Study guide

5.4 Descriptive Statistics: Central Tendency, Dispersion & Frequency Distributions

Bocconi Admission Test Online Bocconi Test for Bachelor Programs

Track your progress as you read

Finished sections get a check mark.

1 Chapter 1: Exam Structure, Scoring Mechanics & Test Strategy

1.1 Test Architecture, Timing & the Sequential Test Interface 1.2 Scoring System, Penalty Mathematics & Strategic Answering

2 Chapter 2: Mathematics — Algebra, Equations & Inequalities

2.1 Algebraic Expressions, Polynomials, Powers & Radicals 2.2 Linear & Quadratic Equations and Systems 2.3 Linear & Quadratic Inequalities and Sign Charts 2.4 Equations and Inequalities with Absolute Values

3 Chapter 3: Mathematics — Functions, Exponents & Logarithms

3.1 Function Concepts, Domain, Range & Inverses 3.2 Composition of Functions & Transformations 3.3 Exponential Functions, Properties & Equations 3.4 Logarithmic Functions, Laws & Equations

4 Chapter 4: Mathematics — Geometry, Analytic Geometry & Trigonometry

4.1 Plane Geometry: Polygons, Circles & Area Theorems 4.2 Analytic Geometry: Lines, Slopes & Distances in the Cartesian Plane 4.3 Conic Sections: Circles & Parabolas in the Coordinate Plane 4.4 Trigonometric Functions, Identities & Right-Triangle Applications

5 Chapter 5: Mathematics — Combinatorics, Probability, Statistics & Set Theory

5.1 Set Theory, Operations & Venn Diagrams 5.2 Combinatorics: Permutations, Combinations & Factorials 5.3 Probability Theory: Independent Events, Conditional Probability & Bayes' Basics 5.4 Descriptive Statistics: Central Tendency, Dispersion & Frequency Distributions

6 Chapter 6: Reading Comprehension — Business, Economic & Academic Analysis

6.1 Main Idea, Text Structure & Passage Mapping 6.2 Explicit Information Retrieval & Detail Verification 6.3 Inference, Implicit Meaning & Authorial Purpose 6.4 Tone, Rhetorical Devices & Vocabulary in Academic Context

7 Chapter 7: Numerical Reasoning — Charts, Tables & Data Interpretation

7.1 Data Tables & Multi-Series Matrices 7.2 Graphical Interpretation: Bar, Line, Pie & Composite Charts 7.3 Percentage Calculations, Changes & Financial Metrics 7.4 Ratios, Proportions, Rates & Weighted Averages

8 Chapter 8: Logic & Critical Thinking — Formal & Deductive Reasoning

8.1 Propositional Logic, Truth Tables & Logical Connectives 8.2 Conditional Reasoning, Contrapositives & Modus Ponens/Tollens 8.3 Syllogisms, Quantifiers & Venn Logic

9 Chapter 9: Critical Thinking — Argument Analysis, Assumptions & the Official Item Types

9.1 Argument Components, Premises & Unstated Assumptions 9.2 Strengthening, Weakening & Flaw Identification 9.3 Constraint Deduction Drills: Ordering, Arrangement & Assignment 9.4 The Two Official Critical-Thinking Item Types: Data Propositions & Deducibility

5.4 Descriptive Statistics: Central Tendency, Dispersion & Frequency Distributions

Key Takeaways Explain This Topic AI

The median divides an ordered dataset into two equal halves and, unlike the arithmetic mean, is invariant to extreme outliers and skewed tails, while the interquartile range IQR = Q₃ - Q₁ measures the middle 50% of data and sets the standard outlier fences at [Q₁ - 1.5·IQR, Q₃ + 1.5·IQR].

Linear transformations y = ax + b scale measures of central tendency by a·μ + b, but shift b has zero effect on dispersion: Var(y) = a²·Var(x) and SD(y) = |a|·SD(x).

The computational variance identity σ² = [Σ(x_i²)/n] - μ² computes variance rapidly without calculating individual deviation terms (x_i - μ).

In frequency distributions, the weighted mean x̄_w = (Σ f_i · x_i) / (Σ f_i) weights each distinct value or class midpoint by its frequency.

