Correlation and Causation

Active learning works because students need to experience the gap between two ideas: a strong correlation feels convincing, yet causation demands proof. These activities make that gap visible through hands-on graphing, debates, and data hunts, so students confront their intuitive leap from ‘it moves together’ to ‘one makes the other happen.’

• Year 10
• Mathematics
• 4 activities
• 30 min–45 min

Learning Objectives

1. Explain why a strong correlation between two variables does not automatically mean one causes the other.
2. Analyze real-world scenarios to identify instances where correlation is incorrectly interpreted as causation.
3. Evaluate the role of confounding variables in obscuring or creating apparent relationships in bivariate data.
4. Critique statistical claims made in media or advertising by distinguishing between correlation and causation.

Jigsaw

⏱ 45 min·Small Groups

Jigsaw: Spurious Correlations

Assign small groups one real-world example, such as cheese consumption and bed linen tangles. Groups research data, identify confounders, and create posters. Regroup into expert jigsaws to teach peers, followed by class vote on most convincing case. Conclude with shared scatterplot sketches.

Prepare & details

Explain why correlation does not necessarily imply causation between two variables?

Facilitation Tip: During Jigsaw Puzzle, circulate and listen for students who immediately claim causation; pause the group to re-read the headline data on the card and redefine the axes together.

Setup: Flexible seating for regrouping

Materials: Expert group reading packets, Note-taking template, Summary graphic organizer

• Understand
• Analyze
• Evaluate
• Relationship Skills
• Self-Management

Socratic Seminar

⏱ 30 min·Pairs

Scatterplot Debates: Pairs Challenge Claims

Pairs receive a scatterplot with a causal headline, like 'More parks cause lower obesity.' They list evidence for and against causation, then debate with another pair. Switch roles and vote on strongest arguments using correlation coefficient criteria.

Prepare & details

Analyze real-world examples where correlation is mistaken for causation.

Facilitation Tip: During Scatterplot Debates, hand each pair two colored pens so they physically mark the third variable they think might be driving the pattern.

Setup: Chairs arranged in two concentric circles

Materials: Discussion question/prompt (projected), Observation rubric for outer circle

• Analyze
• Evaluate
• Create
• Social Awareness
• Relationship Skills

Socratic Seminar

⏱ 35 min·Whole Class

Data Detective Hunt: Whole Class Analysis

Project three datasets from Australian sources, such as rainfall and crop yields. Class brainstorms causal hypotheses in a shared digital whiteboard, then identifies confounders via think-pair-share. Tally votes and discuss experimental design needs.

Prepare & details

Justify the importance of considering confounding variables in statistical analysis.

Facilitation Tip: During Data Detective Hunt, assign roles like ‘graph interpreter’ and ‘confounder hunter’ to keep everyone accountable for the analysis.

Setup: Chairs arranged in two concentric circles

Materials: Discussion question/prompt (projected), Observation rubric for outer circle

• Analyze
• Evaluate
• Create
• Social Awareness
• Relationship Skills

Socratic Seminar

⏱ 40 min·Small Groups

Simulation Stations: Confounding Variables

Set up stations with props: one for ice cream/shark attacks (weather confounder), another for homework/grades (parental involvement). Groups rotate, model with graphs, and predict coefficient changes if confounder is controlled. Share insights in plenary.

Prepare & details

Explain why correlation does not necessarily imply causation between two variables?

Facilitation Tip: During Simulation Stations, require each station to record its confounding variable on a sticky note and post it on a class ‘lurking factors’ poster before moving on.

Setup: Chairs arranged in two concentric circles

Materials: Discussion question/prompt (projected), Observation rubric for outer circle

• Analyze
• Evaluate
• Create
• Social Awareness
• Relationship Skills

Teaching This Topic

Start by modeling how correlation feels real but is still just an association. Use real datasets students care about, such as study time versus sleep quality, and deliberately introduce a lurking variable like homework load. Have students swap axes in pairs to see that the direction of correlation does not decide which variable is the cause. Keep whole-class debriefs focused on evidence: ask ‘What would we need to see to believe causation?’ rather than letting opinions dominate.

What to Expect

By the end of the hub, students confidently label scatterplots as correlation only, articulate why correlation alone is insufficient evidence, and design simple controls for confounders. They speak in complete sentences and cite specific features of the data that rule out causation when appropriate.

Watch Out for These Misconceptions

Common Misconception

During Jigsaw Puzzle, watch for students who assume the third variable on the card must be the cause because the headline pairs two others.

What to Teach Instead

Pause the jigsaw and ask each group to circle the two variables mentioned in the headline and underline the lurking variable, then rephrase the relationship without using ‘cause’ or ‘because.’

Common Misconception

During Scatterplot Debates, watch for students who claim the direction of the correlation determines which variable is the cause.

What to Teach Instead

Hand each pair a set of blank axes and have them re-plot the same data with the axes swapped; require them to defend whether the causal claim changes when the labels flip.

Common Misconception

During Data Detective Hunt, watch for students who conclude no correlation means no causal relationship exists.

What to Teach Instead

Ask groups to revisit their dataset and list any hidden patterns or thresholds they may have missed, then discuss how small sample sizes or nonlinear trends can mask real effects.

Assessment Ideas

Discussion Prompt

After Jigsaw Puzzle, display the firefighter damage graph and ask students to use their puzzle pieces to explain at least two alternate explanations before voting on whether the claim of causation holds.

Quick Check

During Scatterplot Debates, collect one sentence from each pair that labels the relationship as correlation or causation and names one confounder they spotted in the data.

Exit Ticket

After Simulation Stations, ask students to define correlation and causation in one sentence each, then sketch a quick scatterplot showing a correlated pair and label a potential lurking variable on the same axes.

Extensions & Scaffolding

• Challenge: Ask students to design a controlled experiment that could test the strongest causal claim they rejected in Scatterplot Debates.
• Scaffolding: Provide partially completed scatterplots where one axis is blank so students only need to plot the second variable and identify the correlation strength before debating.
• Deeper: Invite students to find a news headline that incorrectly implies causation from correlation, then rewrite it using only correlational language and list possible confounders.

Key Vocabulary

Correlation	A statistical measure that describes the extent to which two variables change together. It indicates the strength and direction of a linear relationship.
Causation	A relationship where a change in one variable directly produces or brings about a change in another variable.
Confounding Variable	An unmeasured variable that influences both the independent and dependent variables, potentially creating a spurious correlation.
Spurious Correlation	A correlation between two variables that appears to be related but is actually due to coincidence or the influence of a third, unobserved factor.