Correlations

Question 1

What is a correlation?

Answer 1

• A statistical analysis of the relationship between 2 co-variables
• They investigate the strength of the relationship between 2 co-variables

Question 2

What is the difference between correlations and experiments?

Answer 2

• Test of relationship between co-variables rather than the difference in DV caused by IV
• No IVs or DVs just co-variables
• No manipulation of variables

Question 3

What are the types of correlation?

Answer 3

1. Positive - as one variable increases so does the other
2. Negative - as one variable increases the other decreases
3. No/0 – no relationship between variables

Question 4

What do we have to include when drawing a scatter graph?

Answer 4

1 mark = detailed title e.g. ‘A Scatter graph depicting the relationship between __ and __
2 marks = labelling the axes – MUST USE UNITS
1 mark = accurate plotting

Question 5

What are correlation coefficients?

Answer 5

• The strength and direction of a correlation can be expressed as a numerical value known as the correlation coefficient
• Negative coefficient = negative correlation, positive coefficient = positive correlation
• 1-0.7 = strong, 0.6-0.4 =moderate, 0.3-0.1 = weak, less than 0.1 = no correlation

Question 6

What is a strength of correlations?

Answer 6

• Good preliminary tools of research – offer a good starting point as they help identify 2 variables that are related allowing grounding for further investigation into this relationship using methods such as lab experiments to identify cause and effect
• Unlikely to be unethical as only involve gathering/measuring data and no manipulation of variables. Thus are useful to measure variables that may be unethical to manipulate in experimental settings

Question 7

What are the weaknesses of correlations?

Answer 7

• As variables are not controlled and can’t be manipulated in any way, correlations only inform us that 2 variables are related and occur at the same time and not that one variable causes the other. Thus we can’t establish a cause and effect between 2 variables. Also there could be a third variable at play affecting both variables