Normal distribution

Q: What is the probability of a continuous random variable taking an exact single value, and what does this imply for inequalities?

For any continuous random variable, \(P(X = a) = 0\), which means strict and non-strict inequalities have identical probabilities (e.g. \(P(X

Q: What parameters define a normal distribution, and what notation is used to represent it?

A normal distribution is defined by its mean \(\mu\) and variance \(\sigma^2\), written as \(X \sim \text{N}(\mu, \sigma^2)\).

Q: What are the key visual and geometric properties of a normal distribution curve?

The curve is bell-shaped and symmetrical about \(x = \mu\) (where \(\text{mean} = \text{median} = \text{mode}\)), has a total area of \(1\) under the curve, and has tails asymptotic to the horizontal axis.

Q: What is the standard normal distribution and what formula is used to standardise a variable \(X\)?

The standard normal distribution is \(Z \sim \text{N}(0, 1)\), and values are converted using \(Z = \frac{X - \mu}{\sigma}\).

Q: What does the cumulative standard normal distribution function \(\Phi(z)\) represent?

\(\Phi(z) = P(Z \le z)\) for \(z \ge 0\), which gives the area under the standard normal curve to the left of \(z\).

Q: How do you calculate the probability that a normal random variable lies between two values, \(P(a \le X \le b)\)?

Standardise both boundaries to \(z_1\) and \(z_2\), then calculate \(P(z_1 \le Z \le z_2) = \Phi(z_2) - \Phi(z_1)\).

Q: How do you solve an inverse normal problem to find an unknown boundary value \(k\) when given a probability?

Use the statistical table in reverse to find the corresponding \(Z\)-score (including its correct sign), then use \(k = \mu + Z\sigma\).

Q: How do you calculate the expected frequency of items falling into a specific range from a sample of size \(n\)?

\(\text{Expected Frequency} = n \times P(\text{Event})\).

Q: How do you find unknown parameters \(\mu\) or \(\sigma\) from given probabilities?

Look up the \(Z\)-score from the given probability, substitute \(Z\), \(X\), and known values into \(Z = \frac{X - \mu}{\sigma}\), and solve for the unknown parameter (or solve simultaneous equations if both are unknown).

Further Mathematics 2330 · CCEA GCSE · 7 min read · Updated: 31 Aug 2026

Welcome to the Normal Distribution

Have you ever wondered why human heights, test scores, shoe sizes, or the weights of bags of crisps all seem to cluster around an average value, with fewer and fewer extreme values on either side? In statistics, this natural pattern is modelled by the Normal Distribution.

The normal distribution is one of the most important topics in CCEA GCSE Further Mathematics (Unit 3: Statistics). Don't worry if this topic looks intimidating with all its symbols and tables—once you master a few straightforward rules and a single formula, you will be able to solve these exam questions with confidence!

---

1. Discrete vs Continuous Random Variables

Before we dive into the curve itself, let's understand what kind of data the normal distribution models:

Discrete variables: Things you count in distinct steps (like rolling a die or counting goals in a match).
Continuous variables (\(X\)): Things you measure on a continuous scale (like height, weight, time, or temperature).

The Single Value Rule for Continuous Distributions

Because continuous data can take any infinite real value (for example, a height of exactly \(172.48392\dots\text{ cm}\)), the probability of a continuous variable taking an exact single value is always zero:

\(P(X = a) = 0\)

Because of this, strict inequalities (\(<\), \(>\)) and non-strict inequalities (\(\le\), \(\ge\)) mean the exact same thing in calculations:

\(P(X < a) = P(X \le a)\)

\(P(X > a) = P(X \ge a)\)

Key Takeaway: You don't need to worry about whether an inequality sign has an "or equal to" line underneath it!

---

2. Key Properties of the Normal Distribution

A normal distribution is defined entirely by two parameters:

Population Mean (\(\mu\)): The central average of the distribution.
Population Standard Deviation (\(\sigma\)) or Variance (\(\sigma^2\)): The measure of how spread out the data is.

