Probability Distribution, SPM Additional Mathematics (Form 5)

Probability Distribution sits in the Statistics learning area of the Form 5 Add Math syllabus. It takes the everyday idea of chance, whether it will rain, how many bulbs in a box are faulty, how tall a randomly chosen student is, and gives you a precise way to describe it.

Instead of looking at one outcome at a time, you describe the whole pattern of possible values together with their probabilities. That pattern is what we call a probability distribution.

The chapter has three content standards that build on one another. First you learn what a random variable is and how a discrete distribution is set out as a table or a graph.

Then you study the binomial distribution, the model for a fixed number of independent yes/no trials, which reuses the ${}^{n}C_{r}$ notation from Permutation and Combination. Finally you meet the normal distribution, the bell-shaped model for continuous measurements, and the standard score that turns any normal question into one you can read from a single table.

For many students this is one of the friendlier Form 5 chapters, because the working is systematic: identify the distribution, write down its parameters, substitute into a formula, then interpret the answer in context. The real skill is reading a wordy question carefully enough to choose the right model and the right inequality, and our teachers present it as a clear decision process rather than a bag of tricks.

These are the three DSKP content standards for the chapter, with what each one asks you to be able to do. The codes below are the official standard codes from the syllabus.

The three standards move from the general idea (a random variable and its distribution) to two named models you will use again and again, the binomial for counted successes and the normal for continuous measurements. When you revise, keep asking which of these three a given question belongs to; naming the standard first makes the method almost automatic.

1. A random variable turns outcomes into numbers

A random variable is a rule that assigns a number to each outcome of an experiment. We write it with a capital letter such as $X$, and a particular value it can take with a small letter, $x$.

For example, if $X$ is the number of heads in three coin tosses, then $X$ can be 0, 1, 2 or 3.

2. Discrete and continuous variables are not the same

A discrete random variable takes separate, countable values, such as the number of defective items in a sample. A continuous random variable can take any value in an interval, such as a mass between 40 kg and 60 kg.

Set-builder notation makes the difference clear: $X=\{x:x=0,1,2,3\}$ is discrete, while $X=\{x:x\text{ is a height in cm},\,150<x<180\}$ is continuous.

3. Every discrete distribution adds up to one

When you tabulate a discrete random variable, the probabilities of all its possible values must total exactly 1. This is your most useful check: build the table, add the probabilities, and if the sum is not 1 you have missed an outcome or made an arithmetic slip.

$$\sum P(X=x) = 1$$

4. The binomial distribution has four conditions

A situation is binomial only when all four conditions hold: there is a fixed number of trials $n$; each trial has just two outcomes, success or failure; the trials are independent; and the probability of success $p$ is constant from trial to trial. The probability of failure is $q=1-p$.

5. The binomial probability formula is given to you

$$P(X=r) = {}^{n}C_{r}\,p^{r}q^{\,n-r},\quad p+q=1$$

Here $n$ is the number of trials, $r$ the number of successes you want, $p$ the probability of success and $q$ the probability of failure. For phrases like 'at least two' you add the relevant terms, and for 'at most' it is often quickest to use $1$ minus the unwanted terms.

6. Know the mean and spread of a binomial from memory

$$\mu = np, \qquad \sigma^{2} = npq, \qquad \sigma = \sqrt{npq}$$

The mean $np$ is the number of successes you expect on average if the experiment were repeated many times. The variance is $npq$ and the standard deviation is its square root.

A common trap is to write $\sigma=npq$; the standard deviation is $\sqrt{npq}$.

7. The normal distribution models continuous data

The normal distribution is a continuous, bell-shaped curve that is symmetric about its mean $\mu$, with its spread controlled by the standard deviation $\sigma$. The total area under the curve is 1, and an area under the curve represents a probability.

Real measurements such as heights, masses and marks are often modelled this way.

8. Standardise with the Z score, then read the table

$$Z = \dfrac{X-\mu}{\sigma}$$

To find a normal probability you first convert the raw value $X$ into a standard score $Z$, which follows the standard normal distribution with mean 0 and standard deviation 1. You then read the required area from the standard normal distribution table.

Because the table gives one tail, a sketch of the bell curve keeps you clear on whether to add, subtract or use symmetry.

9. Read the table in both directions

Most questions give you a value and ask for a probability, but some give you a probability and ask for the value of $Z$ or of $X$. Being able to work backwards, from an area to a $Z$ score, then to $X$ using $X=\mu+Z\sigma$, is a skill the syllabus specifically expects, so practise it deliberately.

