Mathematics · Year 8 · Data Handling and Probability · Summer Term

Scatter Graphs and Correlation

Students will plot scatter graphs, identify correlation, and draw lines of best fit.

• National Curriculum Attainment Targets
• KS3: Mathematics - Statistics

About This Topic

Scatter graphs visualise relationships between two numerical variables by plotting data points on axes. Year 8 students use bivariate data, such as shoe size versus height or study time versus exam results, to construct these graphs. They recognise positive correlation, where points trend upward; negative correlation, trending downward; and no correlation, with scattered points. These skills meet KS3 Mathematics Statistics standards for data handling and interpretation.

Students progress to drawing lines of best fit, straight lines that pass through or near most points to summarise trends. They use these lines for predictions: interpolation estimates values within the data range, while extrapolation forecasts beyond it with caution. This process develops statistical reasoning and supports probability units by emphasising evidence-based conclusions over assumptions.

Active learning suits this topic well. When students collect classroom data, plot on large grids, and negotiate line positions in pairs, they grasp correlations through direct experience. Collaborative critique of peers' graphs builds precision and confidence in predictions.

Key Questions

1. What does the correlation in a scatter graph tell us about the relationship between variables?
2. Construct a line of best fit on a scatter graph and use it for predictions.
3. Differentiate between positive, negative, and no correlation.

Learning Objectives

• Construct scatter graphs to represent bivariate data sets.
• Analyze scatter graphs to identify and classify correlations as positive, negative, or no correlation.
• Draw an accurate line of best fit on a scatter graph to summarize data trends.
• Calculate predictions using a line of best fit, distinguishing between interpolation and extrapolation.
• Critique the appropriateness of using a line of best fit for predictions based on the observed correlation.

Before You Start

Plotting Coordinates

Why: Students need to be able to accurately plot points on a Cartesian grid to construct scatter graphs.

Understanding of Variables

Why: Students should have a basic understanding of what variables are and how to identify them in a given context.

Key Vocabulary

Bivariate Data	A set of data that consists of paired values for two different variables, used to explore relationships.
Correlation	The statistical relationship or connection between two variables, indicating how they tend to change together.
Line of Best Fit	A straight line drawn on a scatter graph that passes as close as possible to all the data points, representing the general trend.
Interpolation	Estimating a value within the range of the observed data points using the line of best fit.
Extrapolation	Estimating a value outside the range of the observed data points using the line of best fit, which should be done with caution.

Watch Out for These Misconceptions

Common Misconception

The line of best fit must pass through every data point.

What to Teach Instead

The line balances points above and below it to minimise overall deviation. Hands-on plotting with real data in small groups lets students experiment with lines and see why exact passes rarely fit noisy data, building judgement skills.

Common Misconception

Correlation between variables means one causes the other.

What to Teach Instead

Correlation shows association only; causation requires controlled tests. Role-playing scenarios in pairs helps students generate counterexamples, like ice cream sales and shark attacks, clarifying the distinction through discussion.

Common Misconception

No correlation means the variables are completely unrelated.

What to Teach Instead

At this level, it indicates no linear pattern, but non-linear links may exist. Group analysis of varied plots reveals subtle trends missed individually, refining pattern recognition.

Active Learning Ideas

Pairs Data Collection: Heights and Reach

Pairs measure classmates' heights and arm reach, record 20 data points. Each pair plots a scatter graph on A3 paper and identifies the correlation type. They draw a line of best fit and test one prediction, such as expected reach for average height.

35 min·Pairs

Small Groups: Correlation Sorting

Provide six printed scatter plots representing positive, negative, and no correlation. Groups sort them into categories, justify choices with evidence, and add lines of best fit to two examples. Share findings with the class via gallery walk.

40 min·Small Groups

Whole Class: Prediction Challenge

Display a large scatter graph of training hours versus race times. Students suggest predictions for new data points; vote on line of best fit positions. Reveal actual data to check accuracy and discuss improvements.

30 min·Whole Class

Individual: Personal Scatter Survey

Students survey 15 peers on sleep hours versus energy levels. Plot individually using graph paper or digital tools, label correlation, and draw best fit line. Submit with one prediction and reflection on data quality.

25 min·Individual

Real-World Connections

• Meteorologists use scatter graphs to analyze the relationship between atmospheric pressure and temperature, helping to predict weather patterns for regions like the UK.
• Economists at the Bank of England might plot unemployment rates against GDP growth to identify correlations and inform monetary policy decisions.
• Sports scientists examine the link between training hours and athletic performance for athletes, using scatter graphs to identify optimal training loads.

Assessment Ideas

Quick Check

Provide students with a pre-made scatter graph showing a clear positive correlation. Ask them to write down: 1. What two variables are being plotted? 2. Describe the correlation in one sentence. 3. Draw a line of best fit on the graph.

Exit Ticket

Give each student a small data set (e.g., hours of sleep vs. test score). Ask them to: 1. Plot one point from the data on a mini-graph. 2. State whether they expect a positive, negative, or no correlation and why. 3. Predict a score for someone who slept 7 hours (if 7 is within the data range).

Discussion Prompt

Present two scatter graphs: one with a strong negative correlation and one with very little correlation. Ask students: 'Which graph shows a stronger relationship between the variables? Explain your reasoning, referring to the spread and direction of the points.'

Frequently Asked Questions

How do you identify positive correlation on a scatter graph?

Positive correlation appears as points clustered along an upward line from left to right: as the x-variable increases, the y-variable tends to increase too. Students confirm by checking if most points lie above an imaginary downward line. Real-world examples like height and weight reinforce this; practice with multiple graphs builds quick recognition for predictions.

What is a line of best fit used for?

A line of best fit summarises the trend on a scatter graph for interpolation or extrapolation. Within the data range, it estimates missing values; beyond, it offers tentative forecasts. Teach by having students draw lines on their plots and test predictions against new data, noting limitations like data spread to avoid overconfidence.

How can active learning help students understand scatter graphs and correlation?

Active approaches engage students by linking abstract ideas to tangible actions. Collecting personal data, plotting collaboratively on large charts, and debating best fit lines make patterns visible and memorable. Peer feedback during group sorts corrects misconceptions on the spot, while prediction games build confidence. This hands-on method outperforms passive lectures, as students retain skills through repeated application and reflection.

What real-life data sets work well for scatter graphs in Year 8?

Choose relatable bivariate data: thumb length versus little finger length, pocket money versus age, or TV hours versus homework completion. Sports stats like practice time versus scores add engagement. Ensure 20-30 points for clear trends. Guide collection to avoid bias, then analyse for correlation types; this contextualises skills and sparks curiosity about everyday patterns.