In a two-way table, joint frequencies divide a cell by the grand total, marginal frequencies are the row or column totals, and conditional frequencies divide a cell by its own row or column total.

Last updated: September 2026

5.4 Descriptive Statistics: Central Tendency, Dispersion & Frequency Distributions

Descriptive statistics synthesizes raw quantitative data into standardized summary metrics that capture central location, spread, and distributional shape. On the Bocconi Admission Test, statistics problems test algebraic relationships, data transformation theorems, and comparative distribution properties under strict time constraints, rather than demanding extensive tabular arithmetic. Candidates must master the distinct behavior of means versus medians in skewed distributions, the shortcut variance formula, and the linear transformation invariance rules that dictate how scaling and shifting affect statistical parameters.

1. Measures of Central Tendency

Measures of central tendency locate the single representative value around which numerical observations cluster.

Arithmetic Mean

The arithmetic mean (sample mean x ˉ \bar{x} x ˉ , population mean μ \mu μ ) of n n n observations x 1 , x 2 , … , x n x_1, x_2, \dots, x_n x 1 ​ , x 2 ​ , … , x n ​ is the sum of all values divided by n n n : μ = x ˉ = 1 n ∑ i = 1 n x i \mu = \bar{x} = \frac{1}{n} \sum_{i=1}^n x_i μ = x ˉ = n 1 ​ i = 1 ∑ n ​ x i ​

Zero-Sum Deviation Property: The sum of signed deviations from the mean is always identically zero: ∑ i = 1 n ( x i − x ˉ ) = 0 \sum_{i=1}^n (x_i - \bar{x}) = 0 i = 1 ∑ n ​ ( x i ​ − x ˉ ) = 0

Least Squares Property: The sum of squared deviations ∑ i = 1 n ( x i − c ) 2 \sum_{i=1}^n (x_i - c)^2 ∑ i = 1 n ​ ( x i ​ − c ) 2 is strictly minimized when c = x ˉ c = \bar{x} c = x ˉ .

Weighted Arithmetic Mean

When observations carry different relative importance or frequencies w i w_i w i ​ (or f i f_i f i ​ ): x ˉ w = ∑ i = 1 k w i x i ∑ i = 1 k w i \bar{x}_w = \frac{\sum_{i=1}^k w_i x_i}{\sum_{i=1}^k w_i} x ˉ w ​ = ∑ i = 1 k ​ w i ​ ∑ i = 1 k ​ w i ​ x i ​ ​

Combined Subgroup Means: If m m m cohorts have sample sizes n 1 , n 2 , … , n m n_1, n_2, \dots, n_m n 1 ​ , n 2 ​ , … , n m ​ and means x ˉ 1 , x ˉ 2 , … , x ˉ m \bar{x}_1, \bar{x}_2, \dots, \bar{x}_m x ˉ 1 ​ , x ˉ 2 ​ , … , x ˉ m ​ , the combined overall mean is: x ˉ comb = n 1 x ˉ 1 + n 2 x ˉ 2 + ⋯ + n m x ˉ m n 1 + n 2 + ⋯ + n m \bar{x}_{\text{comb}} = \frac{n_1 \bar{x}_1 + n_2 \bar{x}_2 + \dots + n_m \bar{x}_m}{n_1 + n_2 + \dots + n_m} x ˉ comb ​ = n 1 ​ + n 2 ​ + ⋯ + n m ​ n 1 ​ x ˉ 1 ​ + n 2 ​ x ˉ 2 ​ + ⋯ + n m ​ x ˉ m ​ ​ Exam Warning: The unweighted simple average x ˉ 1 + x ˉ 2 2 \frac{\bar{x}_1 + \bar{x}_2}{2} 2 x ˉ 1 ​ + x ˉ 2 ​ ​ is valid only if n 1 = n 2 n_1 = n_2 n 1 ​ = n 2 ​ .

Median

The median (denoted Med \text{Med} Med or Q 2 Q_2 Q 2 ​ ) is the value separating the ordered data into two equal halves (50% ≤ Med \le \text{Med} ≤ Med and 50% ≥ Med \ge \text{Med} ≥ Med ).

