Home » All A Level Maths Topics » The Normal Distribution

A Level Maths: The Normal Distribution Topic Summary and Resources

Year 2 · Stats

Exam Questions

Past-paper-style questions organised by topic, with full mark schemes.

Drawn from OCR and Edexcel past papers but designed to be useful for students of all UK exam boards — including AQA and OCR MEI — unless a sheet is explicitly board-specific.

Before You Start This Topic

It will help if you are confident with the following:

A Level Maths the normal distribution is the workhorse continuous distribution of Year 2 statistics. Many real-world quantities — heights, weights, exam marks, measurement errors — are approximately normally distributed, making this the most-used distribution in applied statistics. You learn to work with it, use it for probabilities, and test hypotheses about the mean.

The normal distribution $X \sim N(\mu, \sigma^2)$ has mean $\mu$ and variance $\sigma^2$ (so standard deviation $\sigma$). Its bell-shaped curve is symmetric about $\mu$. You use your calculator to find probabilities directly (the formula for the probability density function is not required). You also use the standard normal distribution $Z \sim N(0, 1)$, with $Z = \frac{X – \mu}{\sigma}$ (standardising), for working with normal tables when needed. The empirical rule — that approximately $68\%$ of values lie within one standard deviation of the mean, $95\%$ within two, and $99.7\%$ within three — gives quick sanity checks. You also apply a normal approximation to the binomial distribution $B(n, p)$ as $N(np, np(1-p))$ when $n$ is large and $p$ is moderate, and run hypothesis tests on the mean of a normally distributed population.

The normal distribution is part of the Statistics strand of A Level Maths for AQA, Edexcel, OCR, and OCR MEI students.

Watch out for…

A few things to be careful with: the distribution is specified by VARIANCE $\sigma^2$ in $N(\mu, \sigma^2)$, but your calculator usually wants STANDARD DEVIATION $\sigma$ — make sure you use the right input; $P(X = k) = 0$ for ANY specific value of a continuous random variable, so $P(X \le k)$ and $P(X < k)$ are equal (unlike for discrete variables); for the normal approximation to the binomial, a continuity correction (shifting by $\pm 0.5$) is often required; and the standard error of the sample mean is $\sigma/\sqrt{n}$, not just $\sigma$.