Correlations

• Why do we manipulate independent variables (IVs) in experiments?

  To test effects on a dependent variable (DV)
• What is the solution when manipulating IVs is not possible or ethical?

  COVARIANCE
• What does covariance measure?

  To what extent do variables co-vary?
• What is the definition of statistical co-variance?

  A measure of how two variables change together
• What does a positive covariance indicate?

  Variables tend to increase and decrease in tandem
• What does a negative covariance indicate?

  One variable tends to increase when the other decreases
• What is the cross-product deviation?

  It is the product of the deviations from the two sets of scores
• What does a positive cross-product deviation indicate?

  When one variable scores above average, the other tends to do the same
• What does a negative cross-product deviation indicate?

  When one variable scores above average, the other tends to score below average
• What are the rules of thumb regarding covariance?

  • Positive covariance: x and y increase together
  • Negative covariance: x goes up and y goes down, and vice versa
  • Zero covariance: no relationship
• What is Pearson’s Correlation Coefficient also known as?

  Pearson’s Product-Moment Coefficient of Correlation
• What type of data is Pearson’s Correlation Coefficient used for?

  Parametric data that is normally distributed
• What does Pearson’s Correlation Coefficient tell us?

  How much two variables are related to each other
• What is Spearman's Rho?

  A non-parametric version of the standard correlation coefficient test

  
• What is a key advantage of Spearman's Rho?

  It does not require the same assumptions as parametric tests
• When is Spearman's Rho often used?

  With ordinal or categorical data that do not meet parametric assumptions

  
• What caution is advised regarding correlations?

  Correlation does not equal causality
• What does correlation measure?

  The relationship (covariance) between variables
• What are the two types of correlation mentioned?

  • Pearson’s: parametric
  • Spearman’s: non-parametric

  
• What can we measure using covariance?

  The degree to which two variables vary with each other
• What are the two measures used to assess the relationship between variables?

  Pearson’s r and Spearman’s Rho

  
• What important note is made regarding correlation?

  Correlation does not imply causation
• What should be conducted before the correlation itself?

  Visual inspections and assumption tests