Algorithm for Discrete Datasets:

Sort the n n n observations in non-decreasing order: x ( 1 ) ≤ x ( 2 ) ≤ ⋯ ≤ x ( n ) x_{(1)} \le x_{(2)} \le \dots \le x_{(n)} x ( 1 ) ​ ≤ x ( 2 ) ​ ≤ ⋯ ≤ x ( n ) ​ .

If n n n is odd: The median is the unique middle observation at rank n + 1 2 \frac{n + 1}{2} 2 n + 1 ​ : Med = x ( n + 1 2 ) \text{Med} = x_{\left(\frac{n + 1}{2}\right)} Med = x ( 2 n + 1 ​ ) ​

If n n n is even: The median is the arithmetic mean of the two central observations at ranks n 2 \frac{n}{2} 2 n ​ and n 2 + 1 \frac{n}{2} + 1 2 n ​ + 1 : Med = x ( n 2 ) + x ( n 2 + 1 ) 2 \text{Med} = \frac{x_{\left(\frac{n}{2}\right)} + x_{\left(\frac{n}{2} + 1\right)}}{2} Med = 2 x ( 2 n ​ ) ​ + x ( 2 n ​ + 1 ) ​ ​

Robustness Against Outliers: The median is resistant to extreme values. Replacing the largest observation with an arbitrarily large number does not alter the median, whereas it inflates the arithmetic mean significantly.

Mode

The mode ( Mod \text{Mod} Mod ) is the observation occurring with the highest frequency.

Unimodal: A single value attains the maximum frequency.

Bimodal / Multimodal: Two or more distinct values tie for the highest frequency.

No Mode: All values appear with equal frequency.

Distribution Symmetry and Skewness

The relative positioning of mean, median, and mode reflects the directional skewness of a distribution:

Symmetric Distribution (Bell-shaped): Mean ≈ Median ≈ Mode \text{Mean} \approx \text{Median} \approx \text{Mode} Mean ≈ Median ≈ Mode

Positively Skewed (Right-Skewed, long right tail): Extreme high outliers pull the mean upward: Mode < Median < Mean \text{Mode} < \text{Median} < \text{Mean} Mode < Median < Mean

Negatively Skewed (Left-Skewed, long left tail): Extreme low values pull the mean downward: Mean < Median < Mode \text{Mean} < \text{Median} < \text{Mode} Mean < Median < Mode

2. Measures of Dispersion (Variability)

Measures of dispersion quantify the extent to which data points spread out from the central value.

Range R = x max ⁡ − x min ⁡ R = x_{\max} - x_{\min} R = x m a x ​ − x m i n ​

While fast to calculate, the range depends exclusively on two extreme values and ignores all intermediate distribution structure.

Population Variance ( σ 2 \sigma^2 σ 2 )

The variance measures the average squared deviation from the mean: σ 2 = 1 n ∑ i = 1 n ( x i − μ ) 2 \sigma^2 = \frac{1}{n} \sum_{i=1}^n (x_i - \mu)^2 σ 2 = n 1 ​ i = 1 ∑ n ​ ( x i ​ − μ ) 2

The Computational Shortcut for Variance

Calculating deviations ( x i − μ ) (x_i - \mu) ( x i ​ − μ ) for every data point is slow and error-prone. Instead, apply the algebraic shortcut identity: σ 2 = ∑ i = 1 n x i 2 n − μ 2 = x 2 ‾ − ( x ˉ ) 2 \sigma^2 = \frac{\sum_{i=1}^n x_i^2}{n} - \mu^2 = \overline{x^2} - (\bar{x})^2 σ 2 = n ∑ i = 1 n ​ x i 2 ​ ​ − μ 2 = x 2 − ( x ˉ ) 2

Verbal Rule: 'The mean of the squares minus the square of the mean.' This formula computes variance in a fraction of the time on the Bocconi test.

Standard Deviation ( σ \sigma σ )

The standard deviation is the non-negative square root of the variance: σ = σ 2 = 1 n ∑ i = 1 n ( x i − μ ) 2 \sigma = \sqrt{\sigma^2} = \sqrt{\frac{1}{n} \sum_{i=1}^n (x_i - \mu)^2} σ = σ 2 ​ = n 1 ​ i = 1 ∑ n ​ ( x i ​ − μ ) 2 ​

Because it shares the original units of measurement of x x x (unlike variance, which is in squared units), standard deviation is the universal benchmark for risk and dispersion.

