Studied by 0 people
Define the term ‘correlation’.
A mathematical technique in which a research investigates an association between two variables, called co-variables.
How are correlations expressed and what do they show?
Correlations are plotted on a scattergram, and they illustrate the strength and direction of an association between two or more co-variables.
What is a positive correlation?
As one co-variable increases, so does the other.
What is a negative correlation?
As one co-variable increases, the other decreases.
What is a zero correlation?
When there is no relationship between the 2 variables.
Correlations VS Experiments
In an experiment we manipulate the IV and measure the effect on the DV.
–There is deliberate change to one variable so we can infer that this manipulation caused any change to the DV.
In a correlation, there is no manipulation so we can not establish a cause an effect between the co-variables.
–Even if we found a super strong positive correlation, we can notassume cause and effect. Eg. We cannot assume that caffeine directly causes anxiety levels to increase, however there is a strong positive correlation.
Evaluating correlations - strengths.
Useful as a starting point for further research, used to first show an interesting relationship between 2 variables.
Relatively quick and economical to carry out, no need to control environment or set up variables to manipulate.
Evaluating correlations - weaknesses.
Cannot demonstrate cause and effect, can only tell us how variables are related not why.
The third-variable problem, Eg. in the anxiety-caffeine example, people have high pressured jobs which make them feel anxious, they work long hours so they drink a lot of caffeine.
Vulnerable to misuse, Eg. the media could present a correlation as a ‘causal’ fact when in reality they are not.
What is a correlation coefficient?
A numerical value between -1 and +1.
They are represented as r, so perfect positive correlation - r = +1. The closer the coefficient is to either -1 or +1, the stronger the relationship between the co-variables.
Shows us the strength and direction of the relationship between 2 variables.
