CORRELATIONAL ANALYSIS - RM

correlational analysis

• mathematical way for looking for a relationship between co-variables

covariables

• variables measured in a correlation

• called this because both variables change and are measured but not manipulated

correlation coefficient

a number between -1 and 1 which represents the strength and direction of the relationship

positive correlation

as variable 1 increases, variable 2 increases

negative correlation

• as variable 1 increases, variable 2 decreases

null hypothesis

• there will be no relationship between variable 1 and 2

non directional

• there will be a relationship between variable 1 and 2

directional

• as variable 1 increases, variable 2 increases

experiments vs correlations

• experiments assess the affect of one variable, on another variable which is measured (DV)

• IV data must be sperate

• correlations do not use discrete separate conditions

• instead, assess how much of a relationship exists between two co-occuring variables which are related both on a scale

• experiments manipulate variables which allows causal relationships to be found

correlations strengths

• very useful as a preliminary research technique, allowing researchers to identify a link that can be further investigated through more controlled research

• they are often cheap and a good way to raise money

• If there’s no correlation, it’s probably not worth doing any more research

• can be used to resesrch topics that would otherwise be seen as sensitive

correlations weakness

• only identify a link: not cause and effect

• there may be a third variable present which is influencing one of the o variables

• hard to capture/display non linear patterns in data

• a simple correlation confuses this pattern with no correlation, because some is up and some is down

• overall the correlation score is low but there is a clear pattern