PSYCHOLOGY - CORRELATION
what are the correlation coefficient 3 features?
- number between -1 & +1 - indicates strengths & direction of relationship between two variables e.g. 0.0 indicates strong positive correlation - 0 = no correlation
what is positive correlation between? no correlation? negative correlation?
0 & +1 0 0 + -1
psychology
correlation
what is correlation analysis?
statistical technique that measures a relationship between two variables can be expressed graphically & as quantitative data in the form of a number +1 & -1 this is known as correlation coefficent
weaknesses?
unlike lab experiments where the research has control over extraneous variables in a controlled setting, a limitation of correlation analysis is that it is difficult to establish cause and effect, which is when we cannot establish a casual relationship between two variables, meaning that we cannot be certain that the recorded changes in the dv are being caused by the changes in iv. this is because we cannot be certain of the direction of the correlation as it is assumed that the iv is causing the change in the dv when in fact the direction of the correlation could be the other way round. for example it is assumed that stress (iv) leads to more stress related illnesses (the dv) however it may be that becoming ill (dv) may lead to stress (iv) unlike lab experiments where the research has control over extraneous variables in a controlled setting, a limitation of correlation analysis is that there is no control over extraneous variables, which is when variables not controlled by the experimenter ay randomly affect the dv. this is because correlations make use of a naturally occurring change in the iv and so do not have full control over confounding variables, such as third unknown variable that could cause the observed change in the dv.
strengths of correlation analysis?
unlike lab experiments, where research is performed in a controlled and artificial setting a strength of correlation analysis is that it allows researchers to investigate behaviour that would be unethical to study in controlled conditions. this is because correlation analysis makes use of a naturally occurring variation in the iv. for example i would be unethical to cause participants to have stress to see the side effect of illness
