Normal Distribution — Mathematics Knowledge System

Overview

The normal (Gaussian) distribution is the iconic bell-shaped probability curve that appears throughout statistics, from measurement error to heights, test scores, and the distribution of sample means. Its ubiquity is not a coincidence — the Central Limit Theorem guarantees that averages of many independent random effects tend toward this exact shape, regardless of the underlying distribution.

Intuition

Imagine flipping many independent coins that each nudge a value slightly up or down — human height is influenced by hundreds of genes and environmental factors, each with a small independent effect. When you add up many small, independent random nudges, the sum reliably piles up into the same bell shape, no matter what the individual nudges looked like. That's the deep reason the normal distribution shows up everywhere: it's the universal 'shape of accumulated randomness'.

Interactive Graph

Formal Definition

Definition

The probability density function of a normal distribution with mean μ and standard deviation σ:

f(x) = \frac{1}{\sigma\sqrt{2\pi}} e^{-\frac{(x-\mu)^2}{2\sigma^2}}

Gaussian PDF

X \sim \mathcal{N}(\mu, \sigma^2)

Standard notation: X is normally distributed with mean μ, variance σ²

Notation

Notation	Meaning
$\mu$	Mean — the center of the distribution
$\sigma$	Standard deviation — spread of the distribution
$\sigma^2$	Variance
$Z = \frac{X-\mu}{\sigma}$	Z-score — standardizes X to the standard normal N(0,1)

Properties

68-95-99.7 rule

\text{About 68\% of values lie within } 1\sigma \text{ of } \mu \text{, 95\% within } 2\sigma \text{, 99.7\% within } 3\sigma.

Symmetry

\text{The distribution is symmetric about } \mu \text{, so mean = median = mode.}

Theorems

Theorem 1: Central Limit Theorem

\text{The sample mean of } n \text{ i.i.d. random variables approaches a normal distribution as } n \to \infty, \text{ regardless of the population's original distribution.}

Applications

Statistical process control charts assume measurement error is normally distributed to detect manufacturing defects.

Worked Examples

σ = √100 = 10. Apply the z-score formula.
$z = \frac{190 - 170}{10} = 2$

Answer: z = 2, meaning 190cm is 2 standard deviations above the mean.

Practice Problems

Difficulty 5/10

Using the 68-95-99.7 rule, what percentage of a normal distribution lies within 2 standard deviations of the mean?

Difficulty 6/10

Concrete cube crushing strengths are normally distributed with mean μ = 32 MPa and standard deviation σ = 4 MPa. A structure specifies a characteristic strength of 25 MPa. What fraction of cubes fall BELOW the specified strength?

Difficulty 6/10

Vehicle speeds on a highway are normal with mean 100 km/h and σ = 12 km/h. Traffic engineers set the speed limit at the 85th-percentile speed. What limit does that give?

Difficulty 7/10

A steel member's capacity R is normal (μ_R = 250 kN, σ_R = 20 kN) and the applied load S is fixed at 200 kN. Treating R − S, what is the probability of failure P(R < 200)?

Common Mistakes

Common Mistake

Assuming every real-world dataset is normally distributed without checking.

Many phenomena are skewed, bounded, or multi-modal (income distribution, reaction times). The Central Limit Theorem justifies normality for SAMPLE MEANS of large samples, not for raw individual data in general.

Quiz

Flashcards

1 / 2

Historical Background

Abraham de Moivre first derived the normal distribution in 1733 as an approximation to the binomial distribution for large sample sizes. Carl Friedrich Gauss independently developed it in 1809 while analyzing astronomical measurement errors, and it's his name (Gaussian) that's most commonly attached to it. Pierre-Simon Laplace proved the general Central Limit Theorem in 1810, explaining WHY this particular curve shows up so often across unrelated phenomena.

1733
De Moivre derives the normal curve as a binomial approximation
Abraham de Moivre
1809
Gauss applies it to astronomical measurement error
Carl Friedrich Gauss
1810
Laplace proves the general Central Limit Theorem
Pierre-Simon Laplace

Summary

The normal distribution is the symmetric bell-shaped curve N(μ, σ²).
68-95-99.7 rule: roughly 68/95/99.7% of data falls within 1/2/3 standard deviations of the mean.
Central Limit Theorem explains its ubiquity: sums/averages of independent random effects tend toward normal.
Z-scores standardize any normal variable to the standard normal N(0,1) for comparison.
Foundation of statistical process control, portfolio theory, and Gaussian-noise ML models.

References

WebsiteWikipedia — Normal distribution