research methods: correlational research

Question 1

what is a correlation?

Answer 1

• a way of looking at relationships between two variables. assesses the degree to which the two co-variables are related
• can be positive or negative
• positive correlation: when high values of one variable equals high values of the other
• negative correlation: when high values of one variable equals low values of the other
• if there is no correlation between two variables they are said to be uncorrelated

Question 2

what are the three important features of a correlation design?

Answer 2

1) there is no independent or dependent variables. there are two variables of equal importance e.g shoe size and height
2) the hypothesis will be about a relationship between two variables (not about a difference’
3) hypothesis could be directional as it could predict a positive or negative correlation e.g. there is a positive relationship between length of time in analysis and the benefit of therapy. or non-directional as it could just state that there will be a relationship but not state + or -

Question 3

can are co-variables measured?

Answer 3

• they can be measured directly by the researcher, of obtained via secondary data gathered from other sources

Question 4

how do you analyse correlations?

Answer 4

• list both sets of scores and then rank set of scores separately
• this involves ranking data starting from the lowest score and giving that rank 1 and continuing
• if there are two or more scores the same, allocate all those scores to the same rank by finding the middle rank e.g. if there were two scores of 20 that would be ranked 3 and 4 give them both rank 3.5. if there were three scores of 20 that would be ranked 3, 4 and 5 give them all a rank of 4
• second way is to draw a scatter graph - just like plotting - and look at the line of best fit to see whether there is a correlation or not
• you can also use a statistical test - spearman rank correlation coefficient

Question 5

when does a correlation indicate that a relationship exists?

Answer 5

• an ’eyeball’ test
• looking at the data sets to see how they compare is useful, but it is difficult to draw firm conclusions from
• a statistical test (spearman test) needs to be carried out to see if the relationship is real for the group

Question 6

how do you interpret the results of the test?

Answer 6

• if both scores rise, there is a positive correlation. a result of +1 means a perfect positive correlation. there is a perfect relationship between the two scores
• a result of 0 means there is no correlation. the scores **do not relate to each other
• if one score rises and the other falls there is a negative correlation. there is a **perfect relationship between the two scores

Question 7

strengths of correlations

Answer 7

• correlational analysis provides a means of looking at relationships and determining whether the relationship is significant
• correlation is a useful way to conduct preliminary analysis on data
• correlational research may stimulate further investigations if a significant relationship is found between the co-variables. e.g. an experiment to then be able to establish a causal link

Question 8

weaknesses of correlations

Answer 8

• correlations cannot show cause and effect relationship (causality) as there is no iv that has been deliberately manipulated
• if co-variables are correlated one may be causing the changes in the other but we do not know the direction of the possible effect. e.g. research shows there is positive correlation between number of hours spent playing violent video games and aggressiveness. it might be that watching violent video games is increasing aggressiveness, or it could be more aggressive people choose to watch violent videos
• there may be intervening variables that can explain why the co-variables are linked

Question 9

what is the correlation coefficient?

Answer 9

• strength of the correlation
• less than 0 = neg
• more than 0 = pos
  0-0.3 = weak
  0.3-0.7 = moderate
  0.7-1 = strong