Correlation

Question 1

What is the purpose of a correlation study?

Answer 1

Investigate the strength and direction of a relatioship between two variables

Question 2

What are the three types of correlation?

Answer 2

• Positive
• Negative
• No correlation

Question 3

What do correlation studies investigate?

Answer 3

A relationship

Question 4

Strengths of Relationships in correlation

Answer 4

-1 = Perfect negative correlation
-0.75 = Strong negative correlation
-0.5 = Moderate negative correlation
-0.25 = Weak negative correlation
0 = No correlation
0.25 = Weak positive correlation
0.5 = Moderate positive correlation
0.75 = Strong positive correlation
1 = Perfect positive correlation

Question 5

Obtaining data for a correlational analysis

Answer 5

Primary and secondary data
Sampling method
Ethics

Question 6

What is primary data?

Answer 6

Data gathered directly by the participants

Question 7

What is secondary data?

Answer 7

Data that has already been gathered by someone other then the researcher.

Question 8

Descriptive statistics for correlations

Answer 8

The appropriate form of descriptive statistics to use to display the results of a correlational study is a scatter graph.
On the basis of how the crosses are distributed, it should be possible to make broad conclusions about whether there is any relationship between the co-variables and if so the direction and approximate strength of the relationship.

-1 = Perfect negative correlation
0 = No correlation
1 = Perfect positive correlation

Question 9

What does it mean when there is no correlation?

Answer 9

There does not appear to be a relationship between two sets of data

Question 10

What does it mean when there is a positive correlation?

Answer 10

A correlation where as one variable increases, the other also increases.
Both variables move in the same direction.
(Has a plus sign)

Question 11

What does it mean when there is a negative correlation?

Answer 11

As one data set increases the other decreases. (Has a minus sign)

Question 12

Operationalising variables in a correlation study

Answer 12

Any co-variable needs to be expressed as a number.
Each participant must have 2 separate (ordinal level) numbers that relate to them, one of reach co-variable.

Question 13

Advantages of a correlation study?

Answer 13

• Although correlations may not involve the collection of new data, they can still tell us something new.
• If it turns out the two co-variables are related, it wont just tell us that, but also the strength and direction of the relationship.
• There is no manipulation in a correlational study, it is a useful technique when either practical or ethical reasons mean that the variables cannot be manipulated.
• It can act as a good starting point for research because one relationships have been established between co-variables, more research can then be established to investigate hem further.

Question 14

Disadvantages of a correlation study?

Answer 14

• It can not tell us anything about cause and effect, just that there is a relationship between them. It doesn’t tell us why or take into account hidden third factors.
• Inferential statistical tests will not always pick up on a relationship between co-variables. e.g. a curvilinea relationship wont be picked up even though there is a genuine pattern to the relationship