We write this in statistical notation as:

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

(Read as: "The random variable \(X\) is normally distributed with mean \(\mu\) and variance \(\sigma^2\)")

Visual Properties of the Normal Curve

Symmetrical & Bell-Shaped: The curve is completely symmetrical about the vertical line \(x = \mu\).
Mean = Median = Mode: All three measures of central tendency sit right at the central peak.
Total Area Under the Curve is \(1\): The entire area represents \(100\%\) probability (\(\text{Total Area} = 1\)). Exactly \(0.5\) (\(50\%\)) lies to the left of the mean, and \(0.5\) lies to the right.
Asymptotic Tails: The curve extends forever in both directions (\(x \to \pm\infty\)), approaching the horizontal axis without ever touching it.

---

3. Standardisation and the Standard Normal Distribution

Every normal distribution has its own specific mean and spread. To avoid needing an infinite number of tables, we convert our variable \(X\) into the Standard Normal variable (\(Z\)).

The standard normal distribution is denoted by:

\(Z \sim \text{N}(0, 1)\)

where the mean \(\mu = 0\) and standard deviation \(\sigma = 1\).

The Standardisation Formula

To convert any value \(X\) into a \(Z\)-score, use:

\(Z = \frac{X - \mu}{\sigma}\)

What does \(Z\) mean? A \(Z\)-score simply tells you how many standard deviations a value \(X\) lies above or below the mean.

If \(X > \mu\), then \(Z\) is positive (above the average).
If \(X < \mu\), then \(Z\) is negative (below the average).
If \(X = \mu\), then \(Z = 0\).

---

4. Reading CCEA Statistical Tables: The \(\Phi(z)\) Function

In your CCEA exam formula booklet, you are provided with the cumulative standard normal distribution table, written as \(\Phi(z)\) (pronounced "phi of z").

\(\Phi(z) = P(Z \le z) \quad \text{for } z \ge 0\)

This table gives the area under the curve to the left of a positive value \(z\).

The Four Essential Table Rules

Rule 1: Standard "Less Than" (\(z > 0\))

\(P(Z \le z) = \Phi(z)\)

Rule 2: "Greater Than" / Upper Tail (\(z > 0\))

Since the total area is \(1\), subtract the area to the left from \(1\):

\(P(Z > z) = 1 - \Phi(z)\)

Rule 3: Negative \(z\)-values (Symmetry Rules)

Because the curve is symmetrical:

\(P(Z < -z) = P(Z > z) = 1 - \Phi(z)\)

\(P(Z > -z) = \Phi(z)\)

Rule 4: Probability Between Two Values (\(a \le X \le b\))

Convert both boundaries to \(Z\)-scores (\(z_1\) and \(z_2\)), then subtract the smaller cumulative probability from the larger one:

\(P(a \le X \le b) = P(z_1 \le Z \le z_2) = \Phi(z_2) - \Phi(z_1)\)

Key Takeaway: Sketching a quick bell curve and shading the area you need will prevent almost every tail error!

---

5. Step-by-Step Worked Examples

Example 1: Basic Probability & Upper Tail

The weights of chocolate bars produced by a machine are normally distributed with a mean of \(50\text{ g}\) and a standard deviation of \(2\text{ g}\).
Find the probability that a randomly chosen bar weighs more than \(53.4\text{ g}\).

Solution:

Step 1: Identify parameters
\(X \sim \text{N}(50, 2^2)\), so \(\mu = 50\) and \(\sigma = 2\).

Step 2: Standardise
\(Z = \frac{53.4 - 50}{2} = \frac{3.4}{2} = 1.70\)

Step 3: Apply the tail rule
\(P(X > 53.4) = P(Z > 1.70) = 1 - \Phi(1.70)\)

Step 4: Look up \(\Phi(1.70)\) in the tables
From the statistical tables, \(\Phi(1.70) = 0.9554\).
\(P(X > 53.4) = 1 - 0.9554 = 0.0446\)

Example 2: Between Two Values & Negative \(z\)-score

Using the same distribution \(X \sim \text{N}(50, 2^2)\), find the probability that a bar weighs between \(46.8\text{ g}\) and \(52.6\text{ g}\).

