research methods.4) - correlation

• Experimental design


  Requires manipulation of an independent variable and measurement of the resulting change in the dependent variable
• Correlational study


  Does not involve the manipulation of an independent variable and measurement of the resulting change in the dependent variable, no variables are manipulated, two co-variables are measured and compared to look for a relationship
• Co-variables


  Two factors/variables that are measured by the researcher and compared to each other
• Scattergram


  A graph used to plot the measurements of two co variables and visually display the relationship between them
• Describing correlations


  • Perfect negative
  • Strong/moderate/weak negative
  • No correlation
  • Weak/moderate/strong positive
  • Perfect positive
• Correlation coefficient


  Represents strength and direction of the relationship between the co-variables as a number between -1 and +1, calculated using statistical tests and used to assess inter rater and test rested reliability, a correlation coefficient equal or greater to 0.8 is usually judged to show a strong correlation
• Correlation


  Does not show causation only suggests a relationship exists, doesn't show us which co-variable led to the change in the other co-variable and there could be third unknown variable that caused the change in both co-variables
• Correlation


  Can highlight potential causal relationships which can then be tested with experimental methods, covariable data is easily accessible so usually few ethical problems in data collection, correlation coefficient is a useful tool in describing both the direction and strength of relationship between factors