Module 11 Worksheet: Correlation, Confounding, and Causation
Scenario
Two measures move together across the dataset and someone has proposed acting on the relationship.
Data
Dataset: screen-time-sleep-confounding.csv
| student_id | screen_hours | sleep_hours | after_school_work_hours | study_hours | quiz_score |
|---|---|---|---|---|---|
| Q01 | 1.5 | 8.0 | 0 | 6 | 82 |
| Q02 | 2.0 | 7.5 | 0 | 5 | 78 |
| Q03 | 3.0 | 7.0 | 1 | 5 | 74 |
| Q04 | 4.0 | 6.5 | 2 | 4 | 69 |
| Q05 | 5.0 | 6.0 | 3 | 3 | 63 |
| Q06 | 2.5 | 7.2 | 0 | 7 | 85 |
Your Task
Write three possible explanations for why two variables move together.
Questions
- How strong is the association?
- What third variable could plausibly drive both?
- What would happen to the association if you held that variable fixed?
- Is the relationship useful for prediction? Say what for.
- Is it useful for deciding what to change? Say why or why not.
- What would an experiment here look like?
- How would you describe the relationship honestly?
Write Your Conclusion
Describe the relationship in one or two sentences that would survive someone asking whether you have shown a cause.
Self-Check
- Did I name a plausible confounder?
- Did I distinguish prediction from explanation?
- Did I avoid causal language I cannot support?
- Did I say what evidence would settle it?