3. Linear Transformations of Statistical Data

When every observation in a dataset undergoes a linear transformation y i = a ⋅ x i + b y_i = a \cdot x_i + b y i ​ = a ⋅ x i ​ + b (where a , b ∈ R a, b \in \mathbb{R} a , b ∈ R ):

Measure Type Statistical Metric Original Transformed ( y = a x + b y = ax + b y = a x + b ) Operational Effect

Central Tendency Arithmetic Mean μ x \mu_x μ x ​ μ y = a ⋅ μ x + b \mu_y = a \cdot \mu_x + b μ y ​ = a ⋅ μ x ​ + b Scaled by a a a , shifted by b b b

Central Tendency Median Med x \text{Med}_x Med x ​ Med y = a ⋅ Med x + b \text{Med}_y = a \cdot \text{Med}_x + b Med y ​ = a ⋅ Med x ​ + b Scaled by a a a , shifted by b b b

Central Tendency Mode Mod x \text{Mod}_x Mod x ​ Mod y = a ⋅ Mod x + b \text{Mod}_y = a \cdot \text{Mod}_x + b Mod y ​ = a ⋅ Mod x ​ + b Scaled by a a a , shifted by b b b

Dispersion Range R x R_x R x ​ R y = ∣ a ∣ ⋅ R x R_y = \vert a\vert\cdot R_x R y ​ = ∣ a ∣ ⋅ R x ​ Scaled by ∣ a ∣ \vert a\vert ∣ a ∣ ; shift b b b has zero effect

Dispersion Variance σ x 2 \sigma_x^2 σ x 2 ​ σ y 2 = a 2 ⋅ σ x 2 \sigma_y^2 = a^2 \cdot \sigma_x^2 σ y 2 ​ = a 2 ⋅ σ x 2 ​ Scaled by a 2 a^2 a 2 ; shift b b b has zero effect

Dispersion Standard Deviation σ x \sigma_x σ x ​ σ y = ∣ a ∣ ⋅ σ x \sigma_y = \vert a\vert\cdot \sigma_x σ y ​ = ∣ a ∣ ⋅ σ x ​ Scaled by ∣ a ∣ \vert a\vert ∣ a ∣ ; shift b b b has zero effect

Dispersion Interquartile Range IQR x \text{IQR}_x IQR x ​ IQR y = ∣ a ∣ ⋅ IQR x \text{IQR}_y = \vert a\vert\cdot \text{IQR}_x IQR y ​ = ∣ a ∣ ⋅ IQR x ​ Scaled by ∣ a ∣ \vert a\vert ∣ a ∣ ; shift b b b has zero effect

Mathematical Proof of Dispersion Shift Invariance

Why does additive shift b b b vanish from variance? σ y 2 = 1 n ∑ i = 1 n ( y i − y ˉ ) 2 = 1 n ∑ i = 1 n [ ( a x i + b ) − ( a x ˉ + b ) ] 2 = 1 n ∑ i = 1 n [ a ( x i − x ˉ ) ] 2 = a 2 [ 1 n ∑ i = 1 n ( x i − x ˉ ) 2 ] = a 2 σ x 2 \sigma_y^2 = \frac{1}{n} \sum_{i=1}^n (y_i - \bar{y})^2 = \frac{1}{n} \sum_{i=1}^n [(a x_i + b) - (a \bar{x} + b)]^2 = \frac{1}{n} \sum_{i=1}^n [a(x_i - \bar{x})]^2 = a^2 \left[\frac{1}{n}\sum_{i=1}^n (x_i - \bar{x})^2\right] = a^2 \sigma_x^2 σ y 2 ​ = n 1 ​ i = 1 ∑ n ​ ( y i ​ − y ˉ ​ ) 2 = n 1 ​ i = 1 ∑ n ​ [( a x i ​ + b ) − ( a x ˉ + b ) ] 2 = n 1 ​ i = 1 ∑ n ​ [ a ( x i ​ − x ˉ ) ] 2 = a 2 [ n 1 ​ i = 1 ∑ n ​ ( x i ​ − x ˉ ) 2 ] = a 2 σ x 2 ​

The constant b b b cancels identically inside the deviation brackets. Adding a constant translates all points equally without altering relative distances.

