Mathematical Methods · Unit 4 · Topic 3

Continuous random variables and the normal distribution

Model measured quantities with continuous random variables, find probabilities as areas with integrals, calculate the mean, variance and standard deviation from a probability density function, and solve problems with the normal distribution, with and without technology.

  • 8 lessons
  • 2 h 19 min of lessons
  • 15 worked examples
  • 12 hours in the syllabus
0 of 8

Start here

From histograms to probability density

Lesson 1 of 8 · 14 min

Start the topic

Lessons

8
  1. From histograms to probability density (up next)

    Estimate probabilities for a measured quantity from relative frequencies and density histograms, and see why probability becomes area for a continuous random variable.

  2. Probability density functions

    Check that a function is a probability density function, find an unknown constant, and calculate probabilities as areas with definite integrals, including for the continuous uniform distribution.

  3. Cumulative distribution functions and the median

    Build the cumulative distribution function F(x)=P(X≤x)F(x) = P(X \le x) from a density, use it to find probabilities, and solve F(m)=0.5F(m) = 0.5 for the median and other quantiles.

  4. Expected value of a continuous random variable

    Calculate the mean E⁡(X)\E(X) of a continuous random variable by integrating x p(x)x\,p(x), use symmetry as a shortcut, and interpret the mean as the balance point of the density.

  5. Variance and standard deviation

    Measure the spread of a continuous random variable with Var⁡(X)\Var(X) and σ\sigma, using the definition or the quicker form E⁡(X2)−μ2\E(X^2) - \mu^2, and interpret the result.

  6. The normal distribution

    Recognise contexts that suit a normal model, describe the features of the bell curve and the notation X∼N(μ,σ2)X \sim N(\mu, \sigma^2), and find normal probabilities with the 68–95–99.7% rule and with technology.

  7. Standardising and z-scores

    Convert values to z-scores and back, use the standard normal distribution and its symmetry, and compare results that come from different distributions.

  8. Quantiles and modelling with the normal distribution

    Use the inverse normal to find quantiles and cut-off values, find an unknown mean or standard deviation from given probabilities, and solve multi-step modelling problems with normal distributions.

  9. Topic quiz

    Ten questions across the topic, from foundation to complex unfamiliar. Your results feed your mastery.

About this topic

How long will a phone battery last? How tall is the next person through the door? How many millilitres of soft drink are really in a "375 mL" can? Each answer is a measurement, not a count, so it can be any value in an interval. A continuous random variable describes quantities like these. Because there are infinitely many possible values, the probability of any single exact value is zero, and probability comes from area instead: the area under a curve called the probability density function.

You start from histograms of real data and see how the bars smooth into a density curve. Then you use integration from Unit 4 Topic 1 to check that a function is a valid density, to find probabilities, to build the cumulative distribution function and to calculate the expected value, variance and standard deviation. The second half of the topic is about the most important continuous distribution of all, the normal distribution X∼N(μ,σ2)X \sim N(\mu, \sigma^2): its bell-shaped graph, standardising with zz-scores, the 68–95–99.7% rule for working without technology, and calculator probabilities and quantiles for modelling real problems. Everything here feeds directly into sampling and confidence intervals in Topics 4 and 5.

Before you start

Builds on Discrete random variables, Further integration and Introduction to integration.

  • Discrete random variables, expected value and variance from Unit 3 Topic 5.
  • Definite integrals, the fundamental theorem of calculus and areas under curves from Unit 4 Topic 1.
  • Antiderivatives of polynomials, exponentials and sin⁡\sin and cos⁡\cos.
  • Histograms, mean and standard deviation of a data set (Years 9–10).
  • Conditional probability P(A∣B)=P(A∩B)P(B)P(A \mid B) = \dfrac{P(A \cap B)}{P(B)} from Unit 1.

What QCAA says you need to know10 dot points

General continuous random variables

6 hours

Normal distributions

6 hours

Subject matter from the Mathematical Methods General senior syllabus 2025 v1.3 (opens in a new tab), CC BY 4.0 © State of Queensland (QCAA).

The focus areas you can practise on their own. Each one maps to dot points above.

  • Probabilities from histograms

    Turn grouped data into relative frequencies and density histograms, and use areas of bars to estimate probabilities for a continuous variable.

    Practise
  • Valid probability density functions

    Check that a function is a probability density function (never negative, total area 1) and find an unknown constant.

    Practise
  • Probabilities as integrals

    Find P(a < X < b) as the area under a probability density function, by integration or geometry, including uniform and other simple models.

    Practise
  • Cumulative distribution functions

    Build F(x) = P(X ≤ x) from a density, use it for probabilities, and find the median and other quantiles.

    Practise
  • Expected value

    Calculate E(X) for a continuous random variable by integration and interpret it as the balance point of the density.

    Practise
  • Variance and standard deviation

    Calculate Var(X) and the standard deviation of a continuous random variable, using the definition or E(X²) − μ².

