Scatter graphs and correlation
Studying this course? Keep your progress in one place.
Key facts
- A scatter graph plots two variables, one point per pair; the controlling variable goes on the horizontal axis.
- Correlation can be positive, negative or none, and strong or weak.
- A line of best fit is one straight line through the middle of the points and through the mean point.
- Interpolation is reliable; extrapolation is not.
- Correlation does not prove causation.
Scatter graphs
Plot one point for each pair of values, with the variable that controls the other on the horizontal axis.
A scatter graph shows two variables for the same people or objects, with one point for each pair of values.
Temperature and drinks sold give points such as and .
Choose scales that fit all the data, label both axes with units, and plot each point as a small cross.
- Horizontal axisthe variable that causes or controls the other
- Vertical axisthe variable that responds
Temperature affects the number of drinks sold. Which variable goes on the horizontal axis?
Types of correlation
Positive, negative or none, and strong or weak depending on how close the points lie to a line.
Correlation describes the relationship between the two variables.
The correlation is strong when the points lie close to a straight line, and weak when they are more spread out. Always describe it in context, for example "the hotter the day, the more drinks are sold".
| Positive | Negative | None | |
|---|---|---|---|
| As x increases | y increases | y decreases | No pattern |
| Points slope | Up to the right | Down to the right | Scattered |
Positive
- As x increases:
- y increases
- Points slope:
- Up to the right
Negative
- As x increases:
- y decreases
- Points slope:
- Down to the right
None
- As x increases:
- No pattern
- Points slope:
- Scattered
As the age of a car increases, its value falls. What type of correlation is this?
Line of best fit
Draw one straight line through the middle of the points and through the mean point.
A line of best fit is a straight line that follows the trend of the points. Draw it with a ruler.
The line does not have to go through the origin, and an outlier (a point far from the pattern) can be ignored when drawing the line.
- 1
Find the mean point
mean of x, mean of y
- 2
Draw one straight line
with a ruler, not dot to dot
- 3
Balance the points
about the same number above and below
- 4
Ignore outliers
points far from the pattern
Worked example
Speeds are and braking distances are . Find the mean point.
- 1
Mean speed: .
- 2
Mean distance: .
Which is a correct feature of a line of best fit?
Using the line to predict
Read up from to the line and across to , or use the line's equation; only trust predictions inside the data range.
To predict for a given , go up from to the line, then across to the -axis. You can also use the equation of the line, , where is the gradient.
A prediction inside the range of the data (interpolation) is usually reliable. A prediction outside the range (extrapolation) is unreliable because the trend may not continue.
Worked example
The line passes through and , with in °C and the number of drinks. Predict the drinks sold at 26 °C.
- 1
Gradient , so each extra 1 °C gives about 5.5 more drinks.
- 2
From to °C is degrees more.
- 3
.
A line of best fit is based on data from 10 °C to 35 °C. Which prediction is least reliable?
Correlation and cause
No: two variables can be related because something else affects both.
Correlation shows that two variables are related, but it does not prove that one causes the other.
Ice cream sales and sunburn cases are positively correlated because both rise in hot weather, not because ice cream causes sunburn.
A small sample and an outlier can also make a relationship look stronger or weaker than it is. When you evaluate a claim, mention causation, the range of the data and the sample size.
- 1
Hot weather
the hidden third variable
- 2
Ice cream sales rise
effect 1
- 3
Sunburn cases rise
effect 2
- 4
They correlate
but neither causes the other
Correlation shows
- The variables are related
- The direction and strength of the link
It does not show
- That one causes the other
- What else may affect both
Ice cream sales and sunburn cases are positively correlated. Does ice cream cause sunburn?
Try an exam question
As the temperature rises, the number of drinks sold rises. (a) Name this type of correlation. (b) The line of best fit uses data from °C to °C. Explain why a prediction at °C may be unreliable.
[3 marks]
- [1]Positive correlation.
- [1] °C is outside the range of the data, so this is extrapolation.
- [1]The trend may not continue beyond the data.
That's the notes covered.
Carry on to the next subtopic.
Try a question
Which statement describes the correlation between temperature and drinks sold?
1 mark, marked against the mark scheme
Which statement describes the correlation between temperature and drinks sold?
1 mark, marked against the mark scheme