Correlation
Grade 4What correlation tells you
When you plot two variables on a scatter graph, the pattern of points tells you whether there is a correlation — a relationship between the two variables.
There are three types: positive (as one increases, so does the other), negative (as one increases, the other decreases), and no correlation (the points are scattered with no pattern).
Strength of correlation
As well as the direction, you need to describe how strong the correlation is. If the points lie close to a straight line, it's strong. If they're more loosely spread around a line, it's weak.
Use both words together in your answer: "strong positive correlation" or "weak negative correlation". Just saying "positive correlation" without a strength will usually lose you a mark.
Worked example — describing correlation
EXAMPLE
A scatter graph shows revision hours on the x-axis and test scores on the y-axis. The points roughly follow a line going from bottom-left to top-right, fairly closely bunched. Describe the correlation.
Points go from bottom-left to top-right → positive direction. Points are fairly closely bunched around a line → strong. As revision hours increase, test scores increase. Strong positive correlation.
Correlation is not causation
Correlation means two things change together — it does not mean one causes the other. Ice cream sales and sunburn both increase in summer, but ice cream doesn't cause sunburn. Always be careful about what you conclude from a correlation on an exam.
