Correlations

• Correlation


  A technique used by researchers to establish the strength of a relationship between two variables
• Positive correlation


  • A relationship between two variables in which as the value of one variable increases, the value of the other variable also increases
• Relationship

  A connection or association between two or more variables
• Strengths and weaknesses 

  -Correlation allows a researcher to see if two variables are connected in some way. This means that once a relationship has been found, the researcher can use a different method, such as an experiment, to try to find the cause of the results.

  -Correlation can be used when it would be impossible or unethical to carry out an experiment. Researchers cannot force people to smoke in order to see if they then develop lung cancer. However, plotting the rates of smoking against lung cancer does tell us that they are related.
• Negative correlation


  • A relationship between two variables in which as the value of one variable increases, the value of the other variable decreases
• No correlation


  • There is no relationship between two variables
• Prediction


  A statement about what will happen made before the event occurs
• • Correlation does not indicate which of the two variables measured caused the relationship to occur. It is sometimes the case that other variables are the cause of the pattern seen on a scatter diagram.

  • In order for a correlation to be informative, there does need to be a large amount of data for each variable so that the possible pattern can be seen. This means that the researcher needs to take lots of measurements of both variables so that the pattern in the data can be reliably identified. Correlations based on small populations are not very reliable.