Positive correlation
Hours of revision and test score for 8 students.
As revision time goes up, test scores tend to go up too -- the points rise left to right.
Year 8
Plot and interpret scatter graphs, describe the type of correlation, draw a line of best fit, and explain why correlation does not prove causation.
Statistics and data
A scatter graph plots pairs of values to show whether two things are linked. If the points rise from bottom-left to top-right, that's positive correlation. If they fall from top-left to bottom-right, that's negative correlation. If there's no clear pattern, there's no correlation. A line of best fit is a straight line drawn through the middle of the points, used to estimate values -- but correlation only shows a link, it never proves that one thing causes the other.
Positive correlation
Hours of revision and test score for 8 students.
As revision time goes up, test scores tend to go up too -- the points rise left to right.
Negative correlation
Age of a car and its resale value for 8 cars.
As the car gets older, its value tends to fall -- the points fall left to right.
No correlation
Shoe size and test score for 8 students.
No clear pattern, and no line of best fit makes sense -- shoe size doesn't affect test score.
Use the line of best fit to estimate the test score for 4.5 hours of revision.
Look at how the points are arranged before deciding on the type of correlation.
A scatter graph shows points rising from bottom-left to top-right. What type of correlation is this?
A scatter graph shows points falling from top-left to bottom-right. What type of correlation is this?
A study finds towns with more ice cream shops also have more sunburn cases. Does this mean ice cream shops cause sunburn?
On a scatter graph with a clear positive correlation, where should you draw the line of best fit?
A scatter graph of shoe size against test score shows points scattered with no pattern. What should you conclude?
Watch for these when working through the lesson.
These ideas fit closely with this lesson.