4. Frequency Distributions & Grouped Data

When data is presented in frequency tables:

Absolute Frequency ( f i f_i f i ​ ): Count of occurrences of value x i x_i x i ​ , with ∑ f i = n \sum f_i = n ∑ f i ​ = n .

Relative Frequency ( p i p_i p i ​ ): Proportion p i = f i n p_i = \frac{f_i}{n} p i ​ = n f i ​ ​ , satisfying ∑ p i = 1 \sum p_i = 1 ∑ p i ​ = 1 .

Cumulative Frequency ( F k F_k F k ​ ): Running sum F k = ∑ i = 1 k f i F_k = \sum_{i=1}^k f_i F k ​ = ∑ i = 1 k ​ f i ​ .

Joint, Marginal and Conditional Frequencies (Two-Way Tables)

Bocconi's statistics syllabus asks candidates to "derive absolute and relative frequencies, conjoint and conditioned frequency distributions given in tables or diagrams." A two-way (contingency) table cross-classifies the same units by two characteristics at once, and each of the three frequency types answers a different question.

Take 200 Bocconi applicants classified by intended area and by whether they took a quantitative secondary-school track:

  • Quantitative track Non-quantitative track Row total
  • Economics & Finance 72 28 100
  • Management 36 44 80
  • International Politics 6 14 20
  • Column total 114 86 200

Joint (conjoint) frequency f i j f_{ij} f ij ​ — the count in a single interior cell. The joint relative frequency divides by the grand total: p i j = f i j / n p_{ij} = f_{ij} / n p ij ​ = f ij ​ / n . Economics applicants from a quantitative track: 72 / 200 = 36.0 % 72 / 200 = 36.0\% 72/200 = 36.0% of all applicants.

Marginal frequency — a row or column total, which recovers the one-variable distribution. The marginal relative frequency of Management is 80 / 200 = 40.0 % 80 / 200 = 40.0\% 80/200 = 40.0% .

Conditional frequency — a cell divided by the total of the group you are conditioning on, so the row (or column) sums to 100 % 100\% 100% . Among Management applicants, the conditional relative frequency of a quantitative track is 36 / 80 = 45.0 % 36 / 80 = 45.0\% 36/80 = 45.0% . Among quantitative-track applicants, the conditional relative frequency of Management is 36 / 114 ≈ 31.6 % 36 / 114 \approx 31.6\% 36/114 ≈ 31.6% .

The Direction Trap: those last two numbers, 45.0 % 45.0\% 45.0% and 31.6 % 31.6\% 31.6% , describe the same 36 people and answer different questions. "What percentage of Management applicants took a quantitative track?" conditions on the row ; "what percentage of quantitative-track applicants chose Management?" conditions on the column . Identify the denominator before touching the arithmetic — reversing it is the most common error on two-way table items, and it is the same inversion fallacy that appears in conditional probability in Section 5.3.

Independence check. Two characteristics are statistically independent when every conditional distribution equals the corresponding marginal distribution. Here the marginal share of quantitative-track applicants is 114 / 200 = 57.0 % 114 / 200 = 57.0\% 114/200 = 57.0% , but the conditional share within Economics & Finance is 72 / 100 = 72.0 % 72 / 100 = 72.0\% 72/100 = 72.0% and within International Politics only 6 / 20 = 30.0 % 6 / 20 = 30.0\% 6/20 = 30.0% . The conditional distributions differ sharply from the marginal, so area of interest and school track are not independent in this cohort.

Grouped Data Approximations

When observations are grouped into continuous intervals [ L i , U i ) [L_i, U_i) [ L i ​ , U i ​ ) :

Compute the class midpoint : m i = L i + U i 2 m_i = \frac{L_i + U_i}{2} m i ​ = 2 L i ​ + U i ​ ​ .

Approximate the grouped mean: x ˉ ≈ ∑ f i m i ∑ f i \bar{x} \approx \frac{\sum f_i m_i}{\sum f_i} x ˉ ≈ ∑ f i ​ ∑ f i ​ m i ​ ​ .

