B5c — AQA GCSE Statistics
Test yourself on B5c with AQA GCSE practice questions.
Start free
7 days Premium · Then free forever · No card, no charge
Your focus
- Know the importance of identifying and controlling extraneous variables.
B5c exam tips
Quick Revision Summary (Key Takeaway)
B5c in AQA GCSE Statistics covers the analysis and interpretation of bivariate data using scatter diagrams, correlation, and lines of best fit. Students must calculate and interpret the product moment correlation coefficient (PMCC), understand its limitations, and use regression lines to make predictions while recognising the difference between correlation and causation.
Topic Overview
B5c focuses on bivariate data analysis, where you study the relationship between two variables. You will learn to construct and interpret scatter diagrams, identify different types of correlation, and calculate the product moment correlation coefficient (PMCC) to quantify the strength and direction of a linear relationship. You will also use lines of best fit to make predictions and understand the critical distinction between correlation and causation.
This topic is essential for understanding how statisticians analyse relationships in real-world contexts, from economics to health sciences. It builds on your knowledge of representing data and calculating summary statistics, and it prepares you for more advanced statistical techniques like regression analysis. Mastering B5c will enable you to critically evaluate claims based on data and make informed decisions.
Key Concepts
- →Scatter diagrams visually display the relationship between two continuous variables, with each point representing a paired observation.
- →Correlation describes the direction (positive or negative) and strength (strong, moderate, weak) of a linear relationship between two variables.
- →The product moment correlation coefficient (PMCC), denoted r, is a numerical measure of linear correlation, ranging from -1 to 1, where -1 is perfect negative, 0 is no linear correlation, and 1 is perfect positive.
- →A line of best fit (regression line) can be drawn on a scatter diagram to model the relationship and make predictions, but predictions are only reliable within the range of the data (interpolation).
- →Correlation does not imply causation; a strong correlation between two variables does not mean one causes the other, as there may be a lurking variable or coincidence.
Examiner Tips
- 💡When describing correlation, always mention the variables, the direction, and the strength. For example, 'There is a strong positive correlation between variable X and variable Y.'
- 💡When calculating r, show your working clearly, including the table of values for x, y, x², y², and xy. This helps you avoid arithmetic errors and allows the examiner to award method marks.
- 💡When interpreting r, state its value, comment on the strength and direction, and note that it measures linear correlation only. Also, mention that correlation does not imply causation if the context suggests a causal link.
Common Mistakes
- Students often think that a correlation of 0 means there is no relationship at all. In fact, it means there is no linear relationship; there could be a non-linear relationship.
- Students may believe that a strong correlation proves causation. This is false; only a controlled experiment can establish causation.
- Students sometimes confuse the strength of correlation with the steepness of the line of best fit. A steep line does not necessarily mean a strong correlation; strength is about how closely points cluster around the line.
Revision Plan
- 1Day 1-2: Revise the basics of scatter diagrams and correlation. Practice plotting points and describing relationships in words.
- 2Day 3-4: Learn the formula for the product moment correlation coefficient (PMCC) and practice calculating it using summary statistics. Check your answers using a calculator or spreadsheet.
- 3Day 5-6: Study lines of best fit and how to use them for prediction. Understand interpolation vs extrapolation and the limitations of predictions.
- 4Day 7-8: Work through exam-style questions on correlation and regression, focusing on interpretation and common pitfalls. Review examiner reports for this topic.
- 5Day 9-10: Complete a full past paper section on B5c under timed conditions. Mark your work and review any mistakes, ensuring you understand the mark scheme.
Exam Question Types
- 📋Describe the correlation shown in a scatter diagram and comment on its strength and direction. Advice: Use precise language and refer to the context.
- 📋Calculate the product moment correlation coefficient (PMCC) from summary statistics and interpret the result. Advice: Show all steps and comment on what r means in context.
- 📋Use a given line of best fit to make a prediction and comment on its reliability. Advice: State whether the prediction is interpolation or extrapolation and discuss potential limitations.
- 📋Explain why correlation does not imply causation in a given context. Advice: Suggest possible lurking variables or alternative explanations.
Command Word Expectations (AQA)
Describe
Give a detailed account of the correlation in terms of direction, strength, and the variables involved. For example, 'There is a moderate negative correlation between age and value.'
Calculate
Show all steps in your working to find a numerical answer, such as the PMCC. You must use the correct formula and round appropriately if required.
Interpret
Explain what the calculated value or graph means in the context of the problem. For PMCC, comment on strength, direction, and linearity. For predictions, comment on reliability.
Evaluate
Consider the strengths and weaknesses of a statistical claim or method. For example, discuss the reliability of a prediction or the limitations of correlation.
How Students Lose Marks (Examiner Pitfalls)
Pitfall: Students often describe correlation as 'positive' or 'negative' without specifying it is a relationship between two variables, or they confuse correlation with causation. They also frequently misread the strength of correlation from a scatter diagram, calling a weak correlation 'strong' just because the points trend upwards.
❌ Weak Answer (Loses Marks):There is a positive correlation because as one thing goes up the other goes up too. This means one causes the other.
Example improved answer:There is a moderate positive correlation between the number of hours spent revising and the test score. As revision hours increase, test scores tend to increase. However, correlation does not imply causation; other factors such as prior knowledge or teaching quality may also affect test scores.
Examiner Tip: Always state the variables, the direction (positive/negative), and the strength (strong/moderate/weak) of the correlation. Explicitly mention that correlation does not prove causation unless you have experimental evidence.
Pitfall: When calculating the product moment correlation coefficient (PMCC), students make arithmetic errors in the formula, especially with the sums of squares, or they misinterpret the value of r. They may also fail to recognise that r is affected by outliers and that a value close to 0 does not mean no relationship, only no linear relationship.