Solution:

Step 1: Standardise both values
\(z_1 = \frac{46.8 - 50}{2} = \frac{-3.2}{2} = -1.60\)
\(z_2 = \frac{52.6 - 50}{2} = \frac{2.6}{2} = 1.30\)

Step 2: Write the probability statement
\(P(46.8 \le X \le 52.6) = P(-1.60 \le Z \le 1.30) = \Phi(1.30) - \Phi(-1.60)\)

Step 3: Apply symmetry for the negative \(z\)-value
\(\Phi(-1.60) = 1 - \Phi(1.60)\)
Therefore:
\(P(-1.60 \le Z \le 1.30) = \Phi(1.30) - [1 - \Phi(1.60)] = \Phi(1.30) + \Phi(1.60) - 1\)

Step 4: Read table values and calculate
\(\Phi(1.30) = 0.9032\)
\(\Phi(1.60) = 0.9452\)
\(\text{Probability} = 0.9032 + 0.9452 - 1 = 0.8484\)

Example 3: Inverse Normal (Finding an Unknown \(x\))

A factory packages cereal boxes where \(X \sim \text{N}(500, 15^2)\). The lightest \(5\%\) of boxes are rejected for being underweight. Find the cut-off weight \(k\) below which a box is rejected.

Solution:

Step 1: Write the probability equation
\(P(X < k) = 0.05\)

Step 2: Relate to standard normal \(Z\)
Because the probability is less than \(0.5\), \(k\) lies below the mean, so \(z\) must be negative.
\(P(Z < -z) = 0.05 \implies 1 - \Phi(z) = 0.05 \implies \Phi(z) = 0.9500\)

Step 3: Find \(z\) in the tables
Looking up \(0.9500\) in the tables gives \(z \approx 1.645\).
Therefore, our actual \(Z\)-score is \(-1.645\).

Step 4: Rearrange the standardisation formula
\(Z = \frac{k - \mu}{\sigma} \implies k = \mu + Z\sigma\)
\(k = 500 + (-1.645)(15) = 500 - 24.675 = 475.33\text{ g}\) (to 2 d.p.)

Example 4: Expected Frequency

A sample of \(400\) cereal boxes is inspected from Example 3. How many boxes would you expect to be rejected?

Solution:

\(\text{Expected Frequency} = n \times P(\text{Event})\)

\(\text{Expected Frequency} = 400 \times 0.05 = 20\text{ boxes}\)

---

6. Finding Unknown Parameters (\(\mu\) or \(\sigma\))

Sometimes the exam will give you probabilities and ask you to find the unknown mean (\(\mu\)) or standard deviation (\(\sigma\)).

Method:

Use the given probability to find the corresponding \(Z\)-score from the table. (Always check if it should be positive or negative!)
Substitute \(Z\), \(X\), and the known parameter into \(Z = \frac{X - \mu}{\sigma}\).
Solve the linear equation for the unknown parameter. (If both \(\mu\) and \(\sigma\) are unknown, set up two simultaneous equations).

---

7. Pitfalls & Examiner Tips

Variance vs Standard Deviation: In the notation \(X \sim \text{N}(\mu, \sigma^2)\), the second number is the variance. If a question states \(X \sim \text{N}(100, 25)\), remember that \(\sigma = \sqrt{25} = 5\). Always divide by \(\sigma\), not \(\sigma^2\)!
Minus Signs on \(Z\)-scores: If your value of \(X\) is below the mean \(\mu\), your \(Z\)-score must be negative. Forgetting the negative sign is one of the most common student mistakes.
Rounding \(Z\)-values: Round \(Z\) to 2 decimal places before looking it up in the standard normal table (unless using specific tabulated values like \(1.645\) or \(1.960\)). Rounding to only 1 decimal place will lose accuracy marks.
No Continuity Corrections: In GCSE Further Mathematics, when dealing with standard continuous normal distributions, do not apply continuity corrections (\(\pm 0.5\)). Simply standardise the given values directly.