Approximate the grouped variance: σ 2 ≈ ∑ f i m i 2 ∑ f i − x ˉ 2 \sigma^2 \approx \frac{\sum f_i m_i^2}{\sum f_i} - \bar{x}^2 σ 2 ≈ ∑ f i ​ ∑ f i ​ m i 2 ​ ​ − x ˉ 2 .

  • 5. Quartiles, Percentiles & Outlier Detection
  • Quartiles

First Quartile ( Q 1 Q_1 Q 1 ​ / 25th Percentile): Median of the lower half of data; 25% of observations fall below Q 1 Q_1 Q 1 ​ .

Second Quartile ( Q 2 Q_2 Q 2 ​ / 50th Percentile): The overall median Med \text{Med} Med .

Third Quartile ( Q 3 Q_3 Q 3 ​ / 75th Percentile): Median of the upper half of data; 75% of observations fall below Q 3 Q_3 Q 3 ​ .

Interquartile Range (IQR) IQR = Q 3 − Q 1 \text{IQR} = Q_3 - Q_1 IQR = Q 3 ​ − Q 1 ​

The IQR spans the middle 50% of observations and provides an outlier-resistant measure of dispersion.

Tukey's 1.5 × \times × IQR Outlier Detection Rule

In boxplot analysis, fences identify anomalous observations:

Lower Outlier Fence: LF = Q 1 − 1.5 ⋅ IQR \text{LF} = Q_1 - 1.5 \cdot \text{IQR} LF = Q 1 ​ − 1.5 ⋅ IQR

Upper Outlier Fence: UF = Q 3 + 1.5 ⋅ IQR \text{UF} = Q_3 + 1.5 \cdot \text{IQR} UF = Q 3 ​ + 1.5 ⋅ IQR Any data point x < LF x < \text{LF} x < LF or x > UF x > \text{UF} x > UF is classified as an outlier .

6. Common Bocconi Traps & Fast Shortcuts

Averaging Averages Without Weights: Never compute x ˉ 1 + x ˉ 2 2 \frac{\bar{x}_1 + \bar{x}_2}{2} 2 x ˉ 1 ​ + x ˉ 2 ​ ​ when combining classes of different sizes. Always multiply each mean by its cohort size, sum the totals, and divide by the combined total n n n .

The Negative Standard Deviation Trap: When transforming y = − 3 x + 10 y = -3x + 10 y = − 3 x + 10 , candidate answers frequently state σ y = − 3 σ x \sigma_y = -3\sigma_x σ y ​ = − 3 σ x ​ . Standard deviation is always non-negative : σ y = ∣ − 3 ∣ σ x = 3 σ x \sigma_y = |-3|\sigma_x = 3\sigma_x σ y ​ = ∣ − 3∣ σ x ​ = 3 σ x ​ .

Assuming Shift Alters Spread: Adding a flat bonus of 10 points to every student's score increases the mean by 10 points, but changes the variance and standard deviation by exactly zero .

Failure to Use the Computational Shortcut: On discrete sets like { 1 , 3 , 5 , 7 , 9 } \{1, 3, 5, 7, 9\} { 1 , 3 , 5 , 7 , 9 } , do not compute ( − 4 ) 2 + ( − 2 ) 2 + … (-4)^2 + (-2)^2 + \dots ( − 4 ) 2 + ( − 2 ) 2 + … . Directly evaluate 1 + 9 + 25 + 49 + 81 5 − 5 2 = 165 5 − 25 = 33 − 25 = 8 \frac{1 + 9 + 25 + 49 + 81}{5} - 5^2 = \frac{165}{5} - 25 = 33 - 25 = 8 5 1 + 9 + 25 + 49 + 81 ​ − 5 2 = 5 165 ​ − 25 = 33 − 25 = 8 .

  • 7. Worked Step-by-Step Examples
  • Example 1: Multi-Cohort Combined Average

In a business analytics department, Section 1 has 25 students with an average exam grade of 80, Section 2 has 35 students with an average of 88, and Section 3 has 40 students with an average of 75. What is the combined weighted average of all 100 students?

