The Normal distribution
S1 Topic 6, spec point by spec point (The Normal distribution). Each spec point has the method, worked examples written the way the mark scheme wants them, how the marks go and the mistakes that cost the most marks.
Spec6.1The Normal distribution
Know the shape and symmetry of the Normal distribution, and use tables of its cumulative distribution function to find probabilities and unknown values, including \(\mu\) and \(\sigma\) by simultaneous equations. (The specification prints this as "5.1" under Topic 6, and the question bank files these questions under S2.3.2.)
The shape
\(X \sim N(\mu, \sigma^2)\) means \(X\) is Normal with mean \(\mu\) and variance \(\sigma^2\) (standard deviation \(\sigma\)).
- Bell-shaped, symmetrical about \(\mu\) (mean = median = mode).
- About 68% of values lie within \(1\sigma\) of the mean, 95% within \(2\sigma\), and almost all (99.7%) within \(3\sigma\).
- It models continuous data that cluster symmetrically around a central value (heights, masses, errors).
- Points of inflection at \(\mu \pm \sigma\).
Standardising
Every Normal distribution is a stretched and shifted copy of the standard Normal \(Z \sim N(0, 1)\):
\[Z = \frac{X - \mu}{\sigma}\]
\(z\) counts how many standard deviations \(x\) is from the mean. The table gives \(\Phi(z) = P(Z < z)\) for \(z \geqslant 0\). Use symmetry for the rest:
- \(P(Z > z) = 1 - \Phi(z)\)
- \(P(Z < -z) = 1 - \Phi(z)\)
- \(P(a < Z < b) = \Phi(b) - \Phi(a)\)
Always sketch the curve and shade the region.
Working backwards
Given a probability, use the percentage points table (or the \(\Phi\) table backwards) to find \(z\), then \(x = \mu + z\sigma\). With two unknowns \(\mu\) and \(\sigma\), two probabilities give two equations: solve simultaneously.
probabilities
\(X \sim N(50, 4^2)\). Find \(P(X < 56)\) and \(P(46 < X < 56)\).
\(P(X < 56) = P(Z < 1.5) = 0.9332\).
\(P(46 < X < 56) = \Phi(1.5) - \Phi(-1) = 0.9332 - (1 - 0.8413) = 0.7745\).
an inverse value
For the same \(X\), find \(a\) such that \(P(X > a) = 0.05\).
\(\frac{a - 50}{4} = 1.6449\), so \(a = 56.6\).
finding μ and σ
\(P(X < 20) = 0.1\) and \(P(X > 35) = 0.2\). Find \(\mu\) and \(\sigma\).
\(\dfrac{20 - \mu}{\sigma} = -1.2816\) and \(\dfrac{35 - \mu}{\sigma} = 0.8416\).
Subtract: \(\dfrac{15}{\sigma} = 2.1232\), so \(\sigma = 7.06\) and \(\mu = 20 + 1.2816 \times 7.06 = 29.1\).
- M1 for standardising with \(\pm\), A1 for the \(z\) value, A1 for the probability to 4 d.p. from tables.
- Inverse: M1 for \(\frac{x - \mu}{\sigma} = z\) with a \(z\) value from tables (B1 for the \(z\)), A1.
- Two unknowns: M1 M1 for both equations with correct signs, M1 for solving, A1 A1.
- Is it Normal? Reasons against: "skewed", "discrete data", values that can't be negative near the mean (WST01A Jan 2026 Q2d).
Often asked as: probabilities in context; the value exceeded by 5%; find \(\mu\) or \(\sigma\) or both; conditional probabilities like \(P(X > 60 \mid X > 55)\).
Using the variance instead of the standard deviation in \(Z\).
A wrong sign for a \(z\) value below the mean.
Not sketching, so taking \(\Phi\) instead of \(1 - \Phi\).