---

8. Quick Revision Checklist

Standardisation Formula: \(Z = \frac{X - \mu}{\sigma}\)
Rearranged for \(X\): \(X = \mu + Z\sigma\)
Upper Tail: \(P(Z > z) = 1 - \Phi(z)\)
Lower Tail with negative value: \(P(Z < -z) = 1 - \Phi(z)\)
Interval: \(P(a \le X \le b) = \Phi(z_2) - \Phi(z_1)\)
Expected Frequency: \(n \times P(X \in \text{range})\)

Quick check

Can you answer these now?

Open each question to check the key ideas from this chapter.

What is the probability of a continuous random variable taking an exact single value, and what does this imply for inequalities?

For any continuous random variable, \(P(X = a) = 0\), which means strict and non-strict inequalities have identical probabilities (e.g. \(P(X < a) = P(X \le a)\)).

What parameters define a normal distribution, and what notation is used to represent it?

A normal distribution is defined by its mean \(\mu\) and variance \(\sigma^2\), written as \(X \sim \text{N}(\mu, \sigma^2)\).

What are the key visual and geometric properties of a normal distribution curve?

The curve is bell-shaped and symmetrical about \(x = \mu\) (where \(\text{mean} = \text{median} = \text{mode}\)), has a total area of \(1\) under the curve, and has tails asymptotic to the horizontal axis.

What is the standard normal distribution and what formula is used to standardise a variable \(X\)?

The standard normal distribution is \(Z \sim \text{N}(0, 1)\), and values are converted using \(Z = \frac{X - \mu}{\sigma}\).

What does the cumulative standard normal distribution function \(\Phi(z)\) represent?

\(\Phi(z) = P(Z \le z)\) for \(z \ge 0\), which gives the area under the standard normal curve to the left of \(z\).

How do you find the upper tail probability \(P(Z > z)\) and lower tail with a negative value \(P(Z < -z)\)?

\(P(Z > z) = 1 - \Phi(z)\) and \(P(Z < -z) = 1 - \Phi(z)\).

How do you calculate the probability that a normal random variable lies between two values, \(P(a \le X \le b)\)?

Standardise both boundaries to \(z_1\) and \(z_2\), then calculate \(P(z_1 \le Z \le z_2) = \Phi(z_2) - \Phi(z_1)\).

How do you solve an inverse normal problem to find an unknown boundary value \(k\) when given a probability?

Use the statistical table in reverse to find the corresponding \(Z\)-score (including its correct sign), then use \(k = \mu + Z\sigma\).

How do you calculate the expected frequency of items falling into a specific range from a sample of size \(n\)?

\(\text{Expected Frequency} = n \times P(\text{Event})\).

How do you find unknown parameters \(\mu\) or \(\sigma\) from given probabilities?

Look up the \(Z\)-score from the given probability, substitute \(Z\), \(X\), and known values into \(Z = \frac{X - \mu}{\sigma}\), and solve for the unknown parameter (or solve simultaneous equations if both are unknown).

Ready to test yourself?

Turn these notes into exam-style practice. Get unlimited AI questions on this topic with instant marking and explanations.

Practise This Topic

More Further Mathematics 2330 chapters

* The content provided by thinka is generated by AI and may not always be accurate or up-to-date. Please use it as a supplementary resource and verify with official materials.

Put These Notes into Practice

Reading the notes is a great start. Now practise with unlimited AI-generated questions and get instant feedback. 100,000+ students are already improving their grades.

Start Practising Now View Pricing

Done reading? Test yourself with AI practice questions

Practise This Topic Now