Calculate Total Score Points per Section:

  • Section 1: 25 × 80 = 2000 25 \times 80 = 2000 25 × 80 = 2000
  • Section 2: 35 × 88 = 3080 35 \times 88 = 3080 35 × 88 = 3080
  • Section 3: 40 × 75 = 3000 40 \times 75 = 3000 40 × 75 = 3000

Sum All Points and Total Sample Size: Total Points = 2000 + 3080 + 3000 = 8080 \text{Total Points} = 2000 + 3080 + 3000 = 8080 Total Points = 2000 + 3080 + 3000 = 8080 N = 25 + 35 + 40 = 100 N = 25 + 35 + 40 = 100 N = 25 + 35 + 40 = 100

Compute Weighted Average: x ˉ comb = 8080 100 = 80.8 \bar{x}_{\text{comb}} = \frac{8080}{100} = 80.8 x ˉ comb ​ = 100 8080 ​ = 80.8

Example 2: Fast Variance Evaluation Using Shortcut Formula

Compute the population variance σ 2 \sigma^2 σ 2 and standard deviation σ \sigma σ for the dataset S = { 2 , 4 , 6 , 8 , 10 } S = \{2, 4, 6, 8, 10\} S = { 2 , 4 , 6 , 8 , 10 } .

Compute Arithmetic Mean: μ = 2 + 4 + 6 + 8 + 10 5 = 30 5 = 6 \mu = \frac{2 + 4 + 6 + 8 + 10}{5} = \frac{30}{5} = 6 μ = 5 2 + 4 + 6 + 8 + 10 ​ = 5 30 ​ = 6

Compute Sum of Squares: ∑ x i 2 = 2 2 + 4 2 + 6 2 + 8 2 + 10 2 = 4 + 16 + 36 + 64 + 100 = 220 \sum x_i^2 = 2^2 + 4^2 + 6^2 + 8^2 + 10^2 = 4 + 16 + 36 + 64 + 100 = 220 ∑ x i 2 ​ = 2 2 + 4 2 + 6 2 + 8 2 + 1 0 2 = 4 + 16 + 36 + 64 + 100 = 220

Apply Computational Variance Identity: σ 2 = ∑ x i 2 n − μ 2 = 220 5 − 6 2 = 44 − 36 = 8 \sigma^2 = \frac{\sum x_i^2}{n} - \mu^2 = \frac{220}{5} - 6^2 = 44 - 36 = 8 σ 2 = n ∑ x i 2 ​ ​ − μ 2 = 5 220 ​ − 6 2 = 44 − 36 = 8

Compute Standard Deviation: σ = 8 = 2 2 ≈ 2.828 \sigma = \sqrt{8} = 2\sqrt{2} \approx 2.828 σ = 8 ​ = 2 2 ​ ≈ 2.828

Example 3: Comprehensive Linear Transformation

A distribution of raw employee productivity scores x x x has mean μ = 50 \mu = 50 μ = 50 , median Med = 48 \text{Med} = 48 Med = 48 , variance σ 2 = 16 \sigma^2 = 16 σ 2 = 16 , and standard deviation σ = 4 \sigma = 4 σ = 4 . If scores are converted via y = − 2 x + 15 y = -2x + 15 y = − 2 x + 15 , find the new statistical metrics.

Transformed Mean: μ y = − 2 ( 50 ) + 15 = − 100 + 15 = − 85 \mu_y = -2(50) + 15 = -100 + 15 = -85 μ y ​ = − 2 ( 50 ) + 15 = − 100 + 15 = − 85 .

Transformed Median: Med y = − 2 ( 48 ) + 15 = − 96 + 15 = − 81 \text{Med}_y = -2(48) + 15 = -96 + 15 = -81 Med y ​ = − 2 ( 48 ) + 15 = − 96 + 15 = − 81 .

Transformed Variance: σ y 2 = ( − 2 ) 2 ⋅ σ x 2 = 4 × 16 = 64 \sigma_y^2 = (-2)^2 \cdot \sigma_x^2 = 4 \times 16 = 64 σ y 2 ​ = ( − 2 ) 2 ⋅ σ x 2 ​ = 4 × 16 = 64 .

Transformed Standard Deviation: σ y = ∣ − 2 ∣ ⋅ σ x = 2 × 4 = 8 \sigma_y = |-2| \cdot \sigma_x = 2 \times 4 = 8 σ y ​ = ∣ − 2∣ ⋅ σ x ​ = 2 × 4 = 8 .

Loading diagram... Linear Transformation Impact on Location vs. Dispersion