Eval Academy

View Original

Correlation

A correlation is a measure of the strength of the relationship between two continuous variables. A correlation coefficient can range from -1 to +1. Values closer to 0 indicate a weaker relationship between the two variables, while values closer to +1 or -1 indicate strong relationships. A value of 0 means there is no relationship between the two variables at all. A positive correlation coefficient signifies a direct relationship between the two variables (e.g., as the outside temperature increases, ice cream sales also increase). A negative correlation coefficient signifies an inverse relationship (e.g., as the outside temperature increases, sweater sales decrease).

It is important to remember when interpreting correlations that just because two variables are correlated, it does not mean one caused the other (correlation is not necessarily causation). In the example above, perhaps the increasing temperatures did not cause the decrease in sweater sales - maybe the decrease in sweater sales was because there was a cotton shortage at the time. This would be called a spurious correlation.

See also: causation, spurious correlation

Return to the Evaluation Dictionary