The effect of lifestyle on some non-communicable diseases: Students should be able to use a scatter diagram to identify a correlation between two variables in terms of risk factors.

The idea

A scatter diagram plots one variable on the x-axis and another on the y-axis, giving one point per individual or group. If points trend upwards, the two variables are positively correlated; if downwards, negatively correlated; if there is no trend, there is no correlation. In this section the variables are often a lifestyle risk factor, such as number of cigarettes smoked per day, and a health outcome, such as incidence of lung cancer. Correlation means the variables are associated, not that one causes the other. A third factor, such as age or income, could link them, so a correlation supports but does not prove causation. You identify a correlation by describing the direction and strength of the trend, for example a strong positive correlation, and you interpret it in terms of increased risk.

What earns the marks

• State that each point on a scatter diagram represents one individual or group, with one variable on the x-axis and the other on the y-axis.
• Identify a positive correlation when y increases as x increases, a negative correlation when y decreases as x increases, and no correlation when there is no clear trend.
• Describe the strength of a correlation as strong or weak according to how closely the points lie to a single trend, without inventing numerical thresholds.
• Interpret a positive correlation between a risk factor and a disease as meaning that higher exposure is associated with higher risk of the disease.
• Explain that correlation does not prove causation because another variable may be responsible for both patterns.
• Apply the skill to given data, for example a graph of daily cigarettes smoked against lung cancer cases per 1000 people.
• Use terms such as risk factor, correlation, positive, negative and causation accurately in written answers.

Common mistakes and how to put them right

• Writing that a positive correlation proves the risk factor causes the disease.

  Put it right by saying the data show an association, and other factors may be involved.

• Confusing the axes, for example reading a negative correlation as positive.

  Put it right by checking which variable is on each axis before describing the trend.

• Describing a correlation as strong merely because many points are plotted.

  Put it right by judging strength from how closely points follow one trend, not from the number of points.

• Treating any scatter of points as showing a correlation.

  Put it right by stating that no clear trend means no correlation.

Exam tips

• Read the axis labels and units before describing the trend, then quote the direction and strength in one sentence.
• Link the correlation back to risk, for example state that as the number of cigarettes smoked per day increases, the risk of lung cancer increases.
• If asked whether the data prove causation, answer no and give a reason such as another lifestyle or genetic factor could affect both variables.
• Practise interpreting unfamiliar scatter diagrams so you can apply the skill to any context, not just smoking and cancer.