4.2.3 CORRELATIONS Flashcards
what is correlation?
- correlation doesn’t mean causation - it means association
- it’s a measure of the extent to which two variables are related
- an analysis of the relationship between co-variables
what happens in correlational research?
- the variables aren’t manipulated and instead two co-variables are measured and compared to look for a relationship
- one or both co-variables may be pre-existing
- each ppt has two scores
- scattergraphs will show the outcome
ie) positive / negative / zero
what is a positive correlation?
- relationships between 2 variables
- both variables move in the same direction
- when 1 variable increases as the other variable increases
- 1 decreases as the other decreases
what’s a negative correlation?
= relationship between 2 variables
- an increase in 1 variable is associated with a decrease in the other
what is a zero correlation?
- exists when there’s no relationship between 2 variables
how is a correlation expressed visually?
- done by drawing a scattergram
aka: scatterplot, scatter graph, scatter chart, scatter diagram - is a graphical display that shows the relationships / associations between 2 numerical variables
- represented as points for each pair of score
- indicates the strength and direction of the correlation between the co-variables
how do you draw a scatter graph?
- it doesn’t matter which variable goes on the x-axis and which goes on the y-axis
- put a cross at the point where the 2 values coincide
- draw a straight line of best fit through the points
how can a correlation be expressed other than graphically?
- by calculating the correlation coefficient which is expressed numerically
- this represents both the direction and the strength of the relationship between co-variables
- expressed as a value between -1 to +1
when working with continuous variables, the correlation coefficient to use is Pearson’s r
what does this indicate?
- correlation coefficient (r) indicates the extent to which the pairs of numbers for these 2 variables lie on a straight line
how is:
1) a perfect positive correlation
2) a perfect negative correlation
3) no relationship
expressed using a correlation coefficient?
and how can all coefficient correlations be described?
1) +1
2) -1
3) 0
- both +ve and -ve coefficient correlations can be described as weak, moderate or strong
ie) 0.03 = a weak positive correlation
-0.08 = a strong negative correlation
what are some uses of correlations?
prediction
- if there is a relationship between 2 variables, we can make predictions about one from another
validity
- concurrent validity (correlation between a new measure and an established measure)
reliability
- test-retest reliability (are measures consistent)
- inter-rater reliability (are observers consistent)
theory verification
- predictive validity
what do values of -1 and +1 mean?
- values over 0 indicate a positive correlation
- values under 0 indicate a negative correlation
- correlation of -1 indicates a perfect negative correlation
-> as one variable goes up, the other goes down - correlation of +1 indicates a perfect positive correlation
-> as one variable goes up, the other goes down
what are some strengths of correlations?
1) allows the researcher to investigate naturally occurring variables that maybe unethical / impractical to test experimentally
2) allows the researcher to clearly and easily see if there’s a relationship between variables
- this can be displayed in a graphical form
what are some limitations of correlations?
1) is not and cannot be taken to imply causation
- even if there’s a very strong association between 2 variables we cannot assume that 1 causes the other
2) doesn’t allow us to go beyond the data that’s given
