25) = 100 \implies \sum x_i - 500 = 100 \implies \sum x_i = 600$. Mean $\bar{x} = \frac{600}{20} = 30$. Alternatively, $\bar{x} = A + \frac{\sum(x_i-A)}{n} = 25 + \frac{100}{20} = 25 + 5 = 30$.

Q2
MCQ 2: Which of the following measures of central tendency is most affected by extreme values?
A Median
B Mode
C Arithmetic Mean
D Geometric Mean
Derivation & Analysis:

The arithmetic mean utilizes every single observation in the dataset with equal weight; hence, extremely large or small values disproportionately pull the mean toward themselves.

Q3
MCQ 3: If each observation in a raw dataset is multiplied by $k$ ($k \neq 0$), then the arithmetic mean of the new observations:
A Remains unchanged
B Is multiplied by $k$
C Is divided by $k$
D Is increased by $k$
Derivation & Analysis:

If $y_i = k x_i$, then $\bar{y} = \frac{1}{n}\sum (k x_i) = k \left(\frac{1}{n}\sum x_i\right) = k \bar{x}$. Thus, the mean is scaled by $k$.

Q4
MCQ 4: For a symmetric distribution, which of the following relations holds strictly true?
A Mean > Median > Mode
B Mean < Median < Mode
C Mean = Median = Mode
D Mode = 3 Median - 2 Mean
Derivation & Analysis:

In a perfectly symmetrical distribution, the frequencies are symmetrically mirrored about the center, causing the mean, median, and mode to coincide at the exact same point.

Q5
MCQ 5: The median of the first $10$ positive even integers is:
A 10
B 11
C 12
D 10.5
Derivation & Analysis:

First 10 even integers: $2, 4, 6, 8, 10, 12, 14, 16, 18, 20$. Number of terms $n = 10$ (even). Median is the mean of the 5th and 6th terms: $\frac{10 + 12}{2} = 11$.

Q6
MCQ 6: If the mean of five observations $x, x+2, x+4, x+6, x+8$ is $11$, then the value of $x$ is:
A 5
B 7
C 9
D 11
Derivation & Analysis:

Sum of observations = $x + (x+2) + (x+4) + (x+6) + (x+8) = 5x + 20$. Mean = $\frac{5x+20}{5} = x + 4$. Given mean is $11$, so $x + 4 = 11 \implies x = 7$.

Q7
MCQ 7: The sum of the squares of the deviations of a set of $n$ observations is minimum when taken about:
A Arithmetic Mean
B Median
C Mode
D Zero
Derivation & Analysis:

By the principle of least squares, $\sum_{i=1}^n (x_i - A)^2$ attains its minimum value when $A$ is chosen equal to the arithmetic mean $\bar{x}$.

Q8
MCQ 8: If the geometric mean of two numbers is $8$ and their harmonic mean is $6.4$, then their arithmetic mean is:
A 7.2
B 10
C 6
D 9.6
Derivation & Analysis:

For any two positive numbers, the relation connecting AM, GM, and HM is $GM^2 = AM \times HM$. Substituting: $8^2 = AM \times 6.4 \implies 64 = AM \times 6.4 \implies AM = \frac{64}{6.4} = 10$.

Q9
MCQ 9: Which measure of central tendency can be calculated from an open-end frequency table?
A Arithmetic Mean only
B Geometric Mean only
C Median and Mode
D None of these
Derivation & Analysis:

Since median depends on positional order and cumulative frequency, and mode depends on the highest concentration within the modal class, neither requires the exact lower/upper limits of extreme open-ended classes.

Q10
MCQ 10: The harmonic mean of two numbers $a$ and $b$ is $4$, and their arithmetic mean is $9$. Find their geometric mean.
A 5
B 6
C 7
D 8
Derivation & Analysis:

Using $GM^2 = AM \times HM$, we have $GM^2 = 9 \times 4 = 36 \implies GM = \sqrt{36} = 6$.

Common questions

The arithmetic mean incorporates every data point's exact magnitude into the numerator sum. Extreme outliers disproportionately pull the mean toward the tails, misrepresenting the typical center of the data. In such cases, the Median is preferred as a robust measure.

Candidates frequently confuse the empirical formula constants or misapply properties of change of origin and scale (forgetting that multiplicative scale factors affect standard deviation and mean, but additive shifts only affect the mean).

Avoid recalculating raw totals. Use the direct weighted formula $\bar{x}_{12} = \frac{n_1\bar{x}_1 + n_2\bar{x}_2}{n_1 + n_2}$ and memorize shortcut properties such as minimizing sum of squares about the mean.

← Previous Topic
Statistics of birth and death
Next Topic →
Frequency distribution