Who this is for: Cambridge IGCSE Mathematics (0580/0607) students who want scatter plots, correlation and the line of regression — drawing graphs, describing relationships and making predictions — to become a reliable source of marks instead of vague comments about “going up”.
What query it owns: how to understand and revise scatter plots, correlation and line of regression in Cambridge IGCSE Mathematics.
Why this is safe: this page owns the scatter plots and regression revision-guide angle, while Tutopiya’s Scatter Plots, Correlation and Line of Regression subtopic page owns the learning resource and the free scatter plots quiz owns the practice.

Scatter plots, correlation and the line of regression appear regularly in the Statistics unit of Cambridge IGCSE Mathematics (0580/0607). Examiners expect you to plot paired data, describe correlation in precise language, draw a line of best fit and use it to interpolate or extrapolate — while knowing the limits of what the data proves. This guide explains exactly what each skill covers, how to handle the question types that actually appear, and where to practise each one.

Key takeaways

• A scatter plot shows paired data as points; the pattern reveals positive, negative or no correlation.
• The line of best fit (regression line) balances points above and below; use it to estimate values within the data range.
• Correlation does not prove causation — never claim one variable causes another from a scatter graph alone.
• Extrapolation beyond the data range is unreliable; exam questions often ask you to explain why.

What are scatter plots, correlation and regression in Cambridge IGCSE Maths?

A scatter plot displays two variables on perpendicular axes, with each pair of values plotted as a point. Correlation describes the trend: as one variable increases, does the other tend to increase (positive), decrease (negative), or show no clear pattern? The line of best fit is a straight line drawn through the points to model the relationship and estimate missing values.

You can read the full explanation, worked examples and notes on Tutopiya’s Scatter Plots, Correlation and Line of Regression subtopic page before you attempt questions.

The core ideas you must master

These four ideas appear again and again. Learn what each one means and the exam phrasing that signals it.

Idea	What it means	How the exam uses it
Positive correlation	As x increases, y tends to increase	”Describe the correlation.”
Negative correlation	As x increases, y tends to decrease	”What type of correlation is shown?”
Line of best fit	Straight line modelling the trend	”Draw a line of best fit.”
Interpolation / extrapolation	Estimate within / beyond data range	”Use your line to estimate …”

How to work with scatter plots — step by step

The safest method works for plotting, describing and using the regression line.

1. Label axes with the variable name and units; choose a sensible scale.
2. Plot each pair as a cross or dot — accuracy matters for method marks.
3. Describe correlation using correct terms: positive, negative, weak, strong, or none.
4. Draw the line of best fit — roughly equal points above and below; do not force it through the origin.
5. Read values by drawing horizontal and vertical lines from the axis to the line of best fit.
6. State limitations when extrapolating or when correlation does not imply causation.

Once you have worked through a few, test yourself with the free scatter plots quiz — it tells you fast whether the method has actually stuck.

Correlation types: which description does the question want?

Students lose marks by using vague language or overstating what the graph shows. Use the point pattern to decide.

Pattern	Correlation	Typical signal words
Points slope upward	Positive	”as temperature increases, sales increase”
Points slope downward	Negative	”as distance increases, time decreases”
No clear trend	None / weak	”scattered”, “no correlation”
Estimate within range	Interpolation — reliable	value lies between plotted x-values
Estimate outside range	Extrapolation — unreliable	x-value beyond the data

Scatter plots in past-paper wording: command words that matter

Most lost marks come from imprecise correlation language or claiming causation. These are the command words you will see.

Command word / phrase	What the question wants	Typical stem
Describe the correlation	State type and strength in words	”Describe the correlation shown.”
Draw a line of best fit	Straight line with balanced points	”Draw a line of best fit on the diagram.”
Use your line to estimate	Read value from the line	”Estimate the value of y when x = 6.”
Explain why … unreliable	Extrapolation or weak correlation	”Explain why this estimate may be unreliable.”
Comment on the relationship	Correlation without causation	”Does this prove that x causes y?”

Worked exam-style stems (how to answer the wording)

Practising the wording — not just the drawing — is what interpretation marks reward.

1. “The scatter graph shows the age and height of children. Describe the correlation.” Points trend upward → positive correlation. As age increases, height tends to increase. Reward: correct correlation type with linked variables named.
2. “Draw a line of best fit and estimate the mass when the length is 15 cm.” Draw balanced line; read at x = 15. Reward: correct reading from line, not from a single point.
3. “A student says the graph proves that eating ice cream causes sunburn. Comment on this statement.” No — correlation does not prove causation; a third factor (hot weather) may explain both. Reward: clear statement that correlation ≠ causation.

When you can recognise the wording instantly, work the full set on the Statistics topical past paper questions and the scatter plots quiz to lock the method in.

How scatter plots connect to the rest of Statistics

Scatter graphs build on Methods of Analysing Data when you compare two data sets. They also link to Statistical Charts and Diagrams as another way to represent data visually. When you are ready to mix topics, the Cambridge IGCSE Maths resource hub lets you move straight from a weak subtopic into the next.

Common mistakes students make

• Drawing the line of best fit through the origin when the data does not pass near (0, 0).
• Using “causes” when the question only shows correlation.
• Extrapolating without commenting that the estimate may be unreliable.
• Describing correlation as “positive” when points are scattered with no clear trend.
• Reading from a single point instead of the line of best fit when estimating.

When you need more support

If scatter plot questions keep tripping you up — especially line of best fit and interpretation — work through the Statistics topical past paper questions and the scatter plots quiz to pinpoint the exact gap, then get focused help from a Cambridge IGCSE Maths tutor to fix it quickly.

Frequently asked questions

Are scatter plots hard in Cambridge IGCSE Maths? No — plotting is straightforward. Marks are lost on imprecise correlation language, poor lines of best fit, and claiming causation from correlation.

What is the difference between correlation and causation? Correlation means two variables tend to change together. Causation means one directly causes the other — a scatter plot alone cannot prove this.

Can I use my calculator for the line of regression? On 0580/0607, you usually draw the line of best fit by hand. Know how to balance points above and below the line.

How do I revise scatter plots effectively? Read the subtopic notes, practise describing correlation in full sentences, then take the scatter plots quiz. Revisit any extrapolation questions you got wrong.

Ready to master Cambridge IGCSE Maths scatter plots and regression?

Start with the Scatter Plots, Correlation and Line of Regression subtopic page, then book a free trial with a Cambridge IGCSE Maths specialist to turn scatter graph skills into guaranteed marks.

Ready to Excel in Your Studies?

Get personalised help from Tutopiya's expert tutors. Whether it's IGCSE, IB, A-Levels, or any other curriculum — we match you with the perfect tutor and your first session is free.

Book Your Free Trial