Correlations

• -          correlation studies look at the relationship between two things/2 variables

  -          in correlations these variables are called Co -variables
• -          you can calculate a correlation coefficient a statistic that has a value between 1 which is a perfect positive correlation a - 1 a perfect negative correlation
• -          correlations are usually plotted onto a scatter gram so you can visually see whether the correlation is positive or negative or if there is 0 correlation
• -          a perfect negative correlation coefficient would equal -1

  -          no correlation coefficient would be equal to 0

  -          a perfect positive correlation coefficient would be equal to 1

  -          in a positive correlation 1 variable tends to increase and so does the other

  -          in a negative correlation as one variable tends to increase the other decreases

  -          0 correlation shows no relationship between 2 variables
• the difference between correlations and experiments

  -          in an experiment the experimenter deliberately manipulates the Ivy whereas in a correlation there is no deliberate changes made to any variables
• the difference between correlations and experiments

  -          in an experiment each level of the IV and its impact on the DV is measured buts in a correlation the impact of 1 variable on another is not being measured there is no comparison made between variables just the relationship between the two Co variables
• the difference between correlations and experiments

  -          in an experiment the experimenter is able to establish cause and effect due to the manipulation of the IV and high levels of control whereas in a correlation the experimenter cannot establish cause and effect they can only establish a relationship between two Co variables and there may be a third unmeasurable variable that also influences the relationship
• the difference between correlations and experiments

  -        1)  In an experiment if we were investigating food and mood they would want to investigate whether the food was the cause that affected our mood and they would manipulate the IV by having some groups each chicken some groups eat cheeseburgers and then would measure their mood using a score system in a questioner
• the difference between correlations and experiments

  2)whereas A correlation would be interested in whether there was a relationship between food and mood they would simply measure how many portions of fruit and vegetables participant ate in a day and use a questionnaire to score mood on a scale as well the results from the experiment would show that people who ate chicken may be happier than those who ate cheeseburgers
• the difference between correlations and experiments

  3)however a positive relationship found between fruit and vegetables and feeling happy does not mean that eating fruit and vegetables cause the happiness it may be that feeling happy caused people to eat more fruit and vegetables in a correlation cause and effect is not identified
• + a strength of correlational analysis is that it can indicate the direction whether it be positive or negative of the relationship between 2 variables the strength of this relationship is also expressed by the size of the correlation coefficient- this is a strength as the technique provides a precise quantitative measure of the strength of the relationship between specific variables which is useful for researchers to know whether to then carry out an experiment into the topic
• + the strength of correlational analysis is it allows researchers to statistically analyse situations that could not be manipulated experimentally or ethically or for practical reasons- for example the hours spent in day care and the amount of aggressive acts show -it wouldn't be ethical to set up a situation where children can be aggressive to one another or to take children away from their parents and put them into day care for hours- therefore a strength of correlation analysis is that it allows researchers to unravel complex relationships easily and is a powerful explanatory tool
• a limitation of correlations is that they do not establish cause and effect they only establish a relationship between 2 variables-if there was a positive correlation between hours spent in day care and aggressive behaviour it does not mean that day care causes aggression it may be that the children who are aggressive are put into day care for longer or there may be a third variable such as divorce which is a reason for both the aggression and the reason why the child is spending longer time in day care-therefore we have to be careful when drawing conclusions from correlations
• 1. a weakness with correlations is that nonlinear relationships cannot be measured by correlational techniques-when looking at the relationship between time of day and attention levels at day care there would initially be a positive correlation between the two variables but as lunchtime approaches this changes into a negative correlation-when such data is analysed the positive and negative relationship tends to cancel each other out with the results having no meaningful relationship
• 2)the meaningless results are indicated by the calculated correlation coefficient-which is why it is important to plot nonlinear relationships visually in order to understand what is happening otherwise it becomes a weakness as there may be a relationship that is missed meaning further research on experiments are not used to measure the topic further.