Correlation and Regression
Calculate and interpret correlation coefficients and regression lines.
Full topic guide: the detailed syllabus page with worked examples and common mistakes lives at studyvector.co.uk/a-level/maths/statistics/regression-correlation.
Topic preview: Correlation and Regression
Sample stems from the StudyVector question bank (AQA · Edexcel · OCR) — not generic filler text.
More questions are being linked to this topic. You can still start adaptive practice after you create a free account.
Coverage and provenance
What this page is based on
StudyVector does not present unsupported question coverage as complete. Read how questions are selected and reviewed.
Topic explanation
Regression and correlation at A-Level involve analysing the relationship between two variables. You will learn to calculate and interpret the product moment correlation coefficient to measure the strength of a linear relationship, and to find the equation of a regression line to make predictions.
Correlation and Regression is easiest to revise when it is treated as a precise exam behaviour, not a loose note-taking category. In A-Level Mathematics, the goal is to recognise how the topic appears in a question, identify the command word, and decide what evidence, method, or vocabulary earns marks. StudyVector keeps this page tied to AQA · Edexcel · OCR language where coverage is available, then routes practice towards the same topic so revision moves from explanation into retrieval.
A strong revision session starts with a short recall check. Write down the rule, definition, process, or method linked to Correlation and Regression before looking at any notes. Then answer one exam-style prompt and compare your answer with the mark-scheme logic: did you make a clear point, support it with the right step, and avoid drifting into a nearby topic? This matters because many lost marks come from almost-correct answers that do not match the expected structure.
Use this guide as the first layer: understand the topic, look at the worked examples, complete the mini quiz, then move into full practice. The full StudyVector practice loop is designed to capture whether mistakes are caused by knowledge, method, language, or timing. That distinction is important. If the error is factual, you need reteaching. If the error is method-based, you need a worked retry. If the error is wording, you need command-word calibration. That is how Correlation and Regression becomes a controlled revision target rather than another page in a folder.
Lost marks → repair task
Why marks are usually lost here
These are the error patterns StudyVector looks for after an attempt. The goal is not a generic explanation; it is one repair move and one follow-up question.
Unit, formula, or method slip
Examiner move: Select the correct method and keep units, substitutions, signs, and rounding visible.
Repair drill: Redo the calculation or method line slowly, naming the formula before substituting values.
Missing chain of reasoning
Examiner move: Show the link between point, method, evidence, and conclusion instead of jumping to the final line.
Repair drill: Write the missing because/therefore step, then retry one isomorphic question.
Timing breakdown
Examiner move: Match answer length to marks and avoid over-writing low-mark questions.
Repair drill: Set a one-mark-per-minute cap and write a compact version before expanding.
Mini quiz
Use these checks before full practice. They test topic recognition, exam technique, and whether you can connect the explanation to a marked response.
1. What should you check first when a Correlation and Regression question appears in A-Level Mathematics?
- A.The command word and the exact topic focus
- B.The longest paragraph in your notes
- C.A memorised answer from a different topic
2. Which revision action gives the strongest evidence that Correlation and Regression is improving?
- A.Rereading the explanation twice
- B.Answering a timed exam-style question and reviewing lost marks
- C.Highlighting every key phrase in the topic notes
Sample questions
Topic-specific public question previews are still being reviewed. We keep them off public pages until the topic match is safe.
Exam tips
- Read the command word carefully — "explain" needs reasons; "state" expects a short fact.
- For Correlation and Regression, show structured working even when you are practising multiple choice — it builds accuracy under time pressure.
- Mark yourself against the mark scheme style: one clear point per mark, in logical order.
- Come back to this topic after a day or two; short spaced reviews beat one long cram.
Worked examples
Example 1
Modelled exam response
A set of data has a product moment correlation coefficient of 0.8. This indicates a strong positive linear relationship between the two variables. The equation of the regression line of y on x is y = 2x + 5. If x = 10, the predicted value of y is 2(10) + 5 = 25.
Example 2
Identify the task before answering
Question type: a Correlation and Regression prompt asks for a clear response in A-Level Mathematics. Step 1: underline the command word. Step 2: name the exact part of Correlation and Regression being tested. Step 3: decide whether the mark scheme wants a definition, method, explanation, comparison, or calculation. Why it works: most weak answers fail before the content starts because they answer the topic generally rather than the exact exam task.
Example 3
Turn feedback into a repair task
Suppose your answer shows partial understanding but loses marks for precision. First, rewrite the missing mark as a short target: "I need to state the mechanism, unit, reason, or evidence explicitly." Then answer one similar question without notes. Finally, compare the second attempt with the first and check whether the same mark was recovered. Why it works: Correlation and Regression improves faster when feedback creates a specific retry, not another passive reading session.
Next revision routes from this subject
Good topic pages should lead naturally into the next useful page. Use these links to stay inside the same strand or jump into the next topic area without starting your search again.
Stay in the same topic area
Explore the wider subject map
Common mistakes
- Confusing correlation with causation. A strong correlation between two variables does not necessarily mean that one causes the other; there may be a third variable involved.
- Extrapolating beyond the range of the data when using a regression line to make predictions. The regression line is only valid for the range of the data used to create it.
- Incorrectly interpreting the product moment correlation coefficient. A value close to 1 or -1 indicates a strong linear relationship, while a value close to 0 indicates a weak linear relationship.
Exam board notes
All A-Level Maths boards (AQA, Edexcel, OCR) cover regression and correlation. The calculation of the product moment correlation coefficient and the equation of the regression line are key topics for all boards.
FAQs
What is the difference between the regression line of y on x and the regression line of x on y?
The regression line of y on x is used to predict y from x, and it minimises the sum of the squared vertical distances from the data points to the line. The regression line of x on y is used to predict x from y, and it minimises the sum of the squared horizontal distances.
What is the product moment correlation coefficient?
The product moment correlation coefficient (PMCC), denoted by r, is a measure of the linear correlation between two variables. It takes a value between -1 and 1, where 1 is total positive linear correlation, -1 is total negative linear correlation, and 0 is no linear correlation.
More on StudyVector
Full practice set
The complete adaptive question bank for this topic — personalised to your weak areas — is available after you sign in. Your session can start on this topic immediately.