0:00 / 0:00

Correlation



Correlation is a measure of how related scores on two variables are. A correlation is denoted by the symbol r.

Watch Out!
Just because two variables are correlated doesn't mean one caused the other! Correlation is not causation.
Photo by DethWench / CC BY
PAGE BREAK
A correlation has two components:
  • Positivity or negativity - which direction does the relationship go?
  • Value - how strong is the relationship, from 0 (no relationship) to 1.00 (perfect relationship). A correlation of -.70 and +.70 are equal in strength


Watch Out!
A correlation cannot be stronger than +1.00 or -1.00. If you see a correlation coefficient outside of those bounds it is a trap!


Practice: Correlations

We can best predict the value of one variable from another variable if they have a correlation coefficient of:

Practice: Correlation VS Causation

Research shows there is a positive correlation between the number of night clubs and churches in cities. We can conclude that: