research methods: correlations Flashcards
What do correlations illustrate?
The strength and direction of an association between to or more co-variables
What is positive correlation?
As one variable increases so does the other
What is negative correlation?
As one variable increases, the other decreases
What is zero correlation?
There is no relationship between the co-variables
What is a correlation coefficient?
Represents both the strength and direction of the relationship between co-variables as a number between -1 and +1
What correlation co-efficient shows a strong correlation?
Equal to or greater than +0.80
What is perfect correlation?
When there is a correlation coefficient of +1
What happens in an experiment?
- the researcher controls/ manipulates the IV to measure the effect on the DV
- As a result of this deliberate change in one variable, it is possible to infer that the IV caused any observed changes in the DV
What happens in a correlation in contrast?
- There is no manipulation of one variable -> it is not possible to establish cause and effect between co-variables
- ‘other variables’ may influence the co-variables known as intervening variables
What are the 3 main differences about experiments?
- Independent and dependent variables
- Measures cause and effect of independent variable on dependent variable
- Can be influenced by extraneous variables
What are the 3 main differences about correlations?
- Co-variables
- Measures relationships between 2 variables
- Can be influenced by third variables called intervening variables
What is one strength of correlations?
Useful as a primary tool
- Correlations provide a quantifiable measure of how two variables are related
- if two variables are strongly related, this might suggest ideas for later research
What is a counterpoint to this strength?
If two variables are related, this does not always mean that one might have caused the other
What is another strength of correlations?
Quick and economical
- as correlations are only concerned with assessing the relationship between two co-variables, there is no need for a controlled environment or to manipulate variables
- secondary data can also be used (e.g. government statistics) which is less time consuming
What is one limitation of correlations?
Cannot demonstrate cause and effect
- due to the lack of experimental manipulation, studies can tell us how variables are related but not why
- we don’t know which co-variable is causing the other one to change. Therefore establishing the direction of the effect is an issue
- may suggest a relationship exists between co-variables but does not show which variable led to a change in the other variable