    Practise
  • Features of the normal distribution

    Recognise contexts suited to a normal model, describe the bell curve and how μ and σ change it, and read the notation X ∼ N(μ, σ²).

    Practise
  • Standardising with z-scores

    Convert values to z-scores and back, use the standard normal distribution, and compare results from different distributions.

    Practise
  • Normal probabilities

    Calculate normal probabilities with a calculator, and without one using symmetry and the 68–95–99.7% rule.

    Practise
  • Quantiles and unknown parameters

    Use the inverse normal to find a value with a given probability, and find an unknown mean or standard deviation from given probabilities.

    Practise
  • Modelling with normal distributions

    Solve multi-step problems with normal models, including conditional probabilities and binomial counts, and judge whether a normal model is reasonable.

    Practise

Worked examples15

All 15

Common mistakes

Reading the height of a density as a probability

p(3)=0.4p(3) = 0.4 does not mean P(X=3)=0.4P(X = 3) = 0.4. For a continuous random variable P(X=3)=0P(X = 3) = 0; probabilities are areas, so integrate over an interval.

Forgetting the density is zero outside its interval

If p(x)=38x2p(x) = \frac{3}{8}x^2 for 0≤x≤20 \le x \le 2, then P(X>1)=∫1238x2 dxP(X > 1) = \int_1^2 \frac{3}{8}x^2\,dx, not ∫1∞\int_1^{\infty} of the formula. Split any interval at the ends of the support.

Writing the standard deviation in N(μ,σ2)N(\mu, \sigma^2)

X∼N(50,16)X \sim N(50, 16) has variance 16 and standard deviation 16=4\sqrt{16} = 4. Calculators ask for σ\sigma, so enter 4, not 16.

Squaring in the wrong place in E⁡(X2)−μ2\E(X^2) - \mu^2

E⁡(X2)=∫x2p(x) dx\E(X^2) = \int x^2 p(x)\,dx squares xx inside the integral. It is not (E⁡(X))2(\E(X))^2, and Var⁡(X)\Var(X) is never negative: if you get a negative variance, look here first.

Giving the variance when the standard deviation is asked for

The standard deviation is Var⁡(X)\sqrt{\Var(X)}, in the same units as XX. Read which one the question wants.

Using the wrong tail

"More than", "at least" and "exceeds" are upper tails. Sketch the bell curve and shade the region before you calculate, then check the answer is above or below 0.5 as the sketch says.

Mixing up the inverse normal tail

Most calculators' inverse normal works with the area to the left. For "the top 10%" enter 0.9 (or set the tail to right), not 0.1.

Treating z-scores as probabilities

A zz-score is a number of standard deviations, which can be negative or bigger than 1. Convert it to a probability with technology or the 68–95–99.7% rule.

Exam tips

  1. Define the random variable and its distribution in words and symbols: "Let XX be the mass of a bag in grams, X∼N(500,42)X \sim N(500, 4^2)."

  2. Write the probability statement you want, such as P(X>506)P(X > 506), then the calculator input in mathematical notation (μ=500\mu = 500, σ=4\sigma = 4, lower bound 506). Markers do not accept calculator syntax alone.

  3. For a pdf with an unknown constant, show ∫p(x) dx=1\int p(x)\,dx = 1 with the limits and the antiderivative before you solve for kk.

  4. On Paper 1 (technology-free), normal questions use the 68–95–99.7% rule, symmetry and given probabilities. Look for values that are a whole number of standard deviations from the mean.

  5. Give probabilities to 4 decimal places on Paper 2 unless told otherwise, and keep unrounded values in your calculator between steps.

  6. Sketch a bell curve with μ\mu and the value marked for every normal question. It catches wrong-tail errors and earns method marks in worked responses.

  7. To find an unknown μ\mu or σ\sigma, convert each given probability to a zz-score with the inverse normal, write z=x−μσz = \frac{x - \mu}{\sigma}, and solve the equations simultaneously.

  8. Check reasonableness: a probability lies between 0 and 1, the mean of a pdf lies inside its support, and a value above the mean has a positive zz-score.

Where this shows up

  • Manufacturing: fill volumes, component lengths and masses vary normally around a target, and machines are set so that only a small proportion falls outside the tolerance.

  • Health: birth weights, heights and blood pressure are compared with population norms using zz-scores and percentiles.

  • Education: standardised scores let results from different tests be compared fairly, as in scaling and ranking.

  • Reliability engineering: the lifetime of a light globe or battery is modelled with a density such as p(t)=λe−λtp(t) = \lambda e^{-\lambda t}, and warranties are set from the cumulative distribution function.

  • Measurement science: repeated measurements scatter normally about the true value, which is the basis of uncertainty in physics and chemistry.

  • Finance and insurance: the spread of returns or claim sizes is summarised by a mean and standard deviation, and tail probabilities measure risk.

Save your progress with a free account