correlations

correlation

• measuring the strength between two or more co-variables (things that are measured).

• e.g. if the amount of aggressive games children play can have an effect on the amount of aggression they show in the playground. (co-variables are aggressive games and aggression displayed).

positive correlation

• where one co-variable increases and so does the other.

• e.g. number of people in a room and noise are positively correlated - the more people in a room, the more noisy it becomes.

negative correlation

• where one co-variable increases and the other decreases.

• e.g. the temperature and number of gloves sold are negatively correlated - the higher the temperature is, the less number of gloves will be sold.

correlational hypotheses

predict a relationship between two variables not a difference (like in experiments), and therefore they are worded differently to experimental hypotheses.

directional correlational hypothesis

• states whether the relationship will be a positive or a negative correlation.

• e.g. there will be a significant positive correlation between temperature and ice-cream sales, or there will be a significant negative correlation between temperature and scarf sales.

non-directional correlational hypothesis

• simply states that there will be a correlation.

• e.g. there will be significant correlation between average time spent reading per week and scores on an I.Q. test.

correlation co-efficients

• a figure between +1 and -1 where +1 represents a perfect positive correlation and -1 represents a perfect negative correlation and 0 means there is no correlation.

• the closer the correlation coefficient is to 0, the weaker the correlation.

• the closer the correlation coefficient is to 1 (or -1), the stronger the correlation.

• -1.0 to -0.8 = strong negative correlation.

• -0.8 to -0.5 = moderate negative correlation.

• -0.5 to 0 = weak negative correlation.

• 0 = no correlation.

• 0 to 0.5 = weak positive correlation.

• 0.5 to 0.8 = moderate positive correlation.

• 0.8 to 1.0 = strong positive correlation.

strengths of correlations

• can be used to assess relationship between two co-variables before committing to an experimental study.

• allows researchers to look at the relationship between variables that you would not be able to experimentally investigate, e.g. relationship between obesity and junk food consumption.

• quick and economical to carry out - no need for controlled environments or manipulation of variables.

• can use secondary data so less time-consuming.

weaknesses of correlations

• don’t provide cause and effect relationship, so cannot conclude that one variable is causing the other to change. This can lead to correlations being misinterpreted or misused, e.g. does increased levels of reciprocity lead to a better quality of attachment OR does a better quality of attachment lead to increased levels of reciprocity?

• cannot tell us why the variables are related.

• third variable problem - another untested variable is causing the relationship between the two co-variables.