Correlations

What is a correlation?

A correlation is a statistical technique used to measure and describe the strength and direction of a relationship between two co-variables.

What are co-variables? Give examples

Co-variables are the two variables measured/collected by the researcher and then are compared to each other

For example -

• Age

• IQ

• Reaction time

• Number of pets

What is a scattergram and what is it used for?

A scattergram (or scatterplot) is a graph that shows the relationship between two co-variables. Each dot represents a pair of scores.
It helps to visualise the type of correlation:

• Upwards trend = positive

• Downwards trend = negative

• No clear pattern = no correlation

What are the types of correlation?

• Positive correlation – as one co-variable increases, the other also increases.

• Negative correlation – as one co-variable increases, the other decreases.

• Zero correlation – no relationship between the co-variables

What is a correlation coefficient? Give examples.

A correlation coefficient is a number between -1 and +1 that shows the strength and direction of a correlation -

• +1 = perfect positive correlation

• -1 = perfect negative correlation

• 0 = no correlation
  The closer to ±1, the stronger the relationship.

Advantages of correlations?

• Often the covariable data already exists and is easily accessible, this means there is usually few ethical problems in data collection.

• Correlational studies can highlight potential casual relationships, these can be tested with experimental methods to discover cause and effect relationships.

Disadvantage of correlations?

• Correlation does not show causation. While a strong correlation may suggest a relationship exists between 2 variables, it does not show which co-variable led to the change in the other co-variable and there is the possibility that an unknown third variable caused the change in both covariables.

What are the differences between experiments and correlations?

• Correlations -

  • Co-variables

  • Test of a relationship between variables

  • Cannot establish cause and effect - only a link.

  • It is represented using a scattergram.

• Experiments -

  • IV is manipulated, DV is measured

  • Test of difference between variables

  • Able to establish cause-and-effect

  • It is likely represented using a pie chart, bar chart or histogram.

Correlation Coefficient	What It Means	Type
+1.00	Perfect positive correlation	Strong +
+0.7 to +0.9	Strong positive correlation	Strong +
+0.3 to +0.6	Moderate positive correlation	Moderate +
+0.1 to +0.2	Weak positive correlation	Weak +
0	No correlation	None
-0.1 to -0.2	Weak negative correlation	Weak –
-0.3 to -0.6	Moderate negative correlation	Moderate –
-0.7 to -0.9	Strong negative correlation	Strong –
-1.00	Perfect negative correlation	Strong –

☺