Correlation

The benefit of using a correlation coefficient to measure the relationship between two variables as opposed to using covariance is that the unit of measurement doesn't matter.

Remember that correlation does not show causation. That is, you could easily show that as the number of ice cream cones consumed increases during a year, so does the number of drownings. But this does not mean that eating ice cream causes people to drown-more likely, these variables are both independently related to another variable-that of temperatures.

Correlation is symmetrical, so you get the same coefficient if you switch the variables. Don't calculate a correlation coefficient if you manipulated one of the variables. Use linear regression instead.