Correlations (AQA GCSE Psychology): Revision Note

Co-variables

• A correlation is not a research method, it is an analysis of the possible relationship between co-variables 

• In correlational research, no variable is manipulated (there is no IV); instead, two co-variables are measured and compared to look for a relationship

• One or both of the co-variables could be pre-existing, e.g.

  • School attendance (days present in Year 11) and number of GCSEs achieved

  • Average temperature in August and number of arrests for violent behaviour that month

• One or both of the co-variables could be measured for the research itself, e.g.

  • Number of takeaway meals eaten in a month and self-reported stress levels for the same month

  • Average hours of sleep in a week and number of caffeinated drinks consumed that week

• A correlation always uses two scores per participant (or per case)

  • e.g. an average of 4 hours' sleep a night correlated with a certain number of cups of caffeine consumed that week

• For pre-existing data, the researcher simply uses existing records

  • e.g. Student X was present for 188 days in Year 11 and achieved 10 GCSEs 

Types of correlation & scatter diagrams

• There are four types of correlation:

  • Positive correlation: one co-variable increases as the other increases (not necessarily at the same rate)

    • e.g. calories consumed and weight gained

  • Negative correlation: one co-variable increases as the other decreases

    • e.g. hours spent watching television and level of fitness

  • Zero correlation: there is no relationship between the co-variables

    • e.g. hair colour and IQ

  • Curvilinear relationship: the relationship changes direction rather than staying constant

    • e.g. alertness rises through the day, peaks, then falls towards bedtime. This shows that correlational analysis can identify more complex relationships than a simple straight-line trend

• Correlations are plotted as one point on a scatter diagram; the pattern and direction of the points show the type of correlation

• A relationship can also be analysed by calculating the correlation coefficient, a numerical value between -1 and +1:

  • +1 = a perfect positive correlation

  • -1 = a perfect negative correlation

  • 0 = no relationship

• Coefficients (positive or negative) can be described as weak, moderate or strong

  • e.g. 0.2 is a weak positive correlation; -0.8 is a strong negative correlation

Scatter diagrams and the type of correlation shown on each.

Evaluation of correlations

Strengths

• Correlations show that two variables are related, which can be a good starting point for further experimental research

  • e.g. a positive correlation between temperature and aggression could lead a researcher to test this further with an experiment

• Correlational analysis can investigate more complex relationships than a simple straight line, such as curvilinear relationships (see above), giving it wider use as a technique for understanding how variables are associated

Weaknesses

• Correlations cannot show cause and effect, only that two variables are related, not why.

  • e.g. a positive correlation between stress and days off work doesn't tell us whether stress is causing illness, or whether being ill (and falling behind at work) is causing the stress

• An apparent link between two co-variables may really be caused by an intervening variable - this is a third, 'in-between' factor

  • e.g. a stressful job might lead someone to sleep less, smoke or drink more, and it is this behaviour, not the stress itself, that increases their chance of becoming ill

  • Because a correlation involves no control of extraneous variables, the conclusions drawn may be misleading