Add Math is assessed by two written papers, and Probability Distribution can appear in either. Because the topic supplies both quick technique questions and full application problems, you should be ready for it at every difficulty level.

Paper 1 (3472/1) lasts 2 hours and carries 80 marks. Section A has 12 questions worth 64 marks that you answer in full, and Section B has 3 questions worth 16 marks from which you choose 2.

Paper 1 items tend to be shorter and test a single skill cleanly, such as reading a probability from a distribution table or a one-step binomial calculation.

Paper 2 (3472/2) lasts 2 hours 30 minutes and carries 100 marks across three sections. Section A has 7 questions worth 50 marks that you answer in full, Section B has 4 questions worth 30 marks from which you choose 3, and Section C has 4 questions worth 20 marks from which you choose 2.

The longer questions you choose in Sections B and C give this chapter room to appear as a contextual problem, a quality-control sample, a set of exam marks, that you model first and calculate second.

In both papers the items are limited-response subjective questions marked by analytic scoring, so every correct step earns its method mark even if a later slip costs the final answer, which is exactly why we insist on full working. You may use a non-programmable scientific calculator.

The overall difficulty mix across the paper is Low : Medium : High = 5 : 3 : 2, so most marks reward careful standard method rather than unusual problem-solving.

These are the errors we correct most often when students first meet Probability Distribution.

1. Translating 'at least' and 'at most' into the wrong sum

'At least 2' means $P(X\ge 2)$ and 'at most 2' means $P(X\le 2)$, and the two need very different sums. Fix: write the inequality in symbols before you touch the calculator, and remember that $P(X\ge 1)=1-P(X=0)$ is usually the fastest route for 'at least one'.

2. Forgetting that $q=1-p$

Students sometimes substitute $p$ where $q$ belongs, so a probability of success of 0.3 is used as the failure probability too. Fix: write down both $p$ and $q=1-p$ at the very start, and check they add to 1 before substituting.

3. Confusing the binomial mean with the variance

It is easy to mix up $np$ and $npq$, or to write the standard deviation as $npq$ instead of $\sqrt{npq}$. Fix: label them clearly, mean $=np$, variance $=npq$, standard deviation $=\sqrt{npq}$, and take the square root last.

4. Reading the normal table without standardising

The standard normal table only works for $Z$, not for the raw value $X$. Fix: always compute $Z=\frac{X-\mu}{\sigma}$ first, then look up $Z$; never feed a value like 63 kg straight into the table.

5. Not using a sketch for 'greater than' areas

Because the table gives the area in one tail, students often forget to subtract from 1 for a 'greater than' probability, or to use symmetry for a negative $Z$. Fix: draw a quick bell curve, shade the region you want, and decide whether to add, subtract or reflect before you read any number.

6. Treating continuous data as if it were discrete

Applying the binomial formula to a continuous measurement, or trying to list separate probabilities for a continuous variable, leads nowhere. Fix: decide first whether the variable is countable (discrete, often binomial) or a measurement on a scale (continuous, often normal), and choose the model to match.

A reliable order of attack, each stage sets up the next, so resist skipping ahead. Most students who struggle here have not missed the concepts; they have skipped the repetition that makes choosing the right model automatic.

1. 1

   Sort the three models

   Make one summary page that names each distribution, discrete table, binomial, normal, with the situation it fits and the formula it needs. Knowing which model to reach for is half the marks.

2. 2

   Master the discrete table

   Build probability distribution tables until the $\sum P(X=x)=1$ check is automatic, and practise drawing the matching bar graph.

3. 3

   Drill the binomial

   Identify $n$, $p$ and $q$, translate the wording into the right inequality, then compute the probability and the mean, variance and standard deviation.

4. 4

   Get fluent with the Z table

   Standardise with $Z=\frac{X-\mu}{\sigma}$ and read the standard normal table in both directions, always with a shaded sketch to guide you.

5. 5

   Finish with full timed questions

   Work mixed, exam-style problems under time, writing every step so the analytic marking scheme rewards your method.

Use these companion resources for this chapter:

• Revision Notes
• Common Mistakes
• Practice Questions
• Paper 2 Answering Guide
• Key Terms
• Worked Examples, Easy
• Worked Examples, Medium
• Worked Examples, KBAT