❌ Weak Answer (Loses Marks):r = 0.85 so there is a strong correlation. This means the data is reliable.
Example improved answer:The product moment correlation coefficient r = 0.85 indicates a strong positive linear correlation between the two variables. This means that as one variable increases, the other tends to increase in a linear fashion. However, r only measures linear relationships and can be influenced by outliers; it does not imply causation.
Examiner Tip: Show all steps in your calculation, including the table of values for x, y, x squared, y squared, and xy. When interpreting r, comment on its strength, direction, and the fact it measures linear association only. Remember that r is always between -1 and 1.
Step-by-Step Worked Solutions
Question: A student records the number of hours spent studying (x) and the marks achieved in a test (y) for 8 students. The summary statistics are: Σx = 40, Σy = 480, Σx² = 250, Σy² = 32000, Σxy = 2800, n = 8. Calculate the product moment correlation coefficient and interpret your result.
- 1.Step 1: Identify the given values: Σx = 40, Σy = 480, Σx² = 250, Σy² = 32000, Σxy = 2800, n = 8.
- 2.Step 2: Calculate Sxx = Σx² - (Σx)²/n = 250 - (40²)/8 = 250 - 1600/8 = 250 - 200 = 50.
- 3.Step 3: Calculate Syy = Σy² - (Σy)²/n = 32000 - (480²)/8 = 32000 - 230400/8 = 32000 - 28800 = 3200.
- 4.Step 4: Calculate Sxy = Σxy - (Σx)(Σy)/n = 2800 - (40 × 480)/8 = 2800 - 19200/8 = 2800 - 2400 = 400.
- 5.Step 5: Apply the formula r = Sxy / √(Sxx × Syy) = 400 / √(50 × 3200) = 400 / √160000 = 400 / 400 = 1.
- 6.Step 6: Interpret: r = 1 indicates a perfect positive linear correlation between hours studied and test marks.
Final Answer: r = 1, indicating a perfect positive linear correlation. As hours studied increase, test marks increase proportionally.
Question: A scatter diagram shows a moderate negative correlation between the age of a car (in years) and its value (in thousands of pounds). The line of best fit is given by y = -1.5x + 20, where x is age in years and y is value in thousands. Predict the value of a 6-year-old car and comment on the reliability of this prediction.
- 1.Step 1: Identify the equation of the line of best fit: y = -1.5x + 20.
- 2.Step 2: Substitute x = 6 into the equation: y = -1.5(6) + 20 = -9 + 20 = 11.
- 3.Step 3: Interpret the result: The predicted value is 11 thousand pounds, i.e., £11,000.
- 4.Step 4: Comment on reliability: The prediction is within the range of the data (interpolation), so it is likely reliable. However, if 6 years is outside the range of observed ages, it would be extrapolation and less reliable.
Final Answer: Predicted value = £11,000. This is an interpolation within the data range, so it is reasonably reliable, but other factors could affect the actual value.
Active Recall Memory Test
What does a correlation coefficient of -0.8 indicate?
Key Fact: It indicates a strong negative linear correlation: as one variable increases, the other tends to decrease.
What is the difference between interpolation and extrapolation?
Key Fact: Interpolation is making predictions within the range of the data, which is generally reliable. Extrapolation is making predictions outside the range, which is less reliable.
Why does correlation not imply causation?
Key Fact: Because a third variable (lurking variable) may be causing both variables to change, or the correlation may be coincidental.
What is the formula for the product moment correlation coefficient?
Key Fact: r = Sxy / √(Sxx × Syy), where Sxx = Σx² - (Σx)²/n, Syy = Σy² - (Σy)²/n, and Sxy = Σxy - (Σx)(Σy)/n.
Frequently Asked Questions
What is the difference between correlation and causation?
Correlation means two variables are related in a linear way, but causation means one variable directly affects the other. A correlation can occur due to a third factor or by chance. For example, ice cream sales and drowning incidents are correlated because both increase in hot weather, but ice cream does not cause drowning. Only a controlled experiment can establish causation.
How do I calculate the product moment correlation coefficient (PMCC)?
To calculate PMCC (r), you need the summary statistics: n, Σx, Σy, Σx², Σy², and Σxy. First calculate Sxx = Σx² - (Σx)²/n, Syy = Σy² - (Σy)²/n, and Sxy = Σxy - (Σx)(Σy)/n. Then use the formula r = Sxy / √(Sxx × Syy). The value of r will be between -1 and 1. Show all your working to gain method marks.
What does an r value of 0.5 mean?
An r value of 0.5 indicates a moderate positive linear correlation. This means that as one variable increases, the other tends to increase, but the relationship is not very strong. About 25% of the variation in one variable can be explained by the other (since r² = 0.25). However, r only measures linear relationships, so a non-linear relationship could still exist.
How do I draw a line of best fit?
A line of best fit should be drawn so that it passes through the mean point (x̄, ȳ) and has roughly equal numbers of points above and below it. It should follow the general trend of the data. Use a ruler and pencil, and aim to minimise the distances from the points to the line. The line can then be used to make predictions, but only within the range of the data.
Why is extrapolation unreliable?
Extrapolation is making predictions outside the range of the observed data. It is unreliable because the relationship between variables may change outside the observed range. For example, a linear trend might not continue indefinitely; it could curve or plateau. Therefore, predictions based on extrapolation should be treated with caution and clearly stated as uncertain.
What are the limitations of the product moment correlation coefficient?
The PMCC only measures the strength and direction of a linear relationship. It can be misleading if the relationship is non-linear (e.g., quadratic), as r might be close to 0 even though there is a clear pattern. It is also sensitive to outliers, which can disproportionately affect its value. Additionally, r does not imply causation and should